Next Article in Journal
Evidence of the Intrusion of the Oceanic Lightfish (Vinciguerria nimbaria) into Korean Waters Based on High-Throughput Sequencing of Mixed Fish Eggs
Next Article in Special Issue
A Novel Variable Weight VIKOR Grade Assessment Method for Waterway Navigation Safe Routes Selection
Previous Article in Journal
Model Tests on Cyclic Responses of a Laterally Loaded Pile Considering Sand Anisotropy and Scouring
Previous Article in Special Issue
The Construction and Application of Dual-Objective Optimal Speed Model of Liners in a Changing Climate: Taking Yang Ming Route as an Example
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:

Application of Artificial Intelligence in Marine Corrosion Prediction and Detection

Faculty of Ocean Engineering Technology and Informatics, Universiti Malaysia Terengganu, Kuala Terengganu 21030, Terengganu, Malaysia
Faculty of Maritime Studies, Universiti Malaysia Terengganu, Kuala Terengganu 21030, Terengganu, Malaysia
Department of Electrical, Electronic and Systems Engineering, Faculty of Engineering and Built Environment, Universiti Kebangsaan Malaysia, Bangi 43600, Selangor, Malaysia
Faculty of Innovative Design and Technology, Universiti Sultan Zainal Abidin, Kuala Terengganu 21030, Terengganu, Malaysia
Author to whom correspondence should be addressed.
J. Mar. Sci. Eng. 2023, 11(2), 256;
Submission received: 18 December 2022 / Revised: 7 January 2023 / Accepted: 17 January 2023 / Published: 21 January 2023
(This article belongs to the Special Issue State-of-the-Art in Maritime Safety and Smart Shipping)


One of the biggest problems the maritime industry is currently experiencing is corrosion, resulting in short and long-term damages. Early prediction and proper corrosion monitoring can reduce economic losses. Traditional approaches used in corrosion prediction and detection are time-consuming and challenging to execute in inaccessible areas. Due to these reasons, artificial intelligence-based algorithms have become the most popular tools for researchers. This study discusses state-of-the-art artificial intelligence (AI) methods for marine-related corrosion prediction and detection: (1) predictive maintenance approaches and (2) computer vision and image processing approaches. Furthermore, a brief description of AI is described. The outcomes of this review will bring forward new knowledge about AI and the development of prediction models which can avoid unexpected failures during corrosion detection and maintenance. Moreover, it will expand the understanding of computer vision and image processing approaches for accurately detecting corrosion in images and videos.

1. Introduction

Corrosion is the chemical decomposition of the metal into its components by interacting chemically or electrochemically; corrosion degrades metals into their oxides and sulfides [1]. Because of its interdisciplinary approach, corrosion has become one of the most challenging parts of science and engineering [2]. Moreover, corrosion poses significant short-term and long-term threats that cost billions of dollars [3]. According to the NACE, corrosion cost approximately 2.5 trillion US dollars, or 3.4% of the global GDP in 2013 [4]: (1) the direct costs include the price of supplies, labor, upkeep, and the expense of replacing corroded equipment, (2) the indirect costs of corrosion include production losses, environmental effects, transportation delays, injuries, and fatalities [5,6]. Of the 3–4% of GDP [7], 15–35% of this sum is believed to be preventable, with a significant portion linked to inspection costs [8].
In the shipping industry, marine structures are significantly damaged by corrosion, which will reduce the efficiency of mechanical properties and the different structural parts [9], such as hull structural failure [10]. Statistical data [11] shows that corrosion is responsible for approximately 90% of ship structural failure costs. Therefore, long-term corrosion detection is an excellent method to prevent catastrophic marine structure accidents. In addition to financial advantages, early detection of structural deterioration before failure can also minimize hazardous situations for both people and the environment and prevent catastrophic failures of structures [12,13]. The approximate cost can be reduced by 18–35% using proper strategy [4]. Furthermore, using the current artificial technologies, 20–25% of the yearly direct cost could be reduced [14,15].
In 1997, Sharon and Itzhak [16] employed image processing to explore how corrosion affected stainless steel. The most significant advantage of that method is that it can identify nearly entirely superficial defects (cracks and corrosion). However, it requires substantial human resources, workload, and financial resources. Feature extraction methods are often used in corrosion detection [17]. Therefore, developing other methods for corrosion prediction and detection is essential. Consequently, new ways of artificial intelligence have been able to attract researchers because of enormous advantages over human intelligence [18,19], advanced technology to solve complex problems [20,21,22], faster decision making [23] such as big data, machine learning (ML), deep learning (DL), neural networks (NN), face recognition, pattern recognition, image classification, and recognition, character recognition [24,25,26,27,28]. Cost reductions and risk reductions have been the driving forces for research into automated corrosion detection over the past ten years [29,30,31,32,33,34].
This paper aims to deliver a state-of-the-art review of artificial intelligence methods in corrosion prediction and detection from 2017 to 2022. Table 1 represents the review corresponding to the review protocol. A search of the chosen databases followed by curating a list of literature has resulted in 379 notable works on this topic. These studies were analyzed within the research scopes, where 151 studies were chosen to be explored in this work.
The discussion in this paper is divided into two sections. First, a description of artificial intelligence and its branches, such as; pattern recognition, machine learning, and deep learning, is elaborated. Additionally, three subdivision of machine learning (reinforcement learning, supervised education, and unsupervised learning) is discussed. Second, the artificial intelligence approaches in corrosion detection and prediction are elaborated. Two primary corrosion detection and monitoring methods are discussed: (1) predictive maintenance approaches and (2) computer vision and image processing approaches.

2. Artificial Intelligence

Artificial intelligence (AI) is a machine’s capability to impersonate human behavior, respond perceptively, solve problems and make decisions automatically without human interference or with less human interference. The main objective of AI research involves general intelligence, automated planning, perception, natural language processing, knowledge representation, and robotics [35,36,37,38,39]. AI applications, for example, machine learning (ML), deep learning (DL), pattern recognition (PR), evolutionary computation, neural networks, expert systems, discriminant analysis, metaheuristic optimization, swarm optimization, image processing, and computer vision, have been used in marine research. Among those technologies, pattern recognition, deep learning, and machine learning are the most consistent and effective methods in corrosion engineering [23]. In this section, we have illustrated the technical background of the main artificial intelligence branches (machine learning, pattern recognition, and deep learning). The artificial intelligence techniques are shown in Figure 1, along with their correlation.

2.1. Pattern Recognition

The main objective of pattern recognition is to classify objects into several classes. The objects could be signals, speech, images, or handwriting, depending on the application [40,41]. Several elements collectively serve to represent a pattern; the statistical theory is used to define decision boundaries across pattern classes. The pattern recognition system is divided into two modes: learning and classification (Figure 2). Learning and classification are called training and testing; in the learning mode, the selection module and feature extraction disclose the relevant features for describing the input patterns, and the classifier is taught to partition the feature space. The input patterns are assigned to a particular class by using the trained classifier, whereas the performance of the designed classifier, such as the system evaluation module, evaluates the classification error rate. Generally, pattern recognition can be categorized into two groups: supervised PR and unsupervised PR. Unsupervised pattern recognition uses training data that are not leveled, whereas supervised pattern recognition uses a collection of labeled training samples. Additionally, there is no preceding information concerning class level. Unsupervised PR is also called clustering. The generative and discriminative pattern recognition models and their algorithms are shown in Figure 3.
As there are few applications of pattern recognition in corrosion, researchers [42] used a PRS (pattern recognition system) based on electrochemical noise (EN) to detect the uniform and pitting corrosion and passivation of 304 steel (EN). They discovered that the PRS-EN parameters’ accuracy of 99.7% was higher than those created using only statistical parameters (92.4%) and principal component analysis-selected parameters (97.8%). The same approach was used by [43,44] to identify the type and rate of corrosion in metal coatings and onshore pipelines using inline inspection (ILI) [45].

2.2. Machine Learning (ML)

ML is a subdivision of artificial intelligence. Building and developing mathematical models that can be trained to process extensive information is the goal of machine learning [46]. The primary objective of ML is to create and improve mathematical models that can be taught without having complete knowledge of all the external factors that influence decisions [47,48,49,50]. Additionally, these methods are trained by given data and capable of solving problems without or with minimum human intervention. Furthermore, it can predict future actions utilizing complex learning and indicating algorithms [46,51,52,53,54,55]. These models can either be predictive to perform decisions, acquire knowledge from data or both [56,57]. ML models have been successfully utilized in numerous fields of research, such as computational finance [58,59], image and speech processing [60,61], energy production [62,63], hydrology [64,65], and computational biology [66,67]. Over a few decades, it has brought substantial advancement in science and engineering along with developments in the eminence of our daily life.
Pattern recognition (PR) and deep learning (DL) are AI subsets that generally differ. Since PR and ML are thoroughly linked fields, their application areas primarily overlap [23]. However, ML focuses on learning algorithms, while PR concentrates on approaches for classification tasks [68]. The primary responsibility of pattern recognition is to identify patterns in data. Besides, learning is not required to categorize them. However, ML systems are built with the ability to learn on their own. Alternatively, Machine learning systems are created to learn independently [23].
A subset of machine learning is called deep learning. In reality, data representation can be learned using DL, and ML problems can be solved once the representation is created. Without a doubt, a high-dimensional challenge has its dimensions reduced via deep learning. The three primary subcategories of ML algorithms are reinforcement learning, supervised learning, and unsupervised learning. Figure 4 shows different machine learning categories. An overview of these groups is provided in the following chapters.

2.2.1. Supervised Learning

In supervised learning, one or more output variables are predicted based on the input variables’ values. The training data set with n samples and accompanying output values might serve as an example of an input variable (labels). The output variable could be a continuous variable (regression problem) or a discrete variable (classification problem) [68]. In contrast to classification, regression is used whenever an ML model aims to predict continuous target variables [23]. Applications for supervised learning include software engineering [69,70,71,72], natural language processing [73], computer architecture [74], and seafaring. The two main supervised learning techniques categories are parametric and non-parametric models. The parameters are fixed in parametric and non-parametric models, and the number of parameters depends on the training set [68]. Figure 5 depicts a common generic model of supervised learning.

2.2.2. Unsupervised Learning

Unsupervised learning uses a machine learning algorithm to cluster and analyze unlabeled datasets [75]. These algorithms can group data and discover hidden patterns without human intervention. Algorithms used in ML approaches are accustomed to concluding datasets with input data but no labeled responses. To develop the prediction model, the data is explored to detect hidden patterns or structures. Beforehand the algorithm is not instructed on what to do; henceforth, the algorithm must discover what is in the data. Clustering is the most common unsupervised learning used to find the possible grouping or inherent pattern in the given data. The Gaussian mixture model and k-means are types of clustering approaches [76]. A typical general unsupervised learning model is shown in Figure 6 and Table 2.

2.2.3. Reinforcement Learning

Reinforcement Learning is a machine learning algorithm that allows the machine or software agents to intelligently regulate the best behavior within a definite context and exploit the performance. RL models are enforced to learn optimum objectives through the trial-and-error method [77]. As shown in Figure 7, the RL paradigm enables an agent to remember by investigating the potential actions and modifying its behaviors in response to the reward. Exploiting the long-term performance is the main focus of the agent. Therefore, the agent can consider future outcomes and the present reward for individual activities. RL is predominantly more efficient in dynamic and not completely deterministic environment RL [68]. Recent research discloses that RL has been applied in many different fields, such as speech recognition [60,61,78,79,80,81], computational biology [82,83,84], computational finance [85,86,87], computer vision, and image processing [88,89,90,91,92,93], energy production [94,95]. Various field methods have been adopted for this purpose [96,97]. Figure 8 displays some of the most popular algorithms used in machine learning.

2.3. Deep Learning (DL)

Deep learning is a subset of machine learning and is essentially a three-or-more-layer neural network. A single layer can make predictions, but an additional hidden layer enhances and improves the correctness. These neural networks can learn from big data and act as the human brain [23]. Deep learning techniques are applied in many areas: law enforcement, finance, customer service, engineering technology application [98], turbines [99], aero engines [100], bearings [101], etc. Although deep learning models can significantly improve integrity estimation, a recent assessment found that they have not been used in corrosion [102]. Deep learning models can be crucial in corrosion prediction integrity estimates [103]. A notable result was obtained by [104] utilizing a deep learning method to measure the corrosion rate in a natural gas pipeline using a back-propagation artificial neural network (BP ANN). Artificial neural networks operated by [105] predicted the CO2 corrosion rate. The same method was used by [106] to indicate the internal corrosion rate. In the following chapter, corrosion detection approaches are discussed.

3. Corrosion Detection Approaches

This section is divided into two subsections: (1) predictive maintenance approaches for corrosion detection and (2) computed vision and image processing techniques. A short introduction about corrosion is present at the beginning of this section.
Corrosion is a natural phenomenon [107] that happens when metallic materials gradually convert into undesirable substances, such as hydrogen, oxygen, bacteria, and electrical current, due to the chemical and electrochemical response to the encompassing environment. Moreover, corrosion is inevitable and susceptible to the degradation of metallic materials [108]. The anodic and cathodic electrochemical reactions are involved in the corrosion process [109]. Corrosion is categorized according to environmental exposure and attack morphology. General or uniform attack, galvanic or two-metal corrosion, pitting, intergranular corrosion, selective leaching, erosion corrosion, and stress-corrosion cracking are the eight types of corrosion [110]. A general attack is a uniform electrochemical reaction that happens on the entire surface of a material. This kind of corrosion is predictable and can be contained. Galvanic or two-metal corrosion occurs between two metals due to the potential difference when both metals are submerged in a corrosive solution [111]. The resistant metal becomes a cathode, while the less resistant metal becomes the anode. The cathode metal will corrode less than the anode metal. Localized corrosion, called crevice corrosion, occurs when there are limited volumes of stagnant solution. It always attacks the lap joints, gaskets, and holes; pitting is the most intense corrosion form. It is a localized attack and can create holes in the metal.
Moreover, it is hard to locate them as they are covered with corrosion products. Intergranular corrosion is a localized attack on the grain boundaries. This type of corrosion creates a small, corroded area. Selective leaching happens when one element of an alloy is removed from it [112]. This phenomenon occurs in chromium, cobalt, iron, aluminum, and zinc. Erosion corrosion happens because of the rapid movement between a metal surface and a corrosive fluid, which accelerates the corrosion process. Abrasion and mechanical wear are also involved. Tensile stress and the corrosive media contribute to stress-corrosion crack propagation. A crack is produced from the steel caustic embrittlement and brass season cracking. These eight forms of corrosion can occur in the pipeline, ship hulls, bronze statues, copper roofs, steel bridges, metallic equipment, and many more. In terms of ship structures, fatigue and corrosion can reduce the strength of ships and vessels, which can cause structural failures [113]. The primary corrosion elements of the ship structures are the single metal element (ship hull).
Meanwhile, ship structures are categorized into the atmospheric and immersed zones of stiffeners and plates. The factors influencing corrosion in the atmospheric zone are temperature, humidity, steel type, ventilation, pressure, carbon dioxide, sulphuric acid, oxygen, sulfur dioxide, and chloride concentrations. Meanwhile, the immersed zone’s main influencing factors are the seawater pressure, pH value, seawater velocity, temperature, salinity, carbon dioxide, sulphuric acid, and hydrogen sulfide concentrations. Because of that, a good maintenance strategy must be adopted for corrosion detection and maintenance activities. The cost of corrosion is high and estimated to be billions of dollars, which burdens the related industry if it is not detected in the early stage [20]. Due to that, numerous approaches have been established to reduce and minimize the impact of corrosion on the industry [114]. In the following subsection, we present predictive maintenance approaches for corrosion detection.

3.1. Predictive Maintenance Approaches for Corrosion Detection

Predictive maintenance (PdM) is a strategy involving detecting the early signs and acts of breakdown by doing proactive maintenance work [115]. A smooth operation can be ensured by attending to and acting on any failure, even if there is no major breakdown of the materials. PdM contains a set of mathematical models that will detect when the error happens and when to do maintenance [1]. The main objectives of PdM are to reduce maintenance time, production downtime, and the cost of component supplies. Due to that, PdM has been used in various industries to ensure the quality, efficiency, reliability, and safety of equipment and materials. Recently, PdM has been gaining attention in corrosion detection and maintenance due to its efficiency in predicting and determining an affected material’s corrosion level. It can be categorized into knowledge-based, physic-based, data-based, and hybrid models [116]. In the following subsection, a brief description of those approaches is provided.

3.1.1. PdM with Knowledge-Based Model

The PdM knowledge-based model is a model that uses cases, facts, rules and experiences in developing its prediction model [117]. The data on maintenance and operation are gathered over many years. Recently, IR4.0 allowed this model to be integrated and automated with machine learning, statistical and artificial intelligence.
A framework of impressed current cathodic protection (ICCP) system was introduced in [118], where the machine learning and historical data were used to predict the downstream test post. This knowledge-based model was evaluated with survival, regression and classification analysis. The knowledge in the test post potential was used to estimate and detect the corrosion progress and maintenance time. According to the results, the proposed method managed to create an external corrosion prevention mechanism for effective corrosion control. Despite that, this model used many AI approaches, which can increase the complexity of the developed prediction model.
The vast knowledge of sulfur was used by [119] to investigate the existing maintenance strategy in the maritime industry. The new marine fuel caused a big challenge due to the consistent changes in physical and chemical properties, which can contribute to the corrosion progression. Thus, the planned maintenance work will be inadequate, which can endanger ships’ operations. The very low sulfur fuel oil (VLSFO) characteristic was monitored with PdM to reduce the critical risk potential. Based on the results, the proposed method managed to provide corrective action and detection for corrosion from sulfur emissions. Nevertheless, this prediction model was determined to evaluate the Sulphur 2020 amendment.
The rules of hull girder [120] were used to assess the corrosion effect on the bulk carrier. The web section and flange section on the cross-section property and vertical bending moment were investigated to determine the residual strength of the ship hull. Then, a prediction model was developed from the incremental-iterative method and probabilistic corrosion rate estimation model. The parameters of cross-section property, neutral axis position and vertical bending moment were measured to determine the accurate maintenance activities. The results showed that the proposed method could detect and reduce the corrosion effect on the ship hull. However, the lack of historical data can affect the sensitivity of the prediction model for maintenance planning. The unplanned and unexpected corrosion behavior can still occur even with an accurate prediction model.
The reliability, availability and maintainability (RAM) analysis [121] was developed to predict the future trends of maintenance planning. The real-time data from the fuel injection valve case were measured from the container ship. The valve itself can be affected by corrosion which can reduce the efficiency of ship engines. According to the result, the developed prediction model can enhance the routine and non-routine maintenance activities on the ship engine. Nevertheless, the optimization of the prediction model can be done to further increase the reliability of maintenance planning.
The other PdM knowledge-based corrosion prediction models include the marine steel structures based on the climatic condition cases [122], the facts of ferrography lubricants [123], the rules of double hull girder tanker [124] and the experiences of random field approach [125].

3.1.2. PdM with Physic-Based Model

The PdM physic-based model is a prediction model that uses physics laws, real conditions, original equipment and the behavior of the tool or material. Recently, a digital twin was developed from the subject itself and then compared with the behavior of the physical tool or material. Due to that, the digital twin can be fine-tuned to operate and match the function of the actual subject.
The under-deposit corrosion (UDC) on the firetube boiler [126] was investigated to improve the predictive maintenance of the system. The three-pass seawater steam boiler was monitored for six years to obtain the necessary data. According to the result, the corrosion on the firetube boiler was formed from the hematite minerals and carbonates. Nevertheless, the usage of UDC propagation and phosphate congruent control (PCC) managed to improve the prediction model of predictive maintenance. Despite that, the prediction model itself might not be suitable for the other boilers because of the different parameters and external environment in the workplace.
Wear debris analysis (WDA) [127] was proposed to analyze the wear conditions of the industrial gearbox with the different types of wear failure and gear pitting modes. The moisture corrosion-attacked wear, contaminant-induced abrasive wear and acid attack were simulated on the industrial gearbox in order to monitor and create a prediction model for predictive maintenance. Based on the results, the wear debris morphological analysis managed to detect and anticipate wear and its mechanism. The studied parameters were typical for the industrial gearbox. However, the size, brand and configuration might reduce the accuracy of the developed prediction model since most of the industrial gearboxes were custom-made.
Furthermore, the UHF RFID (Ultra High-Frequency Radio Frequency Identification) sensor [128] was developed to detect corrosion steel in the marine environment. The steel deterioration happened due to the broken thin oxide film layer because of the presence of chloride. Hence, the UHF RFID sensor detected the corrosion area by calculating the difference between the steel layer and the concrete moisture degree. It can measure up to a few micrometers thickness of the metallic film. According to the result, the proposed method managed to monitor and control the mass loss of steel. However, this method did not use PdM in its process. The developed sensor network could be suitable and accurate for developing a PdM physic-based prediction model.
The study on the effect of long-term corrosion in physical infrastructure [129] was proposed to determine the most suitable mathematical model, especially for the marine corrosion of ships. The effect of marine corrosion, such as crevice severity and pit depth, was investigated to create efficient maintenance decision-making. The empiricism degree of corrosion was compared with the available prediction model. However, the historical data on corrosion progression under oxygenated conditions might require several decades to collect. This can increase the complexity of the prediction model.
The Weibull distribution [130] was introduced as the prediction model for the aging ship structural corrosion. The prediction models were developed from the degradation process of stiffener and plate. The ship structures were grouped into the zone, compartment, and structural types, such as longitudinal deck girder, stringer deck, top wing plating, inner side wall, inner bottom, side shell, bilge keel, deck, hopper plating, hatch coaming, bottom plating, machinery space, void space, ballast water tank, fuel oil tank, freshwater tank, cargo hold, atmospheric zone, splash zone and immersed zone. The developed prediction models can be individually adjusted for each ship’s structural elements from the real-time data and historical data. This prediction model can also be fine-tuned by calculating the means of influencing factors. Based on the result, the proposed method can predict corrosion at the aging ship structures. Despite that, this model required large data for each fine-tuning of the ship’s structural elements. The data can be analyzed at the edges or sensor nodes and stored in the cloud in order to reduce transmission costs and data transmission errors.
The other PdM physic-based corrosion prediction models include the prognostic of physics-of-failure [131,132], RUL of ship hull structure profile [133] and ship hull tanker profile [134]. These physics models were validated and compared with the respective simulations.

3.1.3. PdM with Data-Based Model

The PdM data-based model is a prediction model that uses a data-driven approach in its implementation, such as stochastic, statistical, and machine learning. This prediction model is heavily dependent on real-time and historical data. Due to that, the presence of noise and uncertainty in data could affect its behavior. Validation with the knowledge-based and physic-based models is required to verify its result. Despite that, not all prediction models with machine learning, statistical and artificial intelligence are considered data-based models. The core or fundamental of the developed prediction model will determine its own category.
The data-based model was proposed for corrosion failure prediction with extreme value analysis (EVA) [135]. EVA was used to make predictions of the depth of pits that required immediate maintenance. The real-time data of the degradation process from the inspection reports were used to develop a prediction model by considering the peaks over threshold (POT). The developed prediction model was validated with the block maxima (BM) approach to assess corrosion failure. This prediction model achieved high performance in detecting and assessing corrosion failures. However, this prediction model was not implemented in the multiple sections in the same workflow. The prediction model might require fine-tuning and parameterization for assessing multiple sections of corrosion failure.
The framework of Bayesian inference [136] was constructed to predict corrosion defects. The prediction model used both real-time data and historical data for the employment of generalized extreme value distribution (GEVD). The real-time data were frequently updating the model, while the historical data were indirectly assisting the corrosion defect distribution. This prediction model achieved the highest reliability and can adapt to the defect depth distribution. Nevertheless, the real-time data were quite sensitive for parameter estimation, even with guidance from historical data. This could reduce the accuracy of the developed prediction model if the historical data were unavailable.
The combination of the expected behavior (EB) model and the exponentially weighted moving average (EWMA) was introduced in [137] for the shipboard corrosion system. The learning potential was explored from the recorded voyage data. This prediction model can detect certain fault parameters, such as air pressure and gas temperature, that could be useful for developing a corrosion model. Despite that, the well-maintained ship was inevitable due to the occurrence of failures which can exhibit energy efficiency, safety and reliability. Such conditions can contribute to corrosion and fouling in the turbocharger and nozzle ring of the vessel.
The new innovative prediction model [138] was developed with time-series anomaly detection and machine learning. The maintenance decision-making was provided by the board sensors on the engine and ship hull. The lifetime of the hull managed to be extended with reduced maintenance costs. A huge amount of data was available through the data sources’ exploitation and deployment. The results showed that the proposed method could predict corrosion on specific parts of the ship’s engine. Nevertheless, the sensors’ placement was on the specific parts of the vessel, which can reduce the accuracy of the prediction model. The model itself might need fine-tuning and parameterization for the different parts of the vessel.
The mathematical model was adopted from the real-time data of the ship’s ballast tank [139] to predict corrosion damages on the ship structure. The nonlinear time-dependent formulation was derived from the probability density function (PDF) method by selecting the best fit of the real-time corrosion data. Then, the curve fitting method was selected for sub-parameters. According to the results, the adopted prediction model was accurate for determining RUL and corrosion damage over time. Despite that, the prediction model might require fine-tuning for each nearshore, offshore, onshore, and ship structures.
The other PdM data-based corrosion prediction models include the 25 years of monitoring of historical data of ship hulls [140], the condition-based predictive maintenance of customized self-healing systems [141], the spatial dependence of material, geometric and corrosion growth properties [142], and the synthesized life-cycle risk analysis framework [143].

3.1.4. PdM with Hybrid Model

The PdM hybrid model is a combination of at least two PdM prediction models from the knowledge-based, physic-based or data-based models. This prediction model has different configurations than the multi-model PdM. Due to that, not all multi-model PdM can be considered as a hybrid model.
Big data and machine learning were used in [144] to initiate solutions for the shipping industry, such as for hull corrosion. This hybrid method used the sensor network to collect both real-time data and historical data to reduce disruption during operations. The results showed that the number of breakdowns and failures could be reduced with PdM. The key parameters demonstrated the strong correlation and influence between equipment. The maintenance decision-making was improved in terms of accuracy and speed. Even though this method can create an efficient prediction model, it probably can create disruption within the shipping industry due to its implementation complexity. Furthermore, the potential failure mode and failure identification mode must be defined prior to developing the prediction model.
The strain sensing method [145] was developed for the detection of thickness loss in the ship hull. The hybrid model of structural health monitoring and classical detection tool was investigated for hull structure maintenance and corrosion detection. The real-time data and historical data were collected from the in-situ sensors. The damaged ship hull conditions were estimated with a Monte Carlo simulation. Then, the Gaussian and mean-shifted methods were considered to measure the deterministic signals from the static strain. The results showed that the strain measurement could be used for the detection of thickness loss in the ship hull. Nevertheless, this method did not consider the effect of noise in the historical data, which can challenge the dynamic of the signal.
The risk-based maintenance scheduling [146] was reviewed and applied for ships and vessels. Previously, this method was implemented in other industries. The decision analysis and probabilistic modeling were suggested for the decision-making of the prediction model. The fatigue crack propagation and corrosion scenario were used for the optimization of the prediction model. The reliability-centered maintenance (RCM) was also combined with the current framework for the evaluation of the prediction model in terms of maintenance cost and availability. The proposed prediction model achieved a reduced maintenance cost. It also managed to detect corrosion from risk-based scheduling. However, the prediction model was still in development and not integrated with the sensor network.
The computerized maintenance management system (CMMS) [147] was used as a framework for the prediction model of all maintenance activities on board the ship. This prediction model covered all related activities for the maintenance of equipment and ship structure corrosion. The constructive features, mission, equipment, and ship structure corrosion were integrated as a parameter to determine the decision-making for maintenance activities. The CMMS managed to create the planning for all equipment and ship structure, resulting in better maintenance resources, recording data of maintenance activities, and optimizing maintenance planning. Nevertheless, this prediction model was implemented for a special or custom-made ship. Fine-tuning and parameterization could be a challenge to implementing a similar prediction model on other ships.
The digital twin and artificial intelligence were proposed in [148] for the ship hull structures. The optimization method of finite element (FE) was implemented to create a prediction model. After that, the artificial neural network (ANN) was used for fitting and classification. The results showed that the specific location could be determined with this prediction model; thus, the sensitive area on the ship’s hull can be monitored closely for any damage or corrosion. The physic-based model of the digital twin and the data-based models of FE and ANN have been proven for the ship hull structure analysis.

3.2. Computer Vision and Image Processing Approaches for Corrosion Detection

Computer vision is an artificial intelligence field where the computer or machine is required to imitate or emulate the human visual system via machine learning. The computer or device can see and interpret patterns from optical inputs. Computer vision and image processing are promising approaches because of their nondestructive testing, high accuracy, and fast detection of corrosion boundaries. It replicates the human visual system complexity and interprets inputs from their color, size, texture, etc. Meanwhile, image processing is a method to enhance, improve and transform images by tuning the features and parameters of the given images. The images can be changed with many techniques. These digital images have particular values and location elements such as pixels, picture elements, and visual elements. Therefore, image processing is used for corrosion detection since its techniques can enhance, sharpen, filter, and segment the corroded area in images. Many computer vision and image processing algorithms have recently been established for corrosion detection, assessment, and prediction. These approaches are based on color, texture, filtering, pixilation, clustering, classification, segmentation, wavelet transformation, and image enhancement. The computer vision and image processing processes for corrosion detection can be divided into five main processes or elements: image acquisition, image pre-processing, image segmentation, feature extraction, and image classification shown in Figure 9. Additionally, the researcher introduced corrosion detection methods and their application, shown in Table 3.

3.2.1. Infrared Thermography

For the purpose of detecting corrosion, infrared thermography is frequently used in computer vision and image processing methods [129,169,170,171]. Due to the recently created infrared detector, these methods produce better corrosion detection accuracy and resolution. The cost of monitoring and development is reduced, but noise and weak signal strength can cause thermal images to be interrupted. The electromagnetic energy that metallic materials emit is captured using this method. Then, using the thermal images, corrosion patterns can be found. Application of thermography-based techniques applied to optical [172], laser [173], induction [174], microwave [175], photovoltaic (PV) electroluminescence module [176] and other systems for crack and corrosion detections on pipelines energy, surface inspection, practically, source, etc. However, each of these methods has limitations regarding their energy, surface inspection, practically, source, etc.

3.2.2. Texture Analysis

Texture analysis has been used in [177,178,179,180]; image processing techniques and object classification computer vision are used. Texture analysis improves classification results by reducing errors for isolated data detection. It can accurately detect, recognize and classify corroded regions in the images. Additionally, texture analysis can identify the corrosion and non-corrosion regions [181,182]. Application of SVM; water pipelines [183], underwater pipelines [184], steel bars [185], bridge cables [186], equipment [187], aircraft structures [188], wind turbine blades [189], and many more.

3.2.3. Non-Destructive Methods

Nondestructive testing for corrosion detection (Table 4) is used to check and assess materials without compromising their usability. Standard nondestructive techniques include acoustic emission utilized for real large-scale structures [190,191,192], fracture propagation [193,194,195], monitored pitting corrosion of stainless steel [196,197] and accelerated corrosion testing [198,199,200,201]. Under insulation, guided waves were employed to detect corrosion. The presence of flaws and their axial location is revealed by guided wave reflections and their arrival time. Magnetic flux leakage and magnetic perturbation techniques are used to detect corrosion in pipes. Eddy currents are used to find stress corrosion in gas transmission pipes, whereas long-distance pipeline inspection uses long-range ultrasonic testing (LRUT) [202]. Meanwhile, Table 5 shows the other corrosion detection methods in the literature.

4. Conclusions

Corrosion endures become one of the biggest concerns in the maritime industry. In our paper, we have summarized the state-of-the-art artificial intelligence approach in marine-related corrosion monitoring. These methods’ working fundamentals, advantages, and limitations have also been discussed. Most of the reviewed methods have provided significant quantitative and qualitative information regarding corrosion detection. Due to that, the present corrosion condition can be assessed, and the future corrosion condition can be predicted accordingly. The outcomes of this review can bring forward new, and additional knowledge of AI approaches for corrosion detection, assessment, and prediction. However, more study is needed to take advantage and fully exploit the recent advancements of IR4.0 technology in terms of advanced sensors and artificial intelligence to achieve impressive and better future performances for corrosion detection, assessment, and prediction.

Author Contributions

Conceptualization, M.M.H.I. and S.J.; methodology, M.M.H.I. and S.J.; investigation, A.F.M.A. and A.A.I.M.A.; resources, S.Z.A.S.A. and M.F.A.A.; writing—original draft preparation, M.M.H.I. and S.J.; writing—review and editing, S.M.N. and S.B.M.; supervision, N.Z. and M.I.R.S.; project administration, S.J.; funding acquisition, S.J. All authors have read and agreed to the published version of the manuscript.


This research was funded by the Ministry of Higher Education Malaysia (MOHE) through Fundamental Research Grant Scheme (FRGS/1/2022/TK07/UMT/02/5) and also Universiti Malaysia Terengganu (UMT) through Talent and Publication Enhancement Research Grant (TAPE-RG 2020/Vot 55229).

Institutional Review Board Statement

Not applicable.

Informed Consent Statement

Not applicable.

Data Availability Statement

Not applicable.

Conflicts of Interest

The authors declare no conflict of interest. The funders had no role in the design of the study; in the collection, analyses, or interpretation of data; in the writing of the manuscript; or in the decision to publish the results.


  1. Muhammad, F.S.; Khurram, K.; Faheem, R.; Salman, S.; Hassan, Z.; Kashif, K. Corrosion detection and severity level prediction using acoustic emission and machine learning based approach. Ain Shams Eng. J. 2021, 12, 3891–3903. [Google Scholar] [CrossRef]
  2. Eric, J.; Michael, A.M.; Jeffrey, M.R. Corrosion of additively manufactured stainless steels—Process, structure, performance: A review. Corrosion 2021, 77, 484–503. [Google Scholar]
  3. Sun, P.; Wang, Z.; Lu, Y.; Shen, S.; Yang, R.; Xue, A.; Parker, T.; Wang, J.; Wang, Q. Analysis of the corrosion failure of a semiconductor polycrystalline distillation column. Process Saf. Environ. Prot. 2020, 135, 244–256. [Google Scholar] [CrossRef]
  4. NACE SP0294-2006; Standard Practice—Design, Fabrication, and Inspection of Storage Tank Systems for Concentrated Fresh and Process Sulfuric Acid and Oleum at Ambient Temperatures. National Association of Corrosion Engineers: Houston, TX, USA, 2006; 42p.
  5. Koch, G.; Varney, J.; Thopson, N.; Moghissi, O.; Gould, M.; Payer, J. International Measures of Prevention, Application, and Economics of Corrosion Technologies Study. NACE Int. 2016, 216, 1–216. [Google Scholar]
  6. Hansson, C.M. The impact of corrosion on society. Metall. Mater. Trans. A Phys. Metall. Mater. Sci. 2011, 42, 2952–2962. [Google Scholar] [CrossRef]
  7. Baorong, H.; Xiaogang, L.; Xiumin, M.; Cuiwei, D.; Dawei, Z.; Meng, Z.; Weichen, X.; Dong-zhu, L.; Fubin, M. The cost of corrosion in China. Npj Mater. Degrad. 2017, 1, 1–10. [Google Scholar] [CrossRef]
  8. Nakai, T.; Matsushita, H.; Yamamoto, N. Effect of pitting corrosion on the ultimate strength of steel plates subjected to in-plane compression and bending. J. Mar. Sci. Technol. 2006, 11, 52–64. [Google Scholar] [CrossRef]
  9. Jamaludin, S.; Zainal, N.; Zaki, W.M.D.W. GPU implementation of sub-iris technique in iris recognition system. Pertanika J. Sci. Technol. 2017, 25, 263–274. [Google Scholar]
  10. Emi, H.; Yuasa, M.; Kumano, A.; Kumamoto, H.; Yamamoto, N.; Matsunaga, M. A study on life assessment of ships and off-shore structures: 2nd report: Risk assessment of fatigue failures of hull structures. Jpn. Soc. Nav. Archit. Ocean. Eng. 1992, 172, 627–635. [Google Scholar] [CrossRef] [PubMed]
  11. Khayatazad, M.; De-Pue, L.; De, W. Detection of corrosion on steel structures using automated image processing. Dev. Built Environ. 2020, 3, 100022. [Google Scholar] [CrossRef]
  12. Wu, D.; Birge, J.R. Risk intelligence in big data era: A review and introduction to special issue. IEEE Trans. Cybern. 2016, 46, 1718–1720. [Google Scholar] [CrossRef]
  13. Agarwala; Vinod, S.; Perry, L.; Reed; Siraj, A. Corrosion detection and monitoring—A review. NACE Int. 2000, 2000, 136664832. [Google Scholar]
  14. Schmitt, G.; Schütze, M.; Hays, G.F.; Burns, W.; Han, E.; Pourbaix, A.; Jacobson, G. Global needs for knowledge dissemination, research, and development in materials deterioration and corrosion control. World Corros. Organ. 2009, 38, 14. [Google Scholar]
  15. Sharon, A.; Itzhak, D. The environmental behavior of SAE 304L stainless steel sintered in the presence of a copper base additive. Mater. Sci. Eng. 1997, 1, 177–186. [Google Scholar] [CrossRef]
  16. Yuan, Y.; Yang, Y.; Yanpeng, W.; Xuefeng, Z. Artificial intelligence-based hull structural plate corrosion damage detection and recognition using convolutional neural network. Appl. Ocean Res. 2019, 90, 101823. [Google Scholar] [CrossRef]
  17. Patwardhan, R.S.; Hamadah, H.A.; Patel, K.M.; Hafiz, R.H.; Al-Gwaiz, M.M. Applications of advanced analytics at Saudi Aramco: A practitioners’ perspective. Ind. Eng. Chem. Res. 2019, 58, 11338–11351. [Google Scholar] [CrossRef]
  18. Jamaludin, S.; Zainal, N.; Zaki, W.M.D.W. A fast specular reflection removal based on pixels properties method. Bull. Electr. Eng. Inform. 2021, 9, 2358–2363. [Google Scholar] [CrossRef]
  19. Völker, C.; Kruschwitz, S.; Ebell, G. A machine learning-based data fusion approach for improved corrosion testing. Surv. Geophys. 2020, 41, 531–548. [Google Scholar] [CrossRef]
  20. Dral, P.O.; Von-Lilienfeld, O.A.; Thiel, W. Machine learning of parameters for accurate semiempirical quantum chemical calculations. J. Chem. Theory Comput. 2015, 11, 2120–2125. [Google Scholar] [CrossRef]
  21. Ser, C.T.; Zˇuvela, P.; Wong, M.W. Prediction of corrosion inhibition efficiency of pyridines and quinolines on an iron surface using machine learning-powered quantitative structure-property relationships. Appl. Surf. Sci. 2020, 512, 145612. [Google Scholar] [CrossRef]
  22. Hadi, S.; Rigoberto, B. Emerging artificial intelligence methods in structural engineering. Eng. Struct. 2018, 171, 170–189. [Google Scholar]
  23. LeCun, Y.; Bengio, Y.; Hinton, G. Deep learning. Nature 2015, 521, 436–444. [Google Scholar] [CrossRef]
  24. LeCun, Y.; Bottou, L.; Bengio, Y.; Haffner, P. Gradient-based learning applied to document recognition. Proc. IEEE 1998, 86, 2278–2324. [Google Scholar] [CrossRef] [Green Version]
  25. Li, Y.; Wang, G.; Nie, L.; Wang, Q.; Tan, W. Distance metric optimization driven convolutional neural network for age invariant face recognition. Pattern Rec. 2017, 75, 46. [Google Scholar] [CrossRef]
  26. Jaderberg, M.; Vedaldi, A.; Zisserman, A. Deep features for text spotting. Eur. Conf. Comput. 2014, 8692, 512–528. [Google Scholar]
  27. Aghdam, H.H.; Heravi, E.J.; Puig, D. A practical approach for detection and classification of traffic signs using convolutional neural networks. Robot. Auton. Syst. 2017, 84, 97–112. [Google Scholar] [CrossRef]
  28. Yammen, S.; Muneesawang, P. An Advanced Vision System for the Automatic Inspection of Corrosions on Pole Tips in Hard Disk Drives. IEEE Trans. Compon. Packag. Manuf. Technol. 2014, 4, 1523–1533. [Google Scholar] [CrossRef]
  29. Liu, L.; Tan, E.; Yin, X.J.; Zhen, Y.; Cai, Z.Q. Deep learning for Coating Condition Assessment with Active perception. In Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference, ACM, Guangzhou, China, 22–24 June 2019; pp. 75–80. [Google Scholar]
  30. Bonnin-Pascual, F.; Ortiz, A. Corrosion Detection for Automated Visual Inspection. Developments in Corrosion Protection. InTech 2014, 25, 619–632. [Google Scholar] [CrossRef] [Green Version]
  31. Jiang, J.; Wang, Z.; Guo, H.; Cheng, J. Multiresolution Analysis Driven Corrosion Detection on Metal Surface. In Proceedings of the 2011 International Conference on Multimedia and Signal Processing, IEEE, Aligarh, India, 17–19 December 2011; pp. 85–88. [Google Scholar]
  32. Petricca, L.; Moss, T.; Figueroa, G.; Broen, S. Corrosion Detection Using, A.I.: A Comparison of Standard Computer Vision Techniques and Deep Learning Model. Computer Science & Information Technology (CS & IT). In Proceedings of the Sixth International Conference on Computer Science, Engineering and Information Technology, Vienna, Austria, 21–22 May 2016; pp. 91–99. [Google Scholar]
  33. Katsamenis, I.; Protopapadakis, E.; Doulamis, A.; Doulamis, N.; Voulodimos, A. Pixel-Level Corrosion Detection on Metal Constructions by Fusion of Deep Learning Semantic and Contour Segmentation. In Proceedings of the ISVC 2020: 15th International Symposium on Visual Computing, San Diego, CA, USA, 5–7 November 2020; pp. 160–169. [Google Scholar]
  34. Bezdek, J. What is Computational Intelligence? Compuational Intelligence Imitating Life; Zurada, J.M., Marks, R.J., II, Robinson, C.J., Eds.; IEEE Press: Piscataway, NJ, USA, 1994; pp. 1–12. [Google Scholar]
  35. Nils, J.N. Artificial Intelligence: A New Synthesis; Elsevier: Amsterdam, The Netherlands, 1998. [Google Scholar] [CrossRef]
  36. David, P.; Alan, K.M.; Randy, G. Computational Intelligence: A Logical Approach; Oxford University Press: New York, NY, USA, 1998. [Google Scholar] [CrossRef] [Green Version]
  37. Kurzweil, R. The Age of Spiritual Machines: When Computers Exceed Human Intelligence; Penguin Books: New York, NY, USA, 2000. [Google Scholar]
  38. Jamaludin, S.; Ayob, A.F.M.; Norzeli, S.M.; Mohamed, S.B. Adaptive initial contour and partly-normalization algorithm for iris segmentation of blurry iris images. J. Inf. Commun. Technol. 2022, 21, 411–435. [Google Scholar] [CrossRef]
  39. Rafael, A.G.; Mauricio, S.S.; Felipe, M. Pattern recognition techniques implementation on data from In-Line Inspection (ILI). J. Loss Prev. Process Ind. 2016, 44, 735–747. [Google Scholar] [CrossRef]
  40. Giorgio, L.; Pierluigi, T.; Paola, L. Applications of chemometric tools in corrosion studies. Corros. Sci. 2010, 52, 2750–2757. [Google Scholar] [CrossRef]
  41. Zhang, Z.; Wu, X.; Amp, T.J. Laboratory-scale identification of corrosion mechanisms by a pattern recognition system based on electrochemical noise measurements. J. Electrochem. Soc. 2019, 166, C284. [Google Scholar] [CrossRef]
  42. Legat, A.; Doleček, V. Corrosion Monitoring System based on measurement and analysis of Electrochemical Noise. Corrosion 1995, 51, 295–300. [Google Scholar] [CrossRef]
  43. Ali, A.; Albasir, A.; Ramahi, O.M. Microwave sensor for imaging corrosion under coatings utilizing pattern recognition. In Proceedings of the IEEE International Symposium on Antennas and Propagation (APSURSI), Fajardo, Puerto Rico, 26 June–1 July 2016; pp. 951–952. [Google Scholar] [CrossRef]
  44. Liu, L.; Tan, E.; Zhen, Y.; Yin, X.J.; Cai, Z.Q. AI-facilitated coating corrosion assessment system for productivity enhancement. In Proceedings of the 13th IEEE Conference on Industrial Electronics and Applications (ICIEA), Wuhan, China, 31 May–2 June 2018; pp. 606–610. [Google Scholar] [CrossRef]
  45. Reich, Y. Machine learning techniques for civil engineering problems. Comput.-Aided Civ. Infrastruct. Eng. 1997, 12, 295–310. [Google Scholar] [CrossRef]
  46. Wang, H.; Zhang, W.; Sun, F.; Zhang, W. A comparison study of machine learning based algorithms for fatigue crack growth calculation. Materials 2017, 10, 543. [Google Scholar] [CrossRef] [Green Version]
  47. Bekkerman, R.; Bilenko, M.; Langford, J. Scaling up Machine Learning: Parallel and Distributed Approaches; Cambridge University Press: Cambridge, UK, 2012; pp. 1–22. [Google Scholar]
  48. Cherkassky, V.; Mulier, F.M. Learning from Data: Concepts, Theory, and Methods; John Wiley & Sons: Hoboken, NJ, USA, 2007. [Google Scholar]
  49. Taffese, W.Z.; Sistonen, E. Machine learning for durability and service-life assessment of reinforced concrete structures: Recent advances and future directions. Autom. Constr. 2017, 77, 1–14. [Google Scholar] [CrossRef]
  50. Imran, M.H.M.; Ayob, A.F.; Jamaludin, S. Applications of artificial intelligence in ship berthing: A review. Indian J. Geo-Mar. Sci. 2022, 50, 855–863. [Google Scholar]
  51. Zibo, P.; Dawei, Z.; Yuanjie, Z.; Tao, Y.; Lulu, J.; Dongmei, F.; Xuequn, C.; Herman, A.T.; Johannes, M.C.M.; Xiaogang, L. Towards understanding and prediction of atmospheric corrosion of an Fe/Cu corrosion sensor via machine learning. Corros. Sci. 2020, 170, 108697. [Google Scholar] [CrossRef]
  52. Duda, R.O.; Hart, P.E.; Stork, D.G. Pattern Classification, 2nd ed.; WileyInterscience: New York, NY, USA, 2000. [Google Scholar]
  53. Theodoridis, S.; Koutroumbas, K. Pattern Recognition, 4th ed.; Elsevier: Amsterdam, The Netherlands, 2008. [Google Scholar]
  54. Karbhari, V.; Lee, L.S.W. Vibration-Based Damage Detection Techniques for Structural Health Monitoring of Civil Infrastructure Systems, Structural Health Monitoring of Civil Infrastructure Systems; Elsevier: Amsterdam, The Netherlands, 2009; pp. 77–212. [Google Scholar]
  55. Murphy, K.P. Machine Learning: A Probabilistic Perspective; MIT Press: Cambridge, MA, USA, 2012. [Google Scholar]
  56. Bishop, C. Pattern Recognition and Machine Learning; Springer: Berlin/Heidelberg, Germany, 2007. [Google Scholar]
  57. Yupeng, D.; Luchun, Y.; Kewei, G. Improvement of the machine learning-based corrosion rate prediction model through the optimization of input features. Mater. Des. 2021, 198, 109326. [Google Scholar] [CrossRef]
  58. Takeda, A.; Kanamori, T. Using financial risk measures for analyzing generalization performance of machine learning models. Neural Netw. 2014, 57, 29–38. [Google Scholar] [CrossRef]
  59. Kim, M.J.; Kang, D.K. Ensemble with neural networks for bankruptcy prediction. Expert Syst. Appl. 2010, 37, 3373–3379. [Google Scholar]
  60. Di, K.; Li, W.; Yue, Z.; Sun, Y.; Liu, Y. A machine learning approach to crater detection from topographic data. Adv. Space Res. 2014, 54, 2419–2429. [Google Scholar] [CrossRef]
  61. Dede, G.; Sazlı, M.H. Speech recognition with artificial neural networks. Digit. Signal Process. 2010, 20, 763–768. [Google Scholar] [CrossRef]
  62. Vaughan, A.; Bohac, S.V. Real-time, adaptive machine learning for nonstationary, near chaotic gasoline engine combustion time series. Neural Netw. 2015, 70, 18–26. [Google Scholar] [CrossRef] [Green Version]
  63. Kialashaki, A.; Reisel, J.R. Development and validation of artificial neural network models of the energy demand in the industrial sector of the United States. Energy 2014, 76, 749–760. [Google Scholar] [CrossRef]
  64. Chau, K.W.; Wu, C. A hybrid model coupled with singular spectrum analysis for daily rainfall prediction. J. Hydroinform. 2010, 12, 458–473. [Google Scholar] [CrossRef] [Green Version]
  65. Chen, X. Hydrologic connections of a stream–aquifer-vegetation zone in southcentral Platte River valley, Nebraska. J. Hydrol. 2007, 333, 554–568. [Google Scholar] [CrossRef]
  66. Che, D.; Liu, Q.; Rasheed, K.; Tao, X. Decision tree and ensemble learning algorithms with their applications in bioinformatics. Adv. Exp. Med. Biol. 2011, 696, 91–199. [Google Scholar] [CrossRef]
  67. Zhang, S.; Chau, K.W. Dimension reduction using semi-supervised locally linear embedding for plant leaf classification. In International Conference on Intelligent Computing; Springer: Berlin/Heidelberg, Germany, 2009; pp. 948–955. [Google Scholar]
  68. Al-Jamimi, H.A.; Sadam, A.A.; Tawfik, A.S. Supervised machine learning techniques in the desulfurization of oil products for environmental protection: A review. Process Saf. Environ. Prot. 2018, 120, 57–71. [Google Scholar] [CrossRef]
  69. Zhang, D.; Tsai, J.J.P. Machine learning and software engineering. Softw. Qual. J. 2003, 11, 87–119. [Google Scholar] [CrossRef]
  70. Zhang, D.; Tsai, J.J.P. Machine Learning Applications in Software Engineering; World Scientific: Singapore, 2005. [Google Scholar] [CrossRef]
  71. Al-Jamimi, H.A.; Ahmed, M. Machine learning-based software quality pre-diction models: State of the art. In Proceedings of the Information Science and Applications (ICISA) International Conference, Suwon, Republic of Korea, 24–26 June 2013; pp. 1–4. [Google Scholar]
  72. Al-Jamimi, H.A.; Ahmed, M.A. Machine learning approaches for predict-ing software maintainability: A fuzzy-based transparent model. IET Softw. 2013, 7, 317–326. [Google Scholar] [CrossRef]
  73. Cussens, J.; Page, D.; Muggleton, S.; Srinivasan, A. Using Inductive Logic Pro-Gramming for Natural Language Processing; University of Economics: Prague, Czech Republic, 1997. [Google Scholar]
  74. Helmy, T.; Al-Azani, S.; Bin-Obaidellah, O. A machine learning-based approachto estimate the CPU-burst time for processes in the computational grids. In Proceedings of the AIMS 2015. 3rd International Conference on Artificial Intelligence, Modelling and Simulation, Kota Kinabalu, Malaysia, 2–4 December 2015; pp. 3–8. [Google Scholar] [CrossRef]
  75. IBM Cloud Education. What is Unsupervised Learning? IBM. Available online: (accessed on 20 October 2022).
  76. Han, J.; Pei, J.; Kamber, M. Data Mining: Concepts and Techniques; Elsevier: Amsterdam, The Netherlands, 2011. [Google Scholar]
  77. Jamaludin, S.; Ayob, A.F.M.; Akhbar, M.F.A.; Ali, A.A.I.M.; Imran, M.M.H.; Norzeli, S.M.; Mohamed, S.B. Efficient, accurate and fast pupil segmentation for pupillary boundary in iris recognition. Adv. Eng. Softw. 2023, 175, 103352. [Google Scholar] [CrossRef]
  78. Rosten, E.; Drummond, T. Machine learning for high-speed corner detection. In Proceedings of the 9th European Conference on Computer Vision, Graz, Austria, 7–13 May 2006; Springer: Berlin/Heidelberg, Germany, 2006; Volume 3951, pp. 430–443. [Google Scholar] [CrossRef]
  79. Lézoray, O.; Charrier, C.; Cardot, H.; Lefèvre, S. Machine learning in image processing. EURASIP J. Adv. Signal Process. 2008, 2008, 927950. [Google Scholar] [CrossRef] [Green Version]
  80. Bradski, G.; Kaehler, A. Learning Open CV: Computer Vision with the Open CV library; O’Reilly Media, Inc.: Sebastopol, CA, USA, 2008. [Google Scholar]
  81. Duygulu, P.; Barnard, K.; Freitas, J.F.; Forsyth, D.A. Object Recognition as Machine Translation: Learning a Lexicon for a Fxed Image Vocabulary; Springer: Berlin/Heidelberg, Germany, 2002; pp. 97–112. [Google Scholar]
  82. Harris, T. Credit scoring using the clustered support vector machine. Expert Syst. Appl. 2015, 42, 741–750. [Google Scholar] [CrossRef] [Green Version]
  83. Sharma, N.; Sharma, P.; Irwin, D.; Shenoy, P. Predicting solar generation from weather forecasts using machine learning. In Proceedings of the 2011 IEEE international conference on smart grid communications (SmartGridComm), Brussels, Belgium, 17–20 October 2011; pp. 528–533. [Google Scholar]
  84. Marvuglia, A.; Messineo, A. Monitoring of wind farms’ power curves using machine learning techniques. Appl. Energy 2012, 98, 574–583. [Google Scholar] [CrossRef]
  85. Hinton, G.; Deng, L.; Yu, D.; Dahl, G.; Mohamed, A.; Jaitly, N.; Senior, A.; Vanhoucke, V.; Nguyen, P.; Sainath, T.N.; et al. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Process. Mag. 2012, 29, 82–97. [Google Scholar] [CrossRef]
  86. Deng, L.; Hinton, G.; Kingsbury, B. New types of deep neural network learning for speech recognition and related applications: An overview. In Proceedings of the 2013 IEEE International Conference on Acoustics, Speech and Signal Processing, Vancouver, Canada, 26–31 May 2013; pp. 8599–8603. [Google Scholar] [CrossRef]
  87. Graves, A.; Mohamed, A.; Hinton, G. Speech recognition with deep recurrent neural networks. In Proceedings of the 2013 IEEE international conference on acoustics, speech and signal processing, Vancouver, Canada, 26–31 May 2013; pp. 6645–6649. [Google Scholar] [CrossRef] [Green Version]
  88. Michalski, R.S.; Carbonell, J.G.; Mitchell, T.M. Machine Learning: An Artificial Intelligence Approach; Springer: Berlin/Heidelberg, Germany, 2013. [Google Scholar]
  89. Alpaydin, E. Introduction to Machine Learning; MIT Press: Cambridge, MA, USA, 2014. [Google Scholar]
  90. Robert, C. Machine learning, a probabilistic perspective. Chance 2014, 27, 62–63. [Google Scholar] [CrossRef]
  91. Jamaludin, S.; Zainal, N.; Zaki, W.M.D.W. The removal of specular reflection in noisy iris image. J. Telecommun. Electron. Comput. Eng. 2016, 8, 59–64. [Google Scholar]
  92. Tong, S.; Chang, E. Support Vector Machine Active Learning for Image Retrieval; ACM Press: New York, NY, USA, 2001; Volume 107, pp. 107–118. [Google Scholar] [CrossRef]
  93. Sebe, N. Machine Learning in Computer Vision; Springer: Berlin/Heidelberg, Germany, 2005; p. 29. [Google Scholar]
  94. Deng, L.; Li, X. Machine learning paradigms for speech recognition: An overview. IEEE Trans. Audio Speech Lang. Process. 2013, 21, 1060–1089. [Google Scholar] [CrossRef]
  95. LeBaron, B. Agent-based computational finance. Handb. Comput. Econ. 2006, 2, 1187–1233. [Google Scholar]
  96. Brabazon, A.; O’Neill, M. Natural Computing in Computational Finance; Springer: Berlin/Heidelberg, Germany, 2008; p. 100. [Google Scholar]
  97. Wan, C.; Xu, Z.; Pinson, P.; Dong, Z.Y.; Wong, K.P. Probabilistic forecasting of wind power generation using extreme learning machine. IEEE Trans. Power Syst. 2014, 29, 1033–1044. [Google Scholar] [CrossRef]
  98. Needham, C.J.; Bradford, J.R.; Bulpitt, A.J.; Westhead, D.R. A primer on learning in Bayesian networks for computational biology. PLoS Comput. Biol. 2007, 3, 129. [Google Scholar] [CrossRef] [PubMed]
  99. IBM Cloud Education. What is Deep Learning? IBM. Available online: (accessed on 20 October 2022).
  100. Fentaye, A.D.; Ul-Haq Gilani, S.I.; Baheta, A.T.; Li, Y.G. Performance-based fault diagnosis of a gas turbine engine using an integrated support vector machine and artificial neural network method. Proceedings of the Institution of Mechanical Engineers. J. Power Energy Syst. 2019, 233, 786–802. [Google Scholar] [CrossRef] [Green Version]
  101. Zhang, C.; Lim, P.; Qin, A.K.; Tan, K.C. Multi objective deep belief networks ensemble for remaining useful life estimation in prognostics. IEEE Trans. Neural Netw. Learn. Syst. 2016, 28, 23062318. [Google Scholar] [CrossRef]
  102. Li, X.; Zhang, W.; Ding, Q. Deep learning based remaining useful life estimation of bearings using multi-scale feature extraction. Reliab. Eng. Syst. 2019, 182, 208–218. [Google Scholar] [CrossRef]
  103. Peng, X.; Anyaoha, U.; Liu, Z.; Tsukada, K. Analysis of Magnetic-Flux Leakage (MFL) Data for Pipeline Corrosion Assessment. IEEE Trans. Magn. 2020, 56, 1–15. [Google Scholar] [CrossRef]
  104. Soomro, A.; Ainul, M.; Jundika, C.K.; Huimin, L.; Najeebullah, L.; Chico, S. Deep Learning-Based Reliability Model for Oil and Gas Pipeline Subjected to Stress Corrosion Cracking: A Review and Concept. Hunan Daxue Xuebao J. Hunan Univ. Nat. Sci. 2021, 48, 10. [Google Scholar]
  105. Ren, C.Y.; Qiao, W.; Tian, X. Natural gas pipeline corrosion rate prediction model based on BP neural network. Adv. Intell. Syst. Comput. 2012, 147, 449–455. [Google Scholar] [CrossRef]
  106. Chamkalani, A.; Nareh’ei, M.A.; Chamkalani, R.; Zargari, M.H.; Dehestaniardakani, M.R.; Farzam, M. Soft computing method for prediction of CO2 corrosion in flow lines based on neural network approach. Chem. Eng. Commun. 2013, 200, 731–747. [Google Scholar] [CrossRef]
  107. Gabetta, G.; De, M.G.; Gentile, M.; Vichi, R.; Scapin, M. Pipeline Internal Damage Prediction by Deterministic Models and Neural Networks. In Proceedings of the Abu Dhabi International Petroleum Exhibition and Conference, Abu Dhabi, United Arab Emirates, 10–13 November 2014. SPE-171919MS. [Google Scholar] [CrossRef]
  108. Shaw, B.; Kelly, R. What is corrosion? Electrochem. Soc. Interface 2006, 15, 24. [Google Scholar] [CrossRef]
  109. Shi, L.; Song, Y.; Zhao, P.; Wang, H.; Dong, K.; Shan, D.; Han, E.H. Variations of galvanic currents and corrosion forms of 2024/Q235/304 tri-metallic couple with multivariable cathode/anode area ratios: Experiments and modeling. Electrochim. Acta 2020, 359, 136947. [Google Scholar] [CrossRef]
  110. Bitenc, J.; Lindahl, N.; Vizintin, A.; Abdelhamid, M.E.; Dominko, R.; Johansson, P. Concept and electrochemical mechanism of an Al metal anode–organic cathode battery. Energy Storage Mater. 2020, 24, 379–383. [Google Scholar] [CrossRef]
  111. Goyal, M.; Kumar, S.; Bahadur, I.; Verma, C.; Ebenso, E.E. Organic corrosion inhibitors for industrial cleaning of ferrous and non-ferrous metals in acidic solutions: A review. J. Mol. Liq. 2018, 256, 565–573. [Google Scholar] [CrossRef]
  112. Ng, D.Q.; Lin, J.K.; Lin, Y.P. Lead release in drinking water resulting from galvanic corrosion in three-metal systems consisting of lead, copper and stainless steel. J. Hazard. Mater. 2020, 398, 122936. [Google Scholar] [CrossRef]
  113. Liu, C.; Deng, Y.; Chen, J.; Zou, D.; Su, W. Integrated process to recover NiMH battery anode alloy with selective leaching and multistage extraction. Ind. Eng. Chem. Res. 2017, 56, 7551–7558. [Google Scholar] [CrossRef]
  114. Han, X.; Yang, D.Y.; Frangopol, D.M. Probabilistic life-cycle management framework for ship structures subjected to coupled corrosion–fatigue deterioration processes. J. Struct. Eng. 2019, 145, 4019116. [Google Scholar] [CrossRef]
  115. Selcuk, S. Predictive maintenance, its implementation and latest trends, Proceedings of the Institution of Mechanical Engineers. Proc. Inst. Mech. Eng. B J. Eng. Manuf. 2017, 231, 1670–1679. [Google Scholar] [CrossRef]
  116. Luo, W.; Hu, T.; Ye, Y.; Zhang, C.; Wei, Y. A hybrid predictive maintenance approach for CNC machine tool driven by Digital Twin. Robot Comput. Integr. Manuf. 2020, 65, 101974. [Google Scholar] [CrossRef]
  117. Filom, S.; Amiri, A.M.; Razavi, S. Applications of machine learning methods in port operations–A systematic literature review. Transp. Res. E-Log. 2022, 161, 102722. [Google Scholar] [CrossRef]
  118. Jimenez, J.J.M.; Schwartz, S.; Vingerhoeds, R.; Grabot, B.; Salaün, M. Towards multi-model approaches to predictive maintenance: A systematic literature survey on diagnostics and prognostics. J. Manuf. Syst. 2020, 56, 539–557. [Google Scholar] [CrossRef]
  119. Rossouw, E.; Doorsamy, W. Predictive Maintenance Framework for Cathodic Protection Systems Using Data Analytics. Energies 2021, 14, 5805. [Google Scholar] [CrossRef]
  120. Canca, A.; Kökkülünk, G. Is existing maintenance system adequate for sulphur 2020 amendments? J. ETA Marit. Sci. 2020, 8, 302–308. [Google Scholar] [CrossRef]
  121. Vu, V.T.; Dong, D.T. Hull girder ultimate strength assessment considering local corrosion. J. Mar. Sci. Appl. 2020, 19, 693–704. [Google Scholar] [CrossRef]
  122. Bicen, S.; Celik, M. A RAM extension to enhance ship planned maintenance system. Aust. J. Marit. Ocean Aff. 2022, 2022, 1–20. [Google Scholar] [CrossRef]
  123. Abbas, M.; Shafiee, M. An overview of maintenance management strategies for corroded steel structures in extreme marine environments. Mar. Struct. 2020, 71, 102718. [Google Scholar] [CrossRef]
  124. Bhat, J.; Bhapkar, U.; Desai, M. Condition based predictive maintenance of worm gearbox using DR ferrography. Mater. Today Proc. 2022, 52, 2210–2212. [Google Scholar] [CrossRef]
  125. Gong, C.; Frangopol, D.M. System reliability of corroded ship hull girders. Struct. Infrastruct. Eng. 2020, 16, 1302–1310. [Google Scholar]
  126. Woloszyk, K.; Garbatov, Y. An enhanced method in predicting tensile behaviour of corroded thick steel plate specimens by using random field approach. Ocean Eng. 2020, 213, 107803. [Google Scholar] [CrossRef]
  127. Pourabdollah, K. Fouling formation and under deposit corrosion of boiler firetubes. J. Environ. Chem. Eng. 2021, 9, 104552. [Google Scholar] [CrossRef]
  128. Raadnui, S. Spur gear wear analysis as applied for tribological based predictive maintenance diagnostics. Wear 2019, 426, 1748–1760. [Google Scholar]
  129. Bouzaffour, K.; Lescop, B.; Talbot, P.; Gallée, F.; Rioual, S. Development of an embedded UHF-RFID corrosion sensor for monitoring corrosion of steel in concrete. IEEE Sens. J. 2021, 21, 12306–12312. [Google Scholar] [CrossRef]
  130. Melchers, R.E. Predicting long-term corrosion of metal alloys in physical infrastructure. NPJ Mater. Degrad. 2019, 3, 4. [Google Scholar] [CrossRef] [Green Version]
  131. Lampe, J.; Hamann, R. Probabilistic model for corrosion degradation of tanker and bulk carrier. Mar. Struct. 2018, 61, 309–325. [Google Scholar] [CrossRef]
  132. Tinga, T.; Tiddens, W.W.; Amoiralis, F.; Politis, M. Predictive maintenance of maritime systems: Models and challenges. In Proceedings of the 27th European Safety and Reliability Conference (ESREL 2017), Portoroz, Slovenia, 18–22 June 2017; pp. 1–9. [Google Scholar]
  133. Tinga, T.; Loendersloot, R. Physical model-based prognostics and health monitoring to enable predictive maintenance. In Predictive Maintenance in Dynamic Systems; Springer: Berlin/Heidelberg, Germany, 2019; pp. 313–353. [Google Scholar]
  134. Ayyub, B.M.; Stambaugh, K.A.; McGill, W.L. End-of-life corrosion estimation and profile of ship hull structure: Nonparametric statistical analysis of medium endurance cutters. ASCE-ASME J. Risk Uncertain. Eng. Syst. B Mech. Eng. 2022, 8, 31203. [Google Scholar] [CrossRef]
  135. Gong, C.; Frangopol, D.M.; Cheng, M. Risk-based decision-making on corrosion delay for ship hull tankers. Eng. Struct. 2020, 212, 110455. [Google Scholar] [CrossRef]
  136. Yarveisy, R.; Khan, F.; Abbassi, R. Data-driven predictive corrosion failure model for maintenance planning of process systems. Comput. Chem. Eng. 2022, 157, 107612. [Google Scholar] [CrossRef]
  137. Kim, K.; Lee, G.; Park, K.; Park, S.; Lee, W.B. Adaptive approach for estimation of pipeline corrosion defects via Bayesian inference. Reliab. Eng. Syst. 2021, 216, 107998. [Google Scholar] [CrossRef]
  138. Cheliotis, M.; Lazakis, I.; Theotokatos, G. Machine learning and data-driven fault detection for ship systems operations. Ocean Eng. 2020, 216, 107968. [Google Scholar] [CrossRef]
  139. Makridis, G.; Kyriazis, D.; Plitsos, S. Predictive maintenance leveraging machine learning for time-series forecasting in the maritime industry. In Proceedings of the 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC). IEEE, Rhodes, Greece, 20–23 September 2020; pp. 1–8. [Google Scholar]
  140. Kim, D.K.; Wong, E.W.C.; Cho, N.K. An advanced technique to predict time-dependent corrosion damage of onshore, offshore, nearshore and ship structures. Int. J. Nav. Archit. 2020, 12, 657–666. [Google Scholar] [CrossRef]
  141. Ivošević, Š.; Bauk, S. The use of information technology in the assessment of the corrosion damage on ship hull. In Proceedings of the 23rd International Scientific-Professional Conference on Information Technology (IT), IEEE, Zabljak, Montenegro, 19–24 February 2018; pp. 1–4. [Google Scholar]
  142. Gautam, M.; Ramu, V.S.; Sinha, S.; Reddy, P.K.; Kondur, M.; Kumar, S.S. Augmenting the existing CBPM maintenance philosophy currently in use in the marine sector with intelligent predictive—CBPM philosophy. In Proceedings of the International Conference on Recent Trends in Machine Learning, IoT, Smart Cities and Applications, Hyderabad, India, 28–29 March 2021; Springer: Berlin/Heidelberg, Germany, 2021; pp. 553–560. [Google Scholar]
  143. Gong, C.; Frangopol, D.M. Time-variant hull girder reliability considering spatial dependence of corrosion growth, geometric and material properties. Reliab. Eng. Syst. 2020, 193, 106612. [Google Scholar] [CrossRef]
  144. Liu, Y.; Frangopol, D.M.; Cheng, M. Risk-informed structural repair decision making for service life extension of aging naval ships. Mar. Struct. 2019, 64, 305–321. [Google Scholar] [CrossRef]
  145. Jimenez, V.J.; Bouhmala, N.; Gausdal, A.H. Developing a predictive maintenance model for vessel machinery. J. Ocean Eng. Sci. 2020, 5, 358–386. [Google Scholar] [CrossRef]
  146. Silionis, N.E.; Anyfantis, K.N. On the detection of thickness loss in ship hull structures through strain sensing. In European Workshop on Structural Health Monitoring; Springer: Berlin/Heidelberg, Germany, 2023; pp. 207–216. [Google Scholar]
  147. Cullum, J.; Binns, J.; Lonsdale, M.; Abbassi, R.; Garaniya, V. Risk-based maintenance scheduling with application to naval vessels and ships. Ocean Eng. 2018, 148, 476–485. [Google Scholar] [CrossRef]
  148. Simion, D.; Purcărea, A.; Cotorcea, A.; Nicolae, F. Maintenance onboard ships using computer maintenance management system. Sci. Bull. Mircea Cel Batran Nav. Acad. 2020, 23, 134–141. [Google Scholar] [CrossRef]
  149. Anyfantis, K.N. An abstract approach toward the structural digital twin of ship hulls: A numerical study applied to a box girder geometry. Proc. Inst. Mech. Eng. M J. Eng. Marit. Environ. 2021, 235, 718–736. [Google Scholar] [CrossRef]
  150. Hassan, S.I.; Dang, L.M.; Mehmood, I.; Im, S.; Choi, C.; Kang, J.; Park, Y.S.; Moon, H. Underground sewer pipe condition assessment based on convolutional neural networks. Autom. Constr. 2019, 106, 102849. [Google Scholar] [CrossRef]
  151. Yin, X.; Chen, Y.; Bouferguene, A.; Zaman, H.; Al-Hussein, M.; Kurach, L. A deep learning-based framework for an automated defect detection system for sewer pipes. Autom. Constr. 2020, 109, 102967. [Google Scholar] [CrossRef]
  152. Cheng, J.C.; Wang, M. Automated detection of sewer pipe defects in closed-circuit television images using deep learning techniques. Autom. Constr. 2018, 95, 155–171. [Google Scholar] [CrossRef]
  153. Vince, P. Advances in condition assessment of water pipelines. Corrosion 2020, 76, 511–519. [Google Scholar] [CrossRef]
  154. Bastian, B.T.; Jaspreeth, N.; Ranjith, S.K.; Jiji, C.V. Visual inspection and characterization of external corrosion in pipelines using deep neural network. NDT E Int. 2019, 107, 102134. [Google Scholar] [CrossRef]
  155. Amaya-Gómez, R.; Riascos-Ochoa, J.; Muñoz, F.; Bastidas-Arteaga, E.; Schoefs, F.; Sánchez-Silva, M. Modeling of pipeline corrosion degradation mechanism with a Lévy process based on ILI (In-Line) inspections. Int. J. Press. Vessel. Pip. 2019, 172, 261–271. [Google Scholar] [CrossRef]
  156. Aryai, V.; Baji, H.; Mahmoodian, M.; Li, C.Q. Time-dependent finite element reliability assessment of cast-iron water pipes subjected to spatio-temporal correlated corrosion process. Reliab. Eng. Syst. 2020, 197, 106802. [Google Scholar] [CrossRef]
  157. Zhang, M.; Song, H.; Lim, S.; Akiyama, M.; Frangopol, D.M. Reliability estimation of corroded RC structures based on spatial variability using experimental evidence, probabilistic analysis and finite element method. Eng. Struct. 2019, 192, 30–52. [Google Scholar] [CrossRef]
  158. Zhang, M.; Akiyama, M.; Shintani, M.; Xin, J.; Frangopol, D.M. Probabilistic estimation of flexural loading capacity of existing RC structures based on observational corrosion-induced crack width distribution using machine learning. Struct. Saf. 2021, 91, 102098. [Google Scholar] [CrossRef]
  159. Hoang, N.D. Image processing-based pitting corrosion detection using metaheuristic optimized multilevel image thresholding and machine-learning approaches. Math. Probl. Eng. 2020, 2020, 6765274. [Google Scholar] [CrossRef]
  160. Wang, K.; Li, C.; Lu, J.; Nan, C.; Zhang, Q.; Zhang, H. Intelligent evaluation of marine corrosion of q420 steel based on image recognition method. Coatings 2022, 12, 881. [Google Scholar] [CrossRef]
  161. Milimonfared, R.; Oskouei, R.H.; Taylor, M.; Solomon, L.B. An intelligent system for image-based rating of corrosion severity at stem taper of retrieved hip replacement implants. Med. Eng. Phys. 2018, 61, 13–24. [Google Scholar] [CrossRef]
  162. Karimi, A.M.; Fada, J.S.; Parrilla, N.A.; Pierce, B.G.; Koyutürk, M.; French, R.H.; Braid, J.L. Generalized and mechanistic PV module performance prediction from computer vision and machine learning on electroluminescence images. IEEE J. Photovolt. 2020, 10, 878–887. [Google Scholar] [CrossRef]
  163. Perumal, P.; Ramanathan, K.; Ganesan, L.; Subramanian, B.; Ganesh, V.; Stalin, B. Investigation of TiN coating uniformity and its corrosion behaviour using image process. Mater. Res. Express 2019, 6, 46411. [Google Scholar] [CrossRef]
  164. Dong, B.; Ding, W.; Qin, S.; Fang, G.; Liu, Y.; Dong, P.; Han, S.; Xing, F.; Hong, S. 3D visualized tracing of rebar corrosion-inhibiting features in concrete with a novel chemical self-healing system. Constr. Build. Mater. 2018, 168, 11–20. [Google Scholar] [CrossRef]
  165. Bado, M.F.; Tonelli, D.; Poli, F.; Zonta, D.; Casas, J.R. Digital twin for civil engineering systems: An exploratory review for distributed sensing updating. Sensors 2022, 22, 3168. [Google Scholar] [CrossRef]
  166. Abbas, M.H.; Norman, R.; Charles, A. Neural network modelling of high-pressure CO2 corrosion in pipeline steels. Process Saf. Environ. Prot. 2018, 119, 36–45. [Google Scholar] [CrossRef] [Green Version]
  167. Florindo, J.B.; Metze, K. A cellular automata approach to local patterns for texture recognition. Expert Syst. Appl. 2021, 179, 115027. [Google Scholar] [CrossRef]
  168. Venketeswaran, A.; Lalam, N.; Wuenschell, J.; Ohodnicki, P.R., Jr.; Badar, M.; Chen, K.P.; Lu, P.; Duan, Y.; Chorpening, B.; Buric, M. Recent advances in machine learning for fiber optic sensor applications. Adv. Intell. Syst. 2022, 4, 2100067. [Google Scholar] [CrossRef]
  169. Nash, W.; Drummond, T.; Birbilis, N. A review of deep learning in the study of materials degradation. NPJ Mater. Degrad. 2018, 2, 37. [Google Scholar] [CrossRef]
  170. Doshvarpassand, S.; Wu, C.; Wang, X. An overview of corrosion defect characterization using active infrared thermography. Infrared Phys. Technol. 2019, 96, 366–389. [Google Scholar] [CrossRef]
  171. Zhang, X.; Saniie, J.; Heifetz, A. Detection of defects in additively manufactured stainless steel 316L with compact infrared camera and machine learning algorithms. JOM 2020, 72, 4244–4253. [Google Scholar] [CrossRef]
  172. Omar, T.; Nehdi, M.L.; Zayed, T. Infrared thermography model for automated detection of delamination in RC bridge decks. Constr. Build. Mater. 2018, 168, 313–327. [Google Scholar] [CrossRef]
  173. Zhao, Y.; Addepalli, S.; Sirikham, A.; Roy, R. A confidence map-based damage assessment approach using pulsed thermographic inspection. NDT E Int. 2018, 93, 86–97. [Google Scholar] [CrossRef]
  174. Park, J.; Han, H.S.; Park, J.; Seo, H.; Edwards, J.; Kim, Y.C.; Ok, M.R.; Seok, H.K.; Jeon, H. Corrosion behavior of biodegradable Mg-based alloys via femtosecond laser surface melting. Appl. Surf. Sci. 2018, 448, 424–434. [Google Scholar] [CrossRef]
  175. Wang, L.; Dai, L.; Bian, H.; Ma, Y.; Zhang, J. Concrete cracking prediction under combined prestress and strand corrosion. Struct. Infrastruct. Eng. 2019, 15, 285–295. [Google Scholar] [CrossRef]
  176. Nair, R.B.; Arora, H.S.; Grewal, H.S. Microwave synthesized complex concentrated alloy coatings: Plausible solution to cavitation induced erosion-corrosion. Ultrason. Sonochem. 2019, 50, 114–125. [Google Scholar] [CrossRef]
  177. Karimi, A.M.; Fada, J.S.; Hossain, M.A.; Yang, S.; Peshek, T.J.; Braid, J.L.; French, R.H. Automated pipeline for photovoltaic module electroluminescence image processing and degradation feature classification. IEEE J. Photovolt. 2019, 9, 1324–1335. [Google Scholar] [CrossRef]
  178. Ayob, A.F.M.; Jalal, N.I.; Hassri, M.H.; Rahman, S.A.; Jamaludin, S. Neuroevolutionary autonomous surface vehicle simulation in restricted waters. TransNav Int. J. Mar. Navig. Saf. Sea Transp. 2020, 14, 865–873. [Google Scholar] [CrossRef]
  179. Atha, D.J.; Jahanshahi, M.R. Evaluation of deep learning approaches based on convolutional neural networks for corrosion detection. Struct. Health Monit. 2018, 17, 1110–1128. [Google Scholar] [CrossRef]
  180. Prithivirajan, S.; Narendranath, S.; Desai, V. Analysing the combined effect of crystallographic orientation and grain refinement on mechanical properties and corrosion behaviour of ECAPed ZE41 Mg alloy. J. Magnes. Alloy. 2020, 8, 1128–1143. [Google Scholar] [CrossRef]
  181. Bondada, V.; Pratihar, D.K.; Kumar, C.S. Detection and quantitative assessment of corrosion on pipelines through image analysis. Procedia Comput. Sci. 2018, 133, 804–811. [Google Scholar] [CrossRef]
  182. Li, J.; Liu, H.; Shi, L.; Lan, J. Imaging feature analysis-based intelligent laser cleaning using metal color difference and dynamic weight dispatch corrosion texture. Photonics 2020, 7, 130. [Google Scholar] [CrossRef]
  183. Li, M.; Duan, Y.; He, X.; Yang, M. Image positioning and identification method and system for coal and gangue sorting robot. Int. J. Coal Prep. Util. 2022, 42, 1759–1777. [Google Scholar] [CrossRef]
  184. Ramkumar, G. Hybrid model for detection of corrosion in water pipeline images using CNN and comparing accuracy with SVM. ECS Trans. 2022, 107, 13861. [Google Scholar]
  185. Hong, X.; Huang, L.; Gong, S.; Xiao, G. Shedding damage detection of metal underwater pipeline external anticorrosive coating by ultrasonic imaging based on HOG + SVM. J. Mar. Sci. 2021, 9, 364. [Google Scholar] [CrossRef]
  186. Lv, Y.J.; Wang, J.W.; Wang, J.; Xiong, C.; Zou, L.; Li, L.; Li, D.W. Steel corrosion prediction based on support vector machines. Chaos Solit. Fractals 2020, 136, 109807. [Google Scholar] [CrossRef]
  187. Li, X.; Guo, Y.; Li, Y. Particle swarm optimization-based SVM for classification of cable surface defects of the cable-stayed bridges. IEEE Access 2019, 8, 44485–44492. [Google Scholar] [CrossRef]
  188. Yang, J.; Li, R.; Chen, L.; Hu, Y.; Dou, Z. Research on equipment corrosion diagnosis method and prediction model driven by data. Process Saf. Environ. Prot. 2022, 158, 418–431. [Google Scholar] [CrossRef]
  189. Le, M.; Luong, V.S.; Nguyen, D.K.; Le, D.K.; Lee, J. Auto-detection of hidden corrosion in an aircraft structure by electromagnetic testing: A machine-learning approach. Appl. Sci. 2022, 12, 5175. [Google Scholar] [CrossRef]
  190. Deng, L.; Guo, Y.; Chai, B. Defect detection on a wind turbine blade based on digital image processing. Processes 2021, 9, 1452. [Google Scholar] [CrossRef]
  191. Blitz, J. Electrical and Magnetic Methods of Non-Destructive Testing; Springer: Berlin/Heidelberg, Germany, 2012; Volume 3. [Google Scholar]
  192. Jamaludin, S.; Zainal, N.; Zaki, W.M.D.W. Sub-iris technique for non-ideal iris recognition. Arab. J. Sci. Eng. 2018, 43, 7219–7228. [Google Scholar] [CrossRef]
  193. Grosse, C.U.; Ohtsu, M. Acoustic Emission Testing; Springer: Berlin/Heidelberg, Germany, 2008. [Google Scholar]
  194. Carpinteri, A.l.; Lacidogna, G.; Pugno, N. Structural damage diagnosis and life-time assessment by acoustic emission monitoring. Eng. Fract. Mech. 2007, 74, 273–289. [Google Scholar] [CrossRef]
  195. Carpinteri, A.G.; Lacidogna, M.C.; Battista, E.D. Cracking and crackling in concrete-like materials: A dynamic energy balance. Eng. Fract. Mech. 2016, 155, 130–144. [Google Scholar] [CrossRef]
  196. Mohamad, G.D.; Nadimul, H.F.; Fraser, O.; John, A.S.; Mohamed, E.S. Acoustic emission method for defect detection and identification in carbon steel welded joints. J. Constr. Steel Res. 2017, 134, 28–37. [Google Scholar] [CrossRef]
  197. Wu, K.; Jung, W.S.; Byeon, J.W. Acoustic emission of hydrogen bubbles on the counter electrode during pitting corrosion of 304 stainless steel. Mater. Trans. 2015, 56, 587–592. [Google Scholar] [CrossRef] [Green Version]
  198. Jamaludin, S.; Zainal, N.; Zaki, W.M.D.W. Iris recognition based on the modified Chan-Vese active contour. J. Teknol. 2016, 78, 13–17. [Google Scholar] [CrossRef] [Green Version]
  199. Patil, S.; Shweta, G.; Bilavari, K. Performance evaluation of accelerated corrosion techniques using electrochemical measurements and acoustic emission parameters. In Proceedings of the 2016 IEEE International Conference on Prognostics and Health Management (ICPHM), Ottawa, Canada, 20–22 June 2016. [Google Scholar]
  200. Gloria, N.B.S.; Areiza, M.C.L.; Miranda, I.V.J.; Rebello, J.M.A. Development of a magnetic sensor for detection and sizing of internal pipeline corrosion defects. NDT E Int. 2009, 42, 669–677. [Google Scholar] [CrossRef]
  201. Van, D.V.P. Internal corrosion in small-diameter, heavy-wall pipelines: A critical phenomenon and how to measure it. Corros. Prev. Control. 2000, 47, 103–106. [Google Scholar]
  202. Raghavan, A.; Cesnik, C.E.S. Review of guided-wave structural health monitoring. Shock. Vibr. Dig. 2007, 39, 91–116. [Google Scholar] [CrossRef]
  203. Mokhles, M.; Ghavipanjeh, C.; Tamimi, A. The use of ultrasonic guided waves for extended pipeline qualification prediction. In Proceedings of the Singapore International NDT Conference & Exhibition, Marina Bay Sands, Singapore, 19–20 July 2013. [Google Scholar]
  204. Kim, D.; Udpa, L.; Udpa, S. Remote field eddy current testing for detection of stress corrosion cracks in gas transmission pipelines. Mater. Lett. 2004, 58, 2102–2104. [Google Scholar] [CrossRef]
  205. Shi, X.; Nguyen, T.A.; Kumar, P.; Liu, Y. A phenomenological model for the chloride threshold of pitting corrosion of steel in simulated concrete pore solutions. Anti-Corros. Methods Mater. 2011, 58, 179–189. [Google Scholar] [CrossRef]
  206. Ali, H.; Amir, B.; Davood, M.; Seyed, M.M.; Kasra, R. Implementing ANN to minimize sewage systems concrete corrosion with glass beads substitution. Constr. Build. Mater. 2017, 138, 441–454. [Google Scholar] [CrossRef]
  207. Wen, Y.F.; Cai, C.Z.; Liu, X.H.; Pei, J.F.; Zhu, X.J.; Xiao, T.T. Corrosion rate prediction of 3C steel under different seawater environment by using support vector regression. Corros. Sci. 2009, 51, 349–355. [Google Scholar] [CrossRef]
  208. Liao, K.; Quanke, Y.; Xia, W.; Wenlong, J. A Numerical Corrosion Rate Prediction Method for Direct Assessment of Wet Gas Gathering Pipelines Internal Corrosion. Energies 2012, 5, 3892–3907. [Google Scholar] [CrossRef] [Green Version]
  209. Jian, L.; Weikang, K.; Shi, J.; Wang, K.; Weikui, W.; Weipu, Z.; Zhoumo, Z. Determination of Corrosion Types from Electrochemical Noise by Artificial Neural Networks. Int. J. Electrochem. Sci. 2013, 8, 2365–2377. [Google Scholar]
  210. Giulia, D.M.; Manuela, G.; Roberta, V.; Roberto, B.; Giovanna, G. Machine learning approach to corrosion assessment in subsea pipelines. In Proceedings of the Oceans 2015 Genova Conference & Exhibition, Genova, Italy, 18–21 May 2015. [Google Scholar]
  211. Qifang, L.; Ray, K.L.; Su, A. Wasserstein distance-based analogous method to predict distribution of non-uniform corrosion on reinforcements in concrete. Constr. Build. Mater. 2019, 226, 965–975. [Google Scholar] [CrossRef]
  212. Medeiros, F.N.S.; Ramalho, G.L.B.; Bento, M.P.; Medeiros, L.C.L. On the evaluation of texture and color features for nondestructive corrosion detection. EURASIP J. Adv. Signal Process. 2010, 2010, 817473. [Google Scholar] [CrossRef] [Green Version]
  213. Russakovsky, O.; Deng, J.; Su, H.; Krause, J.; Satheesh, S.; Ma, S.; Huang, Z.; Karpathy, A.; Khosla, A.; Bernstein, M.; et al. Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 2015, 115, 211–252. [Google Scholar] [CrossRef] [Green Version]
  214. Zeiler, M.D.; Fergus, R. Visualizing and Understanding Convolutional Networks; Springer: Berlin/Heidelberg, Germany, 2014; pp. 818–833. [Google Scholar]
  215. Szegedy, C.; Liu, W.; Jia, Y.; Sermanet, P.; Reed, S.; Anguelov, D.; Erhan, D.; Vanhoucke, V.; Rabinovich, A. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition, Boston, MA, USA, 7–12 June 2015. [Google Scholar]
  216. Tada, Y.; Miura, T.; Nakamura, H. Detection method of corrosion area of rebar and corrosion induced internal crack by using electromagnetic wave radar. In Bridge Maintenance, Safety, Management, Life-Cycle Sustainability and Innovations; CRC Press London: Boca Raton, FL, USA, 2021; pp. 1672–1679. [Google Scholar]
  217. Li, D.; Tan, M.; Zhang, S.; Ou, J. Stress corrosion damage evolution analysis and mechanism identification for prestressed steel strands using acoustic emission technique. Struct. Control Health Monit. 2018, 25, e2189. [Google Scholar] [CrossRef]
  218. Shanbi, P.; Zhe, Z.; Enbin, L.; Wei, L.; Weibiao, Q. A new hybrid algorithm model for prediction of internal corrosion rate of multiphase pipeline. J. Nat. Gas Eng. 2021, 85, 103716. [Google Scholar] [CrossRef]
  219. Rudling, P.; Strasser, A.; Garzarolli, F.; Van, S.L. Welding of Zirconium Alloys; IZNA7 Special Topic Report; Advanced Nuclear Technology International: Krongjutarvagen, Sweden, 2007. [Google Scholar]
  220. Ossai, C.I. A data-driven machine learning approach for corrosion risk assessment—A comparative study. Big Data Cogn. Comput. 2019, 3, 28. [Google Scholar] [CrossRef] [Green Version]
  221. Abdur, R.M.F.; Yong-Bin, K.; Prem, P.J.; Kewen, L.; Rohit, K.; Graham, M.; Rajiv, R.; Samir, S. CorrDetector: A framework for structural corrosion detection from drone images using ensemble deep learning. Expert Syst. Appl. 2022, 193, 116461. [Google Scholar] [CrossRef]
  222. Simonyan, K.; Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv 2014, arXiv:1409.1556. [Google Scholar]
  223. Jui-Sheng, C.; Ngoc-Tri, N.; Chong, W.K. The use of artificial intelligence combiners for modeling steel pitting risk and corrosion rate. Eng. Appl. Artif. Intell. 2017, 65, 471–483. [Google Scholar] [CrossRef]
  224. Hasan, T.; Jamaludin, S.; Wan Nik, W.B. Analysis of intelligent solar ICU water ambulance to optimize energy. Ann. Med. Surg. 2022, 2022, 104141. [Google Scholar] [CrossRef] [PubMed]
  225. Zhang, J.; Sato, T.; Iai, S.; Hutchinson, T. A pattern recognition technique for structural identification using observed vibration signals: Linear case studies. Eng. Struct. 2008, 30, 1439–1446. [Google Scholar] [CrossRef]
Figure 1. AI techniques interrelation.
Figure 1. AI techniques interrelation.
Jmse 11 00256 g001
Figure 2. Schematic of pattern recognition.
Figure 2. Schematic of pattern recognition.
Jmse 11 00256 g002
Figure 3. Pattern recognition model and algorithm structures (generative and discriminative pattern).
Figure 3. Pattern recognition model and algorithm structures (generative and discriminative pattern).
Jmse 11 00256 g003
Figure 4. Machine learning categories.
Figure 4. Machine learning categories.
Jmse 11 00256 g004
Figure 5. General supervised learning model.
Figure 5. General supervised learning model.
Jmse 11 00256 g005
Figure 6. General unsupervised learning model.
Figure 6. General unsupervised learning model.
Jmse 11 00256 g006
Figure 7. Reinforcement learning model.
Figure 7. Reinforcement learning model.
Jmse 11 00256 g007
Figure 8. Machine learning categories and algorithms.
Figure 8. Machine learning categories and algorithms.
Jmse 11 00256 g008
Figure 9. Computer vision and image processing elements.
Figure 9. Computer vision and image processing elements.
Jmse 11 00256 g009
Table 1. Description of scope of bodies within the body of literature.
Table 1. Description of scope of bodies within the body of literature.
DatabaseWeb of Science, Scopus, Science Direct, IEEE
Keywords‘’Artificial intelligence + corrosion+ detection,’’
“Predictive + maintenance + corrosion,”
“Artificial + intelligence” and “current + trends,”
“Computer vision + corrosion + monitoring,”
“Image processing + corrosion + monitoring.”
Publication typeJournal and conference paper
Time interval2017–2022
Table 2. Basic differentiation between supervised and unsupervised learning.
Table 2. Basic differentiation between supervised and unsupervised learning.
ElementSupervised LearningUnsupervised Learning
Input dataLabeledUnlabeled
Feedback mechanismHaveDon’t have
Data classifiedBased on the training datasetAssigns properties of given data to classify it.
DivisionRegression and classificationClustering and association
ApplicationFor predictionFor analysis
AlgorithmLogistic regressions, decision trees, support vector machineHierarchical clustering, K-means clustering, apriori algorithm.
Class numberKnownUnknown
Table 3. Short description of different corrosion detection approaches and their applications.
Table 3. Short description of different corrosion detection approaches and their applications.
Knowledge-Based ModelUsed artificial intelligence to predict the progress of corrosion from images and videos.-Automated sewer inspection [149,150].
-Combination of CCTV and machine learning [151,152,153].
Probabilistic ModelUsed for corrosion detection when the real-time data and historical data are insufficient. Require in-depth knowledge and expertise in physic and mathematics to develop a sophisticated mathematical model. Quite difficult to develop.-Gamma distribution [154].
-Gamma process and copulas of Spatio-temporal [155].
-Probabilistic model and finite element [156].
-Monte Carlo finite element [157,158].
Statistical ModelUsed statistical analysis to predict and detect the corrosion progress based on historical data. The historical data can be collected from the installed CCTV in the gas pipeline, sewer, and many more.-Markov chain with gray level co-occurrence method [159,160].
-Polynomial regression [161] and linear regression [162,163].
Deterministic ModelThe relationships between variables or parameters of corroded material are studied from the field experiments via images and videos. Easier to develop and could be inaccurate in terms of extrapolation results [164].-Structural health monitoring (SHM) and digital twin [165]].
-Texture descriptors with cellular automata [166].
-Others [167,168].
Table 4. Non-destructive testing techniques comparison for corrosion monitoring.
Table 4. Non-destructive testing techniques comparison for corrosion monitoring.
Vision-Based Inspection (VSI)Inexpensive and consistent monitoring.Off-line processing.
Costly in terms of computation. Concerns with minimal access.
Magnetic Flux Leakage (MFK)Inexpensive, rapid inspection of the surface and subsurface. Active type.Restricted to ferromagnetic substances.
It is required to align the magnetic flux and flaws.
Guided waves-based inspectionOn-line monitoring and active type.Ultrasonics with a high frequency. Waves are necessary. Crosstalk problems. Expensive.
Radiographic inspectionNot constrained by material kind, precise, trustworthy, active type.Safety risks are pricey.
Required results interpretation.
Acoustic emissionInexpensive. On-line monitoring, passive type.It’s crucial to interpret AE.
Table 5. Other corrosion detection methods.
Table 5. Other corrosion detection methods.
[203,204,205,206]Artificial neural network Concrete corrosion monitoring in the sewage system. Investigate pitting corrosion in steel-reinforced concrete.
[207] Hybrid machine learning AlgorithmsFind the corrosion rate in a gas pipeline.
[92]ANN and image processingDetect the corrosion level of the concrete structure of reinforced steel.
[95] Tomographic acoustic micro imaging (TAMI)Evaluate the pitted region and corrosion depth in the scanning acoustic microscopy (SAM) images.
[208]Electrochemical noise (EN)Find pitting, uniform, and passivation corrosion rates.
[97,209] Magnetic resonance imaging (MRI)For corrosion analysis.
[210]Fitting neural network (FNN)Investigate the corrosion rate in the pipelines.
[94] Thermal spraying methodAssess the corrosion mechanism and coatings.
[211]A Wasserstein distance-based analogous methodPredict the non-uniform deterioration of reinforcing materials.
[93]Fourier transform and Gaussian filterMonitor and predict the corrosion degree.
[83]Synchrotron radiation computed tomography (SRCT)Tested for corrosion rate measurement, composite failure analysis, and electrochemical reaction visualization.
[33]A python-based deep learning approachAutomatic metal corrosion (rust) detection.
Two weak classifiersAutomatically detecting corrosion on pipelines, storage tanks, and other containers.
[46]HSI (Hue, Saturation, and Intensity)Applied for corrosion detection.
[45]The hybrid wavelet packet transformsCarbon-steel pipeline corrosion detection.
[213]Wavelet image coefficientDetermine the atmospheric corrosion characteristics.
[66] HSV color spaceLocate the corroded and non-corroded regions.
[214]2D-wavelet filteringIdentify structural damage.
[47]Backpropagation method, radial basis function, and extreme learning machinePredict stress corrosion cracking.
[215]SOM (Self Organizing Map)Investigate the deterioration of corrosion-induced crack and rebar corrosion.
[216]SOM-based neural networkAnalysis of the progression of corrosion in prestressed steel and identification of the process.
[217]The hybrid intelligent algorithm methodPredicts the corrosion rate of the multiphase flow pipeline.
[218]CNNHull structural plate corrosion damage detection.
[219]Tree-based ensemble,
kernel-based technique
85% accuracy with the kernel-based technique and 81% accuracy using ensemble techniques for predicting corrosion and stress corrosion cracking.
[220]Principal component analysis-gradient boosting machine, feed-forward ANNPredict corrosion in offshore pipelines.
[221]CorrDetectorStructural corrosion detection from drone
[1]Machine learning algorithmPrevent pipeline corrosion.
[222]Wavelet analysisDetermine the effect of nitrogen on pitting corrosion.
[223]Hybrid metaheuristic
regression model
Monitoring corrosion in steel rebar in real-time.
[224]Automated methodDetermine the cause of corrosion by collecting a set of historical data.
[225]Single support vectors regression (SVR)Estimate the 3C steel corrosion rate in five distinct marine conditions.
[30]Phenomenological modelDetermine pitting corrosion of steel in concrete.
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content.

Share and Cite

MDPI and ACS Style

Imran, M.M.H.; Jamaludin, S.; Ayob, A.F.M.; Ali, A.A.I.M.; Ahmad, S.Z.A.S.; Akhbar, M.F.A.; Suhrab, M.I.R.; Zainal, N.; Norzeli, S.M.; Mohamed, S.B. Application of Artificial Intelligence in Marine Corrosion Prediction and Detection. J. Mar. Sci. Eng. 2023, 11, 256.

AMA Style

Imran MMH, Jamaludin S, Ayob AFM, Ali AAIM, Ahmad SZAS, Akhbar MFA, Suhrab MIR, Zainal N, Norzeli SM, Mohamed SB. Application of Artificial Intelligence in Marine Corrosion Prediction and Detection. Journal of Marine Science and Engineering. 2023; 11(2):256.

Chicago/Turabian Style

Imran, Md Mahadi Hasan, Shahrizan Jamaludin, Ahmad Faisal Mohamad Ayob, Ahmad Ali Imran Mohd Ali, Sayyid Zainal Abidin Syed Ahmad, Mohd Faizal Ali Akhbar, Mohammed Ismail Russtam Suhrab, Nasharuddin Zainal, Syamimi Mohd Norzeli, and Saiful Bahri Mohamed. 2023. "Application of Artificial Intelligence in Marine Corrosion Prediction and Detection" Journal of Marine Science and Engineering 11, no. 2: 256.

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop