Artificial Intelligence and Complex Systems Analysis in Transportation and Maintenance

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: 20 April 2024 | Viewed by 25491

Special Issue Editors

Department of Industrial Engineering, Bologna University, 40126 Bologna, Italy
Interests: analysis, planning, design, and optimization of production processes and technologies
Special Issues, Collections and Topics in MDPI journals
Department of Production and Logistics, Georg-August-University of Göttingen, 37073 Göttingen, Germany
Interests: digital production, retail and logistics operations; sustainability in global supply chains; qualification and knowledge management in logistics; efficiency measurement/data envelopment analysis; artificial intelligence and human-computer-interaction (HCI)
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

This Special Issue focuses on the theory and application of maintenance methodologies in the transportation field. Transportation includes applications in several fields such as automotive, aerospace and industry sectors. Due to the potential advantages of maintenance strategies in terms of cost savings and asset monitoring, prognostic and health management (PHM) methodologies are receiving a broad, positive consensus among scientific and practitioner communities.

In fact, mechanical, electrical, electronic and thermal operations of related complex systems (i.e., powertrain, steering, suspension, electronics or control, among others) are supported by an increased number of sensors and measurements, which require advanced processing solutions in terms of prognostic and health management methodologies.

In this regard, the field of artificial intelligence is continuously providing significant advancements in machine learning, evolutionary computation and expert systems, which have a huge potential in facing current challenges in the maintenance field applied to the transportation sector, such as (i) the limited availability of representative data, (ii) continuous operation and changes in environmental conditions, (iii) uneven sources of information and (iv) limited computation and communication resources in edge solutions for real-time monitoring.

Thus, the focus of this Special Issue is to provide a forum for PHM researchers and practitioners to discuss the applicability and challenges of artificial intelligence in complex systems analysis and maintenance schemes applied to the transportation sector. Papers describing both novel applications and related theory are encouraged, with a specific focus on streaming analysis that provides real-time feedback on the health condition of assets.

We are soliciting papers on topics including, but are not limited to:

  • The application of real-time monitoring solutions;
  • Incremental learning techniques for fault detection and identification;
  • Novelty detection strategies and fault isolation procedures;
  • Applications of PHM in IoT contexts;
  • Degradation modeling of components operating in different operating conditions;
  • System-level prognostics;
  • The definition of requirements and challenges for the implementation of predictive maintenance in transportation;
  • The integration of predictive maintenance with preventive policies;
  • Cost–benefit analysis of predictive maintenance.

Prof. Dr. Alberto Regattieri
Prof. Dr. Matthias Klumpp
Dr. Miguel Delgado-Prieto
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Published Papers (10 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

18 pages, 2224 KiB  
Article
Multicast Routing Based on Data Envelopment Analysis and Markovian Decision Processes for Multimodal Transportation
by Mohanad R. Aljanabi, Keivan Borna, Shamsollah Ghanbari and Ahmed J. Obaid
Appl. Sci. 2024, 14(5), 2115; https://doi.org/10.3390/app14052115 - 04 Mar 2024
Viewed by 527
Abstract
In the context of Iraq’s evolving transportation landscape and the strategic implications of the Belt and Road Initiative, this study pioneers a comprehensive framework for optimizing multimodal transportation systems. The study implemented a decision-making framework for multimodal transportation, combining data envelopment analysis (DEA) [...] Read more.
In the context of Iraq’s evolving transportation landscape and the strategic implications of the Belt and Road Initiative, this study pioneers a comprehensive framework for optimizing multimodal transportation systems. The study implemented a decision-making framework for multimodal transportation, combining data envelopment analysis (DEA) efficiency scores and a Markov decision process (MDP) to optimize transportation strategies. The DEA scores captured decision-making unit (DMU) performance in various aspects, while the MDP rewards facilitated strategic mode selection, promoting efficiency, cost-effectiveness, and environmental considerations. Although our method incurs a total cost approximately 29% higher than MRMQoS, it delivers a nearly 26% reduction in delay compared to MCSTM. Despite MRMQoS yielding an 8.3% higher profit than our approach, our proposed scheme exhibits an 11.7% higher profit compared to MCSTM. In terms of computational time, our method achieves an average CPU time positioned between MCSTM and MRMQoS, with MCSTM showing about 1.6% better CPU time than our approach, while our method displays a 9.5% improvement in computational time compared to MRMQoS. Additionally, concerning CO2 emissions, the proposed model consistently outperforms other models across various network sizes. The percentage decrease in CO2 emissions achieved by the proposed model is 7.26% and 31.25% when compared against MRMQoS and MCSTM for a network size of 25, respectively. Full article
Show Figures

Figure 1

19 pages, 4420 KiB  
Article
Zero-Shot Generative AI for Rotating Machinery Fault Diagnosis: Synthesizing Highly Realistic Training Data via Cycle-Consistent Adversarial Networks
by Luigi Gianpio Di Maggio, Eugenio Brusa and Cristiana Delprete
Appl. Sci. 2023, 13(22), 12458; https://doi.org/10.3390/app132212458 - 17 Nov 2023
Cited by 1 | Viewed by 851
Abstract
The Intelligent Fault Diagnosis of rotating machinery calls for a substantial amount of training data, posing challenges in acquiring such data for damaged industrial machinery. This paper presents a novel approach for generating synthetic data using a Generative Adversarial Network (GAN) with cycle [...] Read more.
The Intelligent Fault Diagnosis of rotating machinery calls for a substantial amount of training data, posing challenges in acquiring such data for damaged industrial machinery. This paper presents a novel approach for generating synthetic data using a Generative Adversarial Network (GAN) with cycle consistency loss function known as cycleGAN. The proposed method aims to generate synthetic data that could effectively replace real experimental data. The generative model is trained to transform wavelet images of simulated vibrational signals into authentic data obtained from machinery with damaged bearings. The utilization of Maximum Mean Discrepancy (MMD) and Fréchet Inception Distance (FID) demonstrates a noteworthy resemblance between synthetic and real experimental data. Also, the generative model enables the synthesis of data that may have been entirely lacking from the experimental observation, indicating generative zero-shot learning capabilities. The efficacy of synthetic data in training diagnosis algorithms by means of Transfer Learning (TL) on Convolutional Neural Networks (CNNs) has been demonstrated to be comparable to that of real data. The study has been validated by means of the test rig for medium-sized industrial bearings accessible at the Politecnico di Torino. Full article
Show Figures

Figure 1

16 pages, 617 KiB  
Article
An Artificial Intelligence Approach for Improving Maintenance to Supervise Machine Failures and Support Their Repair
by Izabela Rojek, Małgorzata Jasiulewicz-Kaczmarek, Mariusz Piechowski and Dariusz Mikołajewski
Appl. Sci. 2023, 13(8), 4971; https://doi.org/10.3390/app13084971 - 15 Apr 2023
Cited by 13 | Viewed by 7083
Abstract
Maintenance of production equipment has a key role in ensuring business continuity and productivity. Determining the implementation time and the appropriate selection of the scope of maintenance activities are necessary not only for the operation of industrial equipment but also for effective planning [...] Read more.
Maintenance of production equipment has a key role in ensuring business continuity and productivity. Determining the implementation time and the appropriate selection of the scope of maintenance activities are necessary not only for the operation of industrial equipment but also for effective planning of the demand for own maintenance resources (spare parts, people, finances). A number of studies have been conducted in the last decade and many attempts have been made to use artificial intelligence (AI) techniques to model and manage maintenance. The aim of the article is to discuss the possibility of using AI methods and techniques to anticipate possible failures and respond to them in advance by carrying out maintenance activities in an appropriate and timely manner. The indirect aim of these studies is to achieve more effective management of maintenance activities. The main method applied is computational analysis and simulation based on the real industrial data set. The main results show that the effective use of preventive maintenance requires large amounts of reliable annotated sensor data and well-trained machine-learning algorithms. Scientific and technical development of the above-mentioned group of solutions should be implemented in such a way that they can be used by companies of equal size and with different production profiles. Even relatively simple solutions as presented in the article can be helpful here, offering high efficiency at low implementation costs. Full article
Show Figures

Figure 1

16 pages, 5857 KiB  
Article
Towards a Digital Twin Warehouse through the Optimization of Internal Transport
by Joaquín S. Félix-Cigalat and Rosario Domingo
Appl. Sci. 2023, 13(8), 4652; https://doi.org/10.3390/app13084652 - 07 Apr 2023
Cited by 1 | Viewed by 1663
Abstract
Through the construction of parametric simulation models in which possible storage space distributions and positioning logics are also considered as variables, it is possible to build scenarios that allow analyzing the changing reality of storage needs in order to minimize material movements in [...] Read more.
Through the construction of parametric simulation models in which possible storage space distributions and positioning logics are also considered as variables, it is possible to build scenarios that allow analyzing the changing reality of storage needs in order to minimize material movements in each case, optimize internal transportation, and increase the efficiency of production processes. This article shows a particular analysis of a restricted storage space in height, typical to when it comes to logistics associated with raw material in a “big bag” format made of recycled and easily deteriorated material. In conjunction, a location management solution based on passive RFID (radio-frequency identification) tags has been chosen. The process is carried out through simulations with object-oriented discrete event software, where the optimization of the internal transport associated with the layout is carried out considering network theory to define the shortest path between warehouse nodes. The combination of both approaches allows, on the one hand, the evaluation of alternatives in terms of distribution and positioning logics, while the implemented system enables the possibility of making agile changes in the physical configuration of this type of storage space. Full article
Show Figures

Figure 1

28 pages, 12051 KiB  
Article
An Unsupervised Anomaly Detection Based on Self-Organizing Map for the Oil and Gas Sector
by Lorenzo Concetti, Giovanni Mazzuto, Filippo Emanuele Ciarapica and Maurizio Bevilacqua
Appl. Sci. 2023, 13(6), 3725; https://doi.org/10.3390/app13063725 - 15 Mar 2023
Cited by 1 | Viewed by 2084
Abstract
Anomaly detection plays a crucial role in preserving industrial plant health. Detecting and identifying anomalies helps prevent any production system from damage and failure. In complex systems, such as oil and gas, many components need to be kept operational. Predicting which parts will [...] Read more.
Anomaly detection plays a crucial role in preserving industrial plant health. Detecting and identifying anomalies helps prevent any production system from damage and failure. In complex systems, such as oil and gas, many components need to be kept operational. Predicting which parts will break down in a time interval or identifying which ones are working under abnormal conditions can significantly increase their reliability. Moreover, it underlines how the use of artificial intelligence is also emerging in the process industry and not only in manufacturing. In particular, the state-of-the-art analysis reveals a growing interest in the subject and that most identified algorithms are based on neural network approaches in their various forms. In this paper, an approach for fault detection and identification was developed using a Self-Organizing Map algorithm, as the results of the obtained map are intuitive and easy to understand. In order to assign each node in the output map a single class that is unique, the purity of each node is examined. The samples are identified and mapped in a two-dimensional space, clustering all readings into six macro-areas: (i) steady-state area, (ii) water anomaly macro-area, (iii) air-water anomaly area, (iv) tank anomaly area, (v) air anomaly macro-area, (vi) and steady-state transition area. Moreover, through the confusion matrix, it is found that the algorithm achieves an overall accuracy of 90 per cent and can classify and recognize the state of the system. The proposed algorithm was tested on an experimental plant at Università Politecnica delle Marche. Full article
Show Figures

Figure 1

22 pages, 5361 KiB  
Article
Explainable AI for Machine Fault Diagnosis: Understanding Features’ Contribution in Machine Learning Models for Industrial Condition Monitoring
by Eugenio Brusa, Luca Cibrario, Cristiana Delprete and Luigi Gianpio Di Maggio
Appl. Sci. 2023, 13(4), 2038; https://doi.org/10.3390/app13042038 - 04 Feb 2023
Cited by 16 | Viewed by 3516
Abstract
Although the effectiveness of machine learning (ML) for machine diagnosis has been widely established, the interpretation of the diagnosis outcomes is still an open issue. Machine learning models behave as black boxes; therefore, the contribution given by each of the selected features to [...] Read more.
Although the effectiveness of machine learning (ML) for machine diagnosis has been widely established, the interpretation of the diagnosis outcomes is still an open issue. Machine learning models behave as black boxes; therefore, the contribution given by each of the selected features to the diagnosis is not transparent to the user. This work is aimed at investigating the capabilities of the SHapley Additive exPlanation (SHAP) to identify the most important features for fault detection and classification in condition monitoring programs for rotating machinery. The authors analyse the case of medium-sized bearings of industrial interest. Namely, vibration data were collected for different health states from the test rig for industrial bearings available at the Mechanical Engineering Laboratory of Politecnico di Torino. The Support Vector Machine (SVM) and k-Nearest Neighbour (kNN) diagnosis models are explained by means of the SHAP. Accuracies higher than 98.5% are achieved for both the models using the SHAP as a criterion for feature selection. It is found that the skewness and the shape factor of the vibration signal have the greatest impact on the models’ outcomes. Full article
Show Figures

Figure 1

22 pages, 7397 KiB  
Article
Estimates of Internal Forces in Torsionally Braced Steel I-Girder Bridges Using Deep Neural Networks
by Jeonghwa Lee, Seongbin Ryu, Woochul Chung, Seungjun Kim and Young Jong Kang
Appl. Sci. 2023, 13(3), 1499; https://doi.org/10.3390/app13031499 - 23 Jan 2023
Cited by 2 | Viewed by 1396
Abstract
The bracing components in steel I-girder bridge systems are essential structural components for the bridges to restrain their rotation due to lateral torsional buckling (LTB). Current design specifications require bracing components to be installed to prevent I-girder sections from unexpectedly twisting due to [...] Read more.
The bracing components in steel I-girder bridge systems are essential structural components for the bridges to restrain their rotation due to lateral torsional buckling (LTB). Current design specifications require bracing components to be installed to prevent I-girder sections from unexpectedly twisting due to instability. To estimate the bracing internal forces acting on the bracing elements, we can use approximate design equations that provide considerably conservative design values. Otherwise, it is necessary to conduct a thorough finite element analysis considering initial imperfections to obtain accurate bracing internal forces in the steel I-girder bracing systems. This study aims to provide estimation models based on deep neural network (DNN) algorithms to more accurately estimate the internal forces acting on the bracing element compared with the current design methodology when LTB occurs. This is conducted by constructing structural response data based on the geometrically nonlinear analysis with imperfections to provide accurate bracing internal forces, namely bracing moments (Mbr) and bracing forces (Fbr). To propose prediction models, 16 input and three output variables were selected for training the structural response data. Furthermore, a parametric study on the hyperparameters used in DNN models was analyzed for the number of hidden layers, neurons, and epochs. Based on statistical performance indices (i.e., RMSE, MSE, MAE, and R2), the estimated values using DNN models were evaluated to determine the best prediction models. Finally, DNN models that more accurately estimate internal forces (Mbr, Fbr) in bracing elements, and that provide the best prediction results depending on hyperparameters (numbers of hidden layers, neurons, and epochs), are proposed. Full article
Show Figures

Figure 1

15 pages, 2697 KiB  
Article
Binary Dense SIFT Flow Based Position-Information Added Two-Stream CNN for Pedestrian Action Recognition
by Sang Kyoo Park, Jun Ho Chung, Dong Sung Pae and Myo Taeg Lim
Appl. Sci. 2022, 12(20), 10445; https://doi.org/10.3390/app122010445 - 17 Oct 2022
Cited by 4 | Viewed by 1487
Abstract
Pedestrian behavior recognition in the driving environment is an important technology to prevent pedestrian accidents by predicting the next movement. It is necessary to recognize current pedestrian behavior to predict future pedestrian behavior. However, many studies have recognized human visible characteristics such as [...] Read more.
Pedestrian behavior recognition in the driving environment is an important technology to prevent pedestrian accidents by predicting the next movement. It is necessary to recognize current pedestrian behavior to predict future pedestrian behavior. However, many studies have recognized human visible characteristics such as face, body parts or clothes, but few have recognized pedestrian behavior. It is challenging to recognize pedestrian behavior in the driving environment due to the changes in the camera field of view due to the illumination conditions in outdoor environments and vehicle movement. In this paper, to predict pedestrian behavior, we introduce a position-information added two-stream convolutional neural network (CNN) with multi task learning that is robust to the limited conditions of the outdoor driving environment. The conventional two-stream CNN is the most widely used model for human-action recognition. However, the conventional two-stream CNN based on optical flow has limitations regarding pedestrian behavior recognition in a moving vehicle because of the assumptions of brightness constancy and piecewise smoothness. To solve this problem for a moving vehicle, the binary descriptor dense scale-invariant feature transform (SIFT) flow, a feature-based matching algorithm, is robust in moving-pedestrian behavior recognition, such as walking and standing, in a moving vehicle. However, recognizing cross attributes, such as crossing or not crossing the street, is challenging using the binary descriptor dense SIFT flow because people who cross the road or not act the same walking action, but their location on the image is different. Therefore, pedestrian position information should be added to the conventional binary descriptor dense SIFT flow two-stream CNN. Thus, learning biased toward action attributes is evenly learned across action and cross attributes. In addition, YOLO detection and the Siamese tracker are used instead of the ground-truth boundary box to prove the robustness in the action- and cross-attribute recognition from a moving vehicle. The JAAD and PIE datasets were used for training, and only the JAAD dataset was used as a testing dataset for comparison with other state-of-the-art research on multitask and single-task learning. Full article
Show Figures

Figure 1

24 pages, 5305 KiB  
Article
Data-Driven Fault Detection and Diagnosis: Challenges and Opportunities in Real-World Scenarios
by Francesca Calabrese, Alberto Regattieri, Marco Bortolini and Francesco Gabriele Galizia
Appl. Sci. 2022, 12(18), 9212; https://doi.org/10.3390/app12189212 - 14 Sep 2022
Cited by 3 | Viewed by 2474
Abstract
The pervasive digital innovation of the last decades has led to a remarkable transformation of maintenance strategies. The data collected from machinery and the extraction of valuable information through machine learning (ML) have assumed a crucial role. As a result, data-driven predictive maintenance [...] Read more.
The pervasive digital innovation of the last decades has led to a remarkable transformation of maintenance strategies. The data collected from machinery and the extraction of valuable information through machine learning (ML) have assumed a crucial role. As a result, data-driven predictive maintenance (PdM) has received significant attention from academics and industries. However, practical issues are limiting the implementation of PdM in manufacturing plants. These issues are related to the availability, quantity, and completeness of the collected data, which do not contain all machinery health conditions, are often unprovided with the contextual information needed by ML models, and are huge in terms of gigabytes per minute. As an extension of previous work by the authors, this paper aims to validate the methodology for streaming fault and novelty detection that reduces the quantity of data to transfer and store, allows the automatic collection of contextual information, and recognizes novel system behaviors. Five distinct datasets are collected from the field, and results show that streaming and incremental clustering-based approaches are effective tools for obtaining labeled datasets and real-time feedback on the machinery’s health condition. Full article
Show Figures

Figure 1

Review

Jump to: Research

13 pages, 2238 KiB  
Review
Revolutionizing Tire Quality Control: AI’s Impact on Research, Development, and Real-Life Applications
by Marcin Tamborski, Izabela Rojek and Dariusz Mikołajewski
Appl. Sci. 2023, 13(14), 8406; https://doi.org/10.3390/app13148406 - 20 Jul 2023
Cited by 2 | Viewed by 3175
Abstract
The tire industry plays a key role in ensuring safe and efficient transportation. With 1.1 billion vehicles worldwide relying on tires for optimum performance, tire quality control is of paramount importance. In recent years, the integration of artificial intelligence (AI) has revolutionized various [...] Read more.
The tire industry plays a key role in ensuring safe and efficient transportation. With 1.1 billion vehicles worldwide relying on tires for optimum performance, tire quality control is of paramount importance. In recent years, the integration of artificial intelligence (AI) has revolutionized various industries, and the tire industry is no exception. In this article, we take a look at the current state of quality control in the tire industry and the transformative impact of AI on this crucial process. Automatic detection of tire defects remains an important and challenging scientific and technical problem in industrial tire quality control. The integration of artificial intelligence into tire quality control has the potential to transform the tire industry, leading to safer, more reliable, and more sustainable tires. Thanks to continuous progress and a proactive approach to challenges, the tire industry is prepared for a future in which artificial intelligence will play a key role in delivering high-quality tires to consumers around the world. Full article
Show Figures

Figure 1

Back to TopTop