Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Condition Monitoring and Their Applications in Industry
share announcement

Condition Monitoring and Their Applications in Industry

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Applied Industrial Technologies".

Deadline for manuscript submissions: closed (30 April 2022) | Viewed by 45676

Special Issue Editors

Prof. Dr. Tat-Hean Gan

E-Mail Website
Guest Editor
Brunel University London, Uxbridge, United Kingdom
Interests: non-destructive testing (NDT); structural health monitoring (SHM) and condition monitoring of rotating machinery
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. David Mba

E-Mail Website
Guest Editor
Executive Office, University of the Arts London, 272 High Holborn, London WC1V 7EY, UK
Interests: condition monitoring; machine fault diagnosis; model based prognostics; machine performance prediction
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Critical assets such as machinery and structures are essential for economic activities across most sectors. Condition monitoring of these critical assets is essential for optimal usage. Such monitoring processes involve detecting faults at an early stage, diagnosing the fault source and monitoring and predicting the fault progression. Achieving these objectives successfully for both machinery and structures requires use of a range of data analysis techniques that are typically developed for the specific application. While numerous theoretical data analysis, machine learning and signal processing techniques have evolved, this Special Edition presents only industrial-application-based papers in which the latest condition monitoring techniques are applied to machinery and structures.

Prof. Dr. Tat-Hean Gan
Prof. Dr. David Mba
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.

Keywords

  • Condition monitoring
  • Machinery
  • Structures
  • Diagnosis
  • Prognosis

Published Papers (19 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

16 pages, 3856 KiB  
Article
Fault Detection, Diagnosis, and Prognosis of a Process Operating under Time-Varying Conditions
by Elena Quatrini, Francesco Costantino, Xiaochuan Li and David Mba
Appl. Sci. 2022, 12(9), 4737; https://doi.org/10.3390/app12094737 - 08 May 2022
Cited by 1 | Viewed by 1749
Abstract
In the industrial panorama, many processes operate under time-varying conditions. Adapting high-performance diagnostic techniques under these relatively more complex situations is urgently needed to mitigate the risk of false alarms. Attention is being paid to fault anticipation, requiring an in-depth study of prediction [...] Read more.
In the industrial panorama, many processes operate under time-varying conditions. Adapting high-performance diagnostic techniques under these relatively more complex situations is urgently needed to mitigate the risk of false alarms. Attention is being paid to fault anticipation, requiring an in-depth study of prediction techniques. Predicting remaining life before the occurrence of faults allows for a comprehensive maintenance management protocol and facilitates the wear management of the machine, avoiding faults that could permanently compromise the integrity of such machinery. This study focuses on canonical variate analysis for fault detection in processes operating under time-varying conditions and on its contribution to the diagnostic and prognostic analysis, the latter of which was performed with machine learning techniques. The approach was validated on actual datasets from a granulator operating in the pharmaceutical sector. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

22 pages, 2795 KiB  
Article
Remaining Useful Life Estimation of Rotating Machines through Supervised Learning with Non-Linear Approaches
by Eoghan T. Chelmiah, Violeta I. McLoone and Darren F. Kavanagh
Appl. Sci. 2022, 12(9), 4136; https://doi.org/10.3390/app12094136 - 20 Apr 2022
Cited by 5 | Viewed by 2140
Abstract
Bearings are one of the most common causes of failure for rotating electric machines. Intelligent condition-based monitoring (CbM) can be used to predict rolling element bearing fault modes using non-invasive and inexpensive sensing. Strategically placed accelerometers can acquire bearing vibration signals, which contain [...] Read more.
Bearings are one of the most common causes of failure for rotating electric machines. Intelligent condition-based monitoring (CbM) can be used to predict rolling element bearing fault modes using non-invasive and inexpensive sensing. Strategically placed accelerometers can acquire bearing vibration signals, which contain salient prognostic information regarding the state of health. Machine learning (ML) algorithms are currently being investigated to accurately predict the health of machines and equipment in real time. This is highly advantageous towards reducing unscheduled maintenance, increasing the operational lifetime, as well as mitigation of the associated health risks caused by catastrophic machine failure. Motivated by this, a robust CbM system is presented for rotating machines that is suitable for various industrial applications. Novel non-linear methods for both feature engineering (one-third octave bands) and wear-state modelling (exponential) are investigated. The paper compares two main types of feature extraction, which are derived from Short-Time Fourier Transform (STFT) and Envelope Analysis (EA). In addition, two types of supervised learning, Support Vector Machines (SVM) and k-Nearest Neighbour (k-NN) are explored. The work is tested and validated on the PRONOSTIA platform dataset, with remaining useful life (RUL) classification results of up to 74.3% and a mean absolute error of 0.08 achieved. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

19 pages, 11270 KiB  
Article
Development of Permanently Installed Magnetic Eddy Current Sensor for Corrosion Monitoring of Ferromagnetic Pipelines
by Rukhshinda Wasif, Mohammad Osman Tokhi, Gholamhossein Shirkoohi, Ryan Marks and John Rudlin
Appl. Sci. 2022, 12(3), 1037; https://doi.org/10.3390/app12031037 - 20 Jan 2022
Cited by 14 | Viewed by 2202
Abstract
Permanently installed sensors are a cost-effective solution for corrosion monitoring due to their advantages, such as less human interference and continuous data acquisition. Some of the most widely used permanently installed corrosion sensors are ultrasonic thickness (UT) gauges. However, UT sensors are limited [...] Read more.
Permanently installed sensors are a cost-effective solution for corrosion monitoring due to their advantages, such as less human interference and continuous data acquisition. Some of the most widely used permanently installed corrosion sensors are ultrasonic thickness (UT) gauges. However, UT sensors are limited by the need for coupling agents between pipe surfaces and sensors. The magnetic eddy current (MEC) method, on the other hand, does not require couplant and can be used over insulations. With the development of powerful rare earth magnets, MEC sensors with low power consumption are possible, and there is the prospect of using them as permanently installed sensors. A novel wireless magnetic eddy current sensor has been designed and optimized using finite element simulation. Sensitivity studies of the sensors reveal that the excitation frequency is a critical parameter for the detection of corrosion defects. An in-depth explanation of the relationship between the sensitivity of the sensor and the excitation frequency is presented in this paper. The results of an accelerated corrosion test, conducted to simulate the service environment of the sensor, are also discussed. It was observed that the sensor signals are very sensitive to corrosion defects and show no subtle differences due to temperature and humidity changes. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

15 pages, 39463 KiB  
Article
Condition Monitoring to Enable Predictive Maintenance on a Six-Die Nut Manufacturing Machine through Force Data Analysis
by Xux Ek’ Azucena Novelo and Hsiao-Yeh Chu
Appl. Sci. 2022, 12(2), 847; https://doi.org/10.3390/app12020847 - 14 Jan 2022
Cited by 2 | Viewed by 1539
Abstract
Nut fasteners are produced by machines working around the clock. Companies generally operate with a run-to-failure or planned maintenance approach. Even with a planned maintenance schedule, however, undetected damage to the dies and non-die parts occurring between maintenance periods can cause considerable downtime [...] Read more.
Nut fasteners are produced by machines working around the clock. Companies generally operate with a run-to-failure or planned maintenance approach. Even with a planned maintenance schedule, however, undetected damage to the dies and non-die parts occurring between maintenance periods can cause considerable downtime and pervasive damage to the machine. To address this shortcoming, force data from the fourth and sixth dies of a six-die nut manufacturing machine were analysed using correlation to the best health condition on the force profile and on the force shock response spectrum profile. Fault features such as quality adjustments and damage to both die and non-die parts were detectable prior to required maintenance or machine failure. This detection was facilitated by the determination of health thresholds, whereby the force SRS profile generated a longer warning period prior to failure. The analytical approach could benefit the industry by identifying damage that would normally go undetected by operators, thereby reducing downtime, extending die life, enabling “as needed” maintenance, and optimising machine operation. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

14 pages, 2463 KiB  
Article
Development of a Reliable Vibration Based Health Indicator for Monitoring the Lubricating Condition of the Toggle Clamping System of a Plastic Injection Molding Machine
by Wani J. Morgan and Hsiao-Yeh Chu
Appl. Sci. 2022, 12(1), 196; https://doi.org/10.3390/app12010196 - 25 Dec 2021
Cited by 5 | Viewed by 4489
Abstract
Plastic injection molding has become one of the most widely used polymer processing methods due to its ability to viably produce large volumes of complex parts in a short time frame. Most of the plastic injection molding machines currently used in industry possess [...] Read more.
Plastic injection molding has become one of the most widely used polymer processing methods due to its ability to viably produce large volumes of complex parts in a short time frame. Most of the plastic injection molding machines currently used in industry possess a toggle clamping mechanism that undergoes a repeated clamping and unclamping cycle during operation. This toggle must therefore be properly lubricated to avoid catastrophic failure and eventual machine downtime. To overcome this limitation, the industry currently relies on the experience of a skilled operator, paired with a fixed empirical value, to determine the timing for re-lubrication. This method often leads to the machine operator either wasting lubricant by over-lubricating the toggle, or damaging the toggle by failing to re-lubricate when needed. Herein, we explore the use of vibration analysis to perform real-time condition monitoring of the lubrication condition of the toggle clamping system. In this study, our novel structural response analysis out performed both traditional time domain and frequency domain analyses in isolating the vibrational signatures indicative of lubricant degradation. Additionally, this study confirms that the vibration generated during the unclamping period of the toggle, proved to contain more valuable information relevant to the instantaneous lubricant quality than provided by its corresponding clamping period. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

19 pages, 10166 KiB  
Article
A Method for Detecting Surface Defects in Railhead by Magnetic Flux Leakage
by Yinliang Jia, Shicheng Zhang, Ping Wang and Kailun Ji
Appl. Sci. 2021, 11(20), 9489; https://doi.org/10.3390/app11209489 - 13 Oct 2021
Cited by 12 | Viewed by 2070
Abstract
With the rapid development of the world’s railways, rail is vital to ensure the safety of rail transit. This article focuses on the magnetic flux leakage (MFL) non-destructive detection technology of the surface defects in railhead. A Multi-sensors method is proposed. The main [...] Read more.
With the rapid development of the world’s railways, rail is vital to ensure the safety of rail transit. This article focuses on the magnetic flux leakage (MFL) non-destructive detection technology of the surface defects in railhead. A Multi-sensors method is proposed. The main sensor and four auxiliary sensors are arranged in the detection direction. Firstly, the root mean square (RMS) of the x-component of the main sensor signal is calculated. In the data more significant than the threshold, the defects are determined by the relative values of the sensors signal. The optimal distances among these sensors are calculated to the size of a defect and the lift-off. From the finite element simulation and physical experiments, it is shown that this method can effectively suppress vibration interference and improve the detection accuracy of defects. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

18 pages, 2716 KiB  
Article
Monitoring a Reverse Osmosis Process with Kernel Principal Component Analysis: A Preliminary Approach
by Elena Quatrini, Francesco Costantino, David Mba, Xiaochuan Li and Tat-Hean Gan
Appl. Sci. 2021, 11(14), 6370; https://doi.org/10.3390/app11146370 - 09 Jul 2021
Cited by 2 | Viewed by 1979
Abstract
The water purification process is becoming increasingly important to ensure the continuity and quality of subsequent production processes, and it is particularly relevant in pharmaceutical contexts. However, in this context, the difficulties arising during the monitoring process are manifold. On the one hand, [...] Read more.
The water purification process is becoming increasingly important to ensure the continuity and quality of subsequent production processes, and it is particularly relevant in pharmaceutical contexts. However, in this context, the difficulties arising during the monitoring process are manifold. On the one hand, the monitoring process reveals various discontinuities due to different characteristics of the input water. On the other hand, the monitoring process is discontinuous and random itself, thus not guaranteeing continuity of the parameters and hindering a straightforward analysis. Consequently, further research on water purification processes is paramount to identify the most suitable techniques able to guarantee good performance. Against this background, this paper proposes an application of kernel principal component analysis for fault detection in a process with the above-mentioned characteristics. Based on the temporal variability of the process, the paper suggests the use of past and future matrices as input for fault detection as an alternative to the original dataset. In this manner, the temporal correlation between process parameters and machine health is accounted for. The proposed approach confirms the possibility of obtaining very good monitoring results in the analyzed context. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

11 pages, 1318 KiB  
Article
Monitoring of Industrial Machine Using a Novel Blind Feature Extraction Approach
by Siu Ki Ho, Harish Chandra Nedunuri, Wamadeva Balachandran, Jamil Kanfoud and Tat-Hean Gan
Appl. Sci. 2021, 11(13), 5792; https://doi.org/10.3390/app11135792 - 22 Jun 2021
Cited by 3 | Viewed by 1431
Abstract
Machinery with several rotating and stationary components tends to produce non-stationary and random vibration signatures due to the fluctuations in the input loads and process defects due to long hours of operation. Traditional heuristics methods are suitable for the detection of fault signatures, [...] Read more.
Machinery with several rotating and stationary components tends to produce non-stationary and random vibration signatures due to the fluctuations in the input loads and process defects due to long hours of operation. Traditional heuristics methods are suitable for the detection of fault signatures, however, they become more complicated when the level of uncertainty or randomness exceeds beyond control. A novel methodology to identify these fault signatures using optimal filtering of vibration data is proposed to eliminate any false alarms and is expected to provide a higher probability of correct diagnosis. In this paper, a detailed pipeline of the algorithms are presented along with the results of the investigation that was carried out. These investigations are performed using open-source vibration data published by the NASA prognostics centre. The performance of these algorithms are evaluated based on the ground truth results published by NASA researchers. Based on the performance of these algorithms several parameters are fine-tuned to ensure generalisation and reliable performance. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

27 pages, 15352 KiB  
Article
Predicting Remaining Useful Life of Rolling Bearings Based on Reliable Degradation Indicator and Temporal Convolution Network with the Quantile Regression
by Qiaoping Tian and Honglei Wang
Appl. Sci. 2021, 11(11), 4773; https://doi.org/10.3390/app11114773 - 23 May 2021
Cited by 10 | Viewed by 2114
Abstract
High precision and multi information prediction results of bearing remaining useful life (RUL) can effectively describe the uncertainty of bearing health state and operation state. Aiming at the problem of feature efficient extraction and RUL prediction during rolling bearings operation degradation process, through [...] Read more.
High precision and multi information prediction results of bearing remaining useful life (RUL) can effectively describe the uncertainty of bearing health state and operation state. Aiming at the problem of feature efficient extraction and RUL prediction during rolling bearings operation degradation process, through data reduction and key features mining analysis, a new feature vector based on time-frequency domain joint feature is found to describe the bearings degradation process more comprehensively. In order to keep the effective information without increasing the scale of neural network, a joint feature compression calculation method based on redefined degradation indicator (DI) was proposed to determine the input data set. By combining the temporal convolution network with the quantile regression (TCNQR) algorithm, the probability density forecasting at any time is achieved based on kernel density estimation (KDE) for the conditional distribution of predicted values. The experimental results show that the proposed method can obtain the point prediction results with smaller errors. Compared with the existing quantile regression of long short-term memory network(LSTMQR), the proposed method can construct more accurate prediction interval and probability density curve, which can effectively quantify the uncertainty of bearing running state. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

19 pages, 7270 KiB  
Article
Numerical Modelling of Ultrasonic Guided Wave Propagation and Defect Detection in Offshore Steel Sheet Piles
by Anuj Dhutti, Anurag Dhutti, Sergio Malo, Hugo Marques, Wamadeva Balachandran and Tat-Hean Gan
Appl. Sci. 2021, 11(9), 4076; https://doi.org/10.3390/app11094076 - 29 Apr 2021
Cited by 1 | Viewed by 2142
Abstract
Sheet piles are significantly more prone to advanced corrosion rates due to accelerated low water corrosion. Current inspection and assessment techniques are costly, time-consuming and labour-intensive. Guided wave testing (GWT) has gained increased attention due to its capability of screening long distances; however, [...] Read more.
Sheet piles are significantly more prone to advanced corrosion rates due to accelerated low water corrosion. Current inspection and assessment techniques are costly, time-consuming and labour-intensive. Guided wave testing (GWT) has gained increased attention due to its capability of screening long distances; however, it has not been used previously to inspect the active zone in steel sheet piles. This paper focuses on the numerical modelling of wave propagation and defect detection in U-shaped piles to demonstrate the capabilities of GWT for the inspection of non-accessible areas of steel sheet piles. Two shear transducer arrays were designed, bearing high SH0 mode purity and directionality. A wave propagation comparison study concluded that the back wall reflection signal from the web of a U-pile was 11.5% higher than the respective signal from the plate, and the excitation signal in the flange, at 5.65 m and 7.12 m, was respectively 35% and 46% less than the excitation signal in the web at the same distance. Defect reflection, measured from five representative defect scenarios, ranged from 7.5 to 47% of the signal amplitude in the web of the pile and 5 to 32.5% in the flange of the pile. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

15 pages, 2274 KiB  
Article
Increasing Wind Turbine Drivetrain Bearing Vibration Monitoring Detectability Using an Artificial Neural Network Implementation
by Daniel Strömbergsson, Pär Marklund and Kim Berglund
Appl. Sci. 2021, 11(8), 3588; https://doi.org/10.3390/app11083588 - 16 Apr 2021
Cited by 4 | Viewed by 1497
Abstract
The highest costs due to premature failures in wind turbine drivetrains are related to defects in the gearbox, with bearing failures being overrepresented. Vibration monitoring has been identified as the primary tool to detect and diagnose these types of failures. However, late or [...] Read more.
The highest costs due to premature failures in wind turbine drivetrains are related to defects in the gearbox, with bearing failures being overrepresented. Vibration monitoring has been identified as the primary tool to detect and diagnose these types of failures. However, late or no signs of the failures are still being reported. Artificial neural networks (ANNs) has been shown to favourably be used as a classifier of bearing failures to increase the detection and diagnosis performance, which requires labelled data when training for all types of considered failures. However, less work has been done with an ANN used to create descriptive functions of the vibration and turbine operation data relationship and thereby negating inherent variance in the vibration data and increasing the detectability when a defect appears. Therefore, this study utilizes the relationship between the rotational speed recorded during a vibration measurement and the calculated condition indicator values of specific bearing failures in three wind turbine gearbox failures. An ANN establishes a function between the rotational speed and condition indicator values with healthy training data collected before the failure occurred. Thereafter, whole datasets leading up to the changing of the gearboxes is used to predict the condition indicator values without the failure influence. The difference between the predicted and true values show an increased sensitivity of the detection in two cases of gearbox output shaft bearing failures as well as indicating a planet bearing failure which with the previous data had gone undetected. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

19 pages, 805 KiB  
Article
A Bayesian Control Chart for Monitoring Process Variance
by Chien-Hua Lin, Ming-Che Lu, Su-Fen Yang and Ming-Yung Lee
Appl. Sci. 2021, 11(6), 2729; https://doi.org/10.3390/app11062729 - 18 Mar 2021
Cited by 9 | Viewed by 2263
Abstract
Automation in the service industry is emerging as a new wave of industrial revolution. Standardization and consistency of service quality is an important part of the automation process. The quality control methods widely used in the manufacturing industry can provide service quality measurement [...] Read more.
Automation in the service industry is emerging as a new wave of industrial revolution. Standardization and consistency of service quality is an important part of the automation process. The quality control methods widely used in the manufacturing industry can provide service quality measurement and service process monitoring. In particular, the control chart as an online monitoring technique can be used to quickly detect whether a service process is out of control. However, the control of the service process is more difficult than that of the manufacturing process because the variability of the service process comes from widespread and complex factors. First of all, the distribution of the service process is usually non-normal or unknown. Moreover, the skewness of the process distribution can be time-varying, even if the process is in control. In this study, a Bayesian procedure is applied to construct a Phase II exponential weighted moving average (EWMA) control chart for monitoring the variance of a distribution-free process. We explore the sampling properties of the new monitoring statistic, which is suitable for monitoring the time-varying process distribution. The average run lengths (ARLs) of the proposed Bayesian EWMA variance chart are calculated, and they show that the chart performs well. The simulation studies for a normal process, exponential process, and the mixed process of normal and exponential distribution prove that our chart can quickly detect any shift of a process variance. Finally, a numerical example of bank service time is used to illustrate the application of the proposed Bayesian EWMA variance chart and confirm the performance of the process control. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

21 pages, 34854 KiB  
Article
Multi-Objective Instance Weighting-Based Deep Transfer Learning Network for Intelligent Fault Diagnosis
by Kihoon Lee, Soonyoung Han, Van Huan Pham, Seungyon Cho, Hae-Jin Choi, Jiwoong Lee, Inwoong Noh and Sang Won Lee
Appl. Sci. 2021, 11(5), 2370; https://doi.org/10.3390/app11052370 - 07 Mar 2021
Cited by 16 | Viewed by 3145
Abstract
Fault diagnosis is a top-priority task for the health management of manufacturing processes. Deep learning-based methods are widely used to secure high fault diagnosis accuracy. Actually, it is difficult and expensive to collect large-scale data in industrial fields. Several prerequisite problems can be [...] Read more.
Fault diagnosis is a top-priority task for the health management of manufacturing processes. Deep learning-based methods are widely used to secure high fault diagnosis accuracy. Actually, it is difficult and expensive to collect large-scale data in industrial fields. Several prerequisite problems can be solved using transfer learning for fault diagnosis. Data from the source domain that are different but related to the target domain are used to increase the diagnosis performance of the target domain. However, a negative transfer occurs that degrades diagnosis performance due to the transfer when the discrepancy between and within domains is large. A multi-objective instance weighting-based transfer learning network is proposed to solve this problem and successfully applied to fault diagnosis. The proposed method uses a newly devised multi-objective instance weight to deal with practical situations where domain discrepancy is large. It adjusts the influence of the domain data on model training through two theoretically different indicators. Knowledge transfer is performed differentially by sorting instances similar to the target domain in terms of distribution with useful information for the target task. This domain optimization process maximizes the performance of transfer learning. A case study using an industrial robot and spot-welding testbed is conducted to verify the effectiveness of the proposed technique. The performance and applicability of transfer learning in the proposed method are observed in detail through the same case study as the actual industrial field for comparison. The diagnostic accuracy and robustness are high, even when few data are used. Thus, the proposed technique is a promising tool that can be used for successful fault diagnosis. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

14 pages, 4179 KiB  
Article
Measurement Method for Fluid Pressure Fluctuation in Fluid-Conveying Pipe Using PVDF Piezoelectric Film Sensor
by Song Liu, Xianmei Wu, Yuanyuan Kong and Xiuqian Peng
Appl. Sci. 2021, 11(3), 1299; https://doi.org/10.3390/app11031299 - 01 Feb 2021
Cited by 4 | Viewed by 2262
Abstract
As a representative fluid-transporting system, fluid-conveying pipes play an essential role in many fields. For a fluid-conveying pipe system in operation, fluid pulsation in pipes contains much information about fluid flow parameters (flow velocity, fluid pressure, etc.). Therefore, the measurement of fluid pulsation [...] Read more.
As a representative fluid-transporting system, fluid-conveying pipes play an essential role in many fields. For a fluid-conveying pipe system in operation, fluid pulsation in pipes contains much information about fluid flow parameters (flow velocity, fluid pressure, etc.). Therefore, the measurement of fluid pulsation is important for understanding the internal fluid flow. To use polyvinylidene fluoride (PVDF) piezoelectric film sensors to indirectly measure the pressure fluctuation of the internal fluid, we simulated a fluid-conveying pipe with PVDF piezoelectric film sensors attached to the outer pipe wall. The simulation results showed that the variation of voltage signal of PVDF, circumferential stress and strain of the pipe wall, and the pressure fluctuation of internal fluid were highly positively correlated, which proved that the PVDF piezoelectric film sensor can be applied to indirectly measure the pressure fluctuation of internal fluid. We also studied the influences of flow velocity pulsation and mechanical vibration caused by the pipeline pump during operation. It is found that the flow velocity pulsation had little influence on the measurements of the variation of circumferential stress and strain of the pipe wall and the internal fluid pressure fluctuation. When both ends of the pipe were fixed by hoops, mechanical vibration had little influence on the measurement of the variation of circumferential stress and strain of the pipe wall as well as the fluid pressure fluctuation. Finally, simulation results were verified by experiments. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

19 pages, 7051 KiB  
Article
A Hierarchical Decision Fusion Diagnosis Method for Rolling Bearings
by Jingzhou Fei, Xinran Lv, Yunpeng Cao and Shuying Li
Appl. Sci. 2021, 11(2), 739; https://doi.org/10.3390/app11020739 - 14 Jan 2021
Cited by 2 | Viewed by 1724
Abstract
In order to achieve accurate fault diagnosis of rolling bearings, a hierarchical decision fusion diagnosis method for rolling bearings is proposed. The hierarchical back propagation neural networks (BPNNs) architecture includes a fault detection layer, fault isolation layer and fault degree identification layer, which [...] Read more.
In order to achieve accurate fault diagnosis of rolling bearings, a hierarchical decision fusion diagnosis method for rolling bearings is proposed. The hierarchical back propagation neural networks (BPNNs) architecture includes a fault detection layer, fault isolation layer and fault degree identification layer, which reduce the calculation cost and enhance the maintainability of the fault diagnosis algorithm. By wavelet packet decomposition and signal reconstruction of the raw vibration signal of a rolling bearing, the time-domain features of the reconstructed signals are extracted as the input of each BPNN and the accuracy of fault detection, fault isolation and degree estimation are improved. By using the majority voting method, the diagnosis results of multiple BPNNs are fused, which avoids the missed diagnosis and misdiagnosis caused by the insensitivity of a vibration characteristic to a specific fault. Finally, the proposed method is verified experimentally. The results show that the proposed method can accurately detect the fault of rolling bearings, recognize the fault location and estimate the fault severity under different operating conditions. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

18 pages, 6878 KiB  
Article
Failure Threshold Determination of Rolling Element Bearings Using Vibration Fluctuation and Failure Modes
by Mehdi Behzad, Sajjad Feizhoseini, Hesam Addin Arghand, Ali Davoodabadi and David Mba
Appl. Sci. 2021, 11(1), 160; https://doi.org/10.3390/app11010160 - 26 Dec 2020
Cited by 4 | Viewed by 3019
Abstract
One of the challenges in predicting the remaining useful life (RUL) of rolling element bearings (REBs) is determining a proper failure threshold (FT). In the literature, the FT is usually assumed to be a constant value of an extracted feature from the vibration [...] Read more.
One of the challenges in predicting the remaining useful life (RUL) of rolling element bearings (REBs) is determining a proper failure threshold (FT). In the literature, the FT is usually assumed to be a constant value of an extracted feature from the vibration signals. In this study, a degradation indicator was extracted to describe damage to REBs by applying principal component analysis (PCA) to their run-to-failure data. The relationship between this degradation indicator and the vibration peak was represented through a joint probability distribution using statistical copula models. The FT was proposed as a probability distribution based on the fluctuation increase in the vibration trend. A set of run-to-failure tests was conducted. Applying the proposed method to this dataset led to various FTs for the different failure modes that occurred. It is shown that, for inner race degradation, a higher FT can be assumed than for rolling element degradation. This could help extend the lives of REBs regarding the degrading elements. A dataset for an industrial machine was also analyzed and it is shown that the proposed model estimated a reasonable and proper FT in an actual case study. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

17 pages, 3105 KiB  
Article
Fleet Resilience: Evaluating Maintenance Strategies in Critical Equipment
by Orlando Durán, Javier Aguilar, Andrea Capaldo and Adolfo Arata
Appl. Sci. 2021, 11(1), 38; https://doi.org/10.3390/app11010038 - 23 Dec 2020
Cited by 6 | Viewed by 2047
Abstract
Resilience is an intrinsic characteristic of systems. Through it, the capacity of a system to react to the existence of disruptive events is expressed. A series of metrics to represent systems’ resilience have been proposed, however, only one indicator relates the availability of [...] Read more.
Resilience is an intrinsic characteristic of systems. Through it, the capacity of a system to react to the existence of disruptive events is expressed. A series of metrics to represent systems’ resilience have been proposed, however, only one indicator relates the availability of the system to this characteristic. With such a metric, it is possible to relate the topological aspects of a system and the resources available in order to be able to promptly respond to the loss of performance as a result of unexpected events. This work proposes the adaptation and application of such a resilience index to assess the influence of different maintenance strategies and topologies in fleets’ resilience. In addition, an application study considering an actual mining fleet is provided. A set of critical assets was identified and represented using reliability block diagrams. Monte Carlo simulation experiments were conducted and the system availability data were extracted. Resilience indexes were obtained in order to carry out the definition of the best maintenance policies in critical equipment and the assessment of the impact of modifying system redundancies. The main results of this work lead to the overall conclusion that redundancy is an important system attribute in order to improve resiliency along time. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

18 pages, 2787 KiB  
Article
Energy-Based Prognosis of the Remaining Useful Life of the Coating Segments in Hot Rolling Mill
by Ioannis Anagiannis, Nikolaos Nikolakis and Kosmas Alexopoulos
Appl. Sci. 2020, 10(19), 6827; https://doi.org/10.3390/app10196827 - 29 Sep 2020
Cited by 8 | Viewed by 2467
Abstract
The field of prognostic maintenance aims at predicting the remaining time for a system or component to continue being used under the desired performance. This time is usually named as Remaining Useful Life (RUL). The current study proposes a novel approach for the [...] Read more.
The field of prognostic maintenance aims at predicting the remaining time for a system or component to continue being used under the desired performance. This time is usually named as Remaining Useful Life (RUL). The current study proposes a novel approach for the RUL estimation of coating segments placed on a hot rolling mill machine. A prediction method was developed, providing real-time updates of the RUL prediction during the rolling milling process. The proposed approach performs energy analysis on measurements of segment surface temperatures and hydraulic forces. It uses nonparametric statistical processes to update the predictions, within a prediction horizon/window, indicating the number of remaining products to be processed. To assess the probability of failure within the defined prediction window, Maximum Likelihood Estimation is used. The proposed methodology was implemented in a software prototype in the MATLAB environment and tested in an industrial use case coming from a steel parts manufacturer, facilitating testing and validation of the suggested approach. Real-world data were acquired from the operational machine, while the validation results support that the proposed methodology demonstrates reasonable performance and robustness against product type variations. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

19 pages, 4071 KiB  
Article
A Sparse Autoencoder-Based Unsupervised Scheme for Pump Fault Detection and Isolation
by Xiaoxia Liang, Fang Duan, Ian Bennett and David Mba
Appl. Sci. 2020, 10(19), 6789; https://doi.org/10.3390/app10196789 - 28 Sep 2020
Cited by 20 | Viewed by 2350
Abstract
Pumps are one of the most critical machines in the petrochemical process. Condition monitoring of such parts and detecting faults at an early stage are crucial for reducing downtime in the production line and improving plant safety, efficiency and reliability. This paper develops [...] Read more.
Pumps are one of the most critical machines in the petrochemical process. Condition monitoring of such parts and detecting faults at an early stage are crucial for reducing downtime in the production line and improving plant safety, efficiency and reliability. This paper develops a fault detection and isolation scheme based on an unsupervised machine learning method, sparse autoencoder (SAE), and evaluates the model on industrial multivariate data. The Mahalanobis distance (MD) is employed to calculate the statistical difference of the residual outputs between monitoring and normal states and is used as a system-wide health indicator. Furthermore, fault isolation is achieved by a reconstruction-based two-dimensional contribution map, in which the variables with larger contributions are responsible for the detected fault. To demonstrate the effectiveness of the proposed scheme, two case studies are carried out based on a multivariate data set from a pump system in an oil and petrochemical factory. The classical principal component analysis (PCA) method is compared with the proposed method and results show that SAE performs better in terms of fault detection than PCA, and can effectively isolate the abnormal variables, which can hence help effectively trace the root cause of the detected fault. Full article
(This article belongs to the Special Issue Condition Monitoring and Their Applications in Industry)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-19
Back to TopTop