Submit to Processes Review for Processes Propose a Special Issue

Journal Browser

Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis

Print Special Issue Flyer
Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Processes (ISSN 2227-9717). This special issue belongs to the section "Automation Control Systems".

Deadline for manuscript submissions: closed (30 November 2020) | Viewed by 49177

Share This Special Issue

Special Issue Editors

Dr. Mohand Djeziri

E-Mail Website
Guest Editor

LIS-Lab, Aix Marseille University, 13007 Marseille, France
Interests: fault diagnosis; failure prognosis; modeling; simulation; AI
Special Issues, Collections and Topics in MDPI journals

Dr. Marc Bendahan

E-Mail Website
Guest Editor

IM2NP-Lab, Aix-Marseille University, 13007 Marseille, France
Interests: conception and characterization of micro-sensors; micro-systems for the environment and building, for nuclear and for health
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Early drift-like fault diagnosis is necessary to determine, as fast as possible, the components that must be replaced or repaired. The earlier the diagnosis, the more eﬃcient the maintenance actions. When a fault is detected (degradation), the remaining time for the component before it is unable to accomplish its mission must be estimated using a prognosis module. A reliable and precise estimation of the remaining useful life is important in order to schedule the maintenance actions that optimize the availability and maintenance costs. The maintenance costs are a signiﬁcant part of the overall cost of system exploitation. In particular, maintenance can be expensive in emergency situations when equipment is suddenly damaged and can no longer perform its function. In this case, maintenance actions should be performed rapidly to get the system working. These actions are more costly because they were unexpected. Thus, to avoid the occurrence of this kind of situations, predictive maintenance can be used by anticipating and correcting the failure of equipment before the occurrence of excessive damage.

Machines are widely used both in industrial and in everyday life, and have different structures and properties and are dedicated to various fields of application like energy and transportation. Among the most used rotating machines, we find AC synchronous machines, AC induction machines, DC machines, turbomachinery, pumping devices, turbines, and different thermal engines. The monitoring of these systems in order to ensure their safety and availability (service quality) and to reduce their maintenance costs is therefore an important economic and social issue. Therefore, one can observe growing interest in the scientific and industrial community for the development of tools for life cycle analysis, fault diagnosis and prognosis, as well as the predictive maintenance of these kind of processes.

This Special Issue aims to bring together researchers and industrials with complementary skills that covers a wide spectrum of methods and applications in the field of machine monitoring, fault diagnosis and fault prognosis, as well as the predictive maintenance, and will give rise to new solutions to the research problems that remain open in this field such as:

- Improving reliability
- Increased life expectancy
- Reduction of pollution
- Smart grid
- Stabilization of frequencies
- Noise pollution
- Changes in structure and operating modes
- Complexity of the environment
- Industry 4.0 challenges
- Fault detection and isolation
- Fault prognosis

Dr. Mohand Djeziri

Dr. Marc Bendahan
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. Processes is an international peer-reviewed open access monthly 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

• Machine learning • Deep learning • Hybrid automata • Hybrid bond graphs • Hybrid observers • Petri nets • Hybrid neural networks • Particle filters • Dynamic Bayesian networks • Switching systems • Non-linear systems • Centralized and decentralized decision structures • Active fault diagnosis • Fault-tolerant control • Self-adaptive and incremental fault diagnosis • Abrupt/drift parametric/structure fault diagnosis • Abrupt/drift discrete/configuration fault diagnosis • Sensor/controller/actuator/process fault diagnosis • System reliability and risk analysis • Decision support systems • Real world applications such as: Manufacturing systems, Wind turbines, Smart management of energy demand/response, Telecommunication networks, Power electronic converters, Transport systems, Power generators, Intrusion detection and cybersecurity, Robotics, Internet of Things, next-generation airspace applications, etc.

Published Papers (13 papers)

Download All Papers

Editorial

Jump to: Research, Review, Other

3 pages, 142 KiB

Open AccessEditorial

Special Issue “Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis”

by Mohand Djeziri and Marc Bendahan

Processes 2021, 9(3), 532; https://doi.org/10.3390/pr9030532 - 17 Mar 2021

Cited by 1 | Viewed by 1559

Abstract

Fault diagnosis and failure prognosis aim to reduce downtime of the systems and to optimise their performance by replacing preventive and corrective maintenance strategies with predictive or conditional ones [...] Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

Research

Jump to: Editorial, Review, Other

17 pages, 2703 KiB

Open AccessFeature PaperArticle

A Wavelet Transform-Assisted Convolutional Neural Network Multi-Model Framework for Monitoring Large-Scale Fluorochemical Engineering Processes

by Xintong Li, Kun Zhou, Feng Xue, Zhibing Chen, Zhiqiang Ge, Xu Chen and Kai Song

Processes 2020, 8(11), 1480; https://doi.org/10.3390/pr8111480 - 17 Nov 2020

Cited by 15 | Viewed by 2450

Abstract

The barely satisfactory monitoring situation of the hypertoxic fluorochemical engineering processes requires the application of advanced strategies. In order to deal with the non-linear mechanism of the processes and the highly complicated correlation among variables, a wavelet transform-assisted convolutional neural network (CNN) based multi-model dynamic monitoring method was proposed. A preliminary CNN model was first trained to detect faults and to diagnose part of them with minimum computational burden and time delay. Then, a wavelet assisted secondary CNN model was trained to diagnose the remaining faults with the highest possible accuracy. In this step, benefitting from the scale decomposition capabilities of the wavelet transform function, the inherent noise and redundant information could be filtered out and the useful signal was transformed into a higher compact space. In this space, a well-designed secondary CNN model was trained to further improve the fault diagnosis performance. The application on a refrigerant-producing process located in East China showed that not only regular faults but also hard to diagnose faults were successfully detected and diagnosed. More importantly, the unique online queue assembly updating strategy proposed remarkably reduced the inherent time delay of the deep-learning methods. Additionally, the application of it on the widely used Tennessee Eastman process benchmark strongly proved the superiority of it in fault detection and diagnosis over other deep-learning methods. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

25 pages, 9274 KiB

Open AccessArticle

PEMFC Transient Response Characteristics Analysis in Case of Temperature Sensor Failure

by Jaeyoung Han, Sangseok Yu and Jinwon Yun

Processes 2020, 8(11), 1353; https://doi.org/10.3390/pr8111353 - 26 Oct 2020

Cited by 6 | Viewed by 2029

Abstract

In this study, transient responses of a polymer electrolyte fuel cell system were performed to understand the effect of sensor fault signal on the temperature sensor of the stack and the coolant inlet. We designed a system-level fuel cell model including a thermal management system, and a controller to analyze the dynamic behavior of fuel cell system applied with variable sensor fault scenarios such as stuck, offset, and scaling. Under drastic load variations, transient behavior is affected by fault signals of the sensor. Especially, the net power of the faulty system is 45.9 kW. On the other hand, the net power of the fault free system is 46.1 kW. Therefore, the net power of a faulty system is about 0.2 kW lower than that of a fault-free system. This analysis can help in understanding the transient behavior of fuel cell systems at the system level under fault situations and provide a proper failure avoidance control strategy for the fuel cell system. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

16 pages, 10386 KiB

Open AccessArticle

Motor Fault Detection Using Wavelet Transform and Improved PSO-BP Neural Network

by Chun-Yao Lee and Yi-Hsin Cheng

Processes 2020, 8(10), 1322; https://doi.org/10.3390/pr8101322 - 21 Oct 2020

Cited by 40 | Viewed by 3486

Abstract

This paper proposes a motor fault detection method based on wavelet transform (WT) and improved PSO-BP neural network which is combined with improved particle swarm optimization (PSO) and a back propagation (BP) neural network with linearly increasing inertia weight. First, this research used WT to analyze the current signals of the healthy motor, bearing damage motor, stator winding inter-turn short circuit motor, and broken rotor bar motor. Second, features after completing the signal analysis were extracted, and three types of classifiers were used to classify. The results show that the improved PSO-BP neural network can effectively detect the cause of failure. In addition, in order to simulate the actual operating environment of the motor, this study added white noise with signal noise ratios of 30 dB, 25 dB, and 20 dB to verify that this model has a better anti-noise ability. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

20 pages, 8157 KiB

Open AccessArticle

Degradation Status Recognition of Axial Piston Pumps under Variable Conditions Based on Improved Information Entropy and Gaussian Mixture Models

by Chuanqi Lu, Zhi Zheng and Shaoping Wang

Processes 2020, 8(9), 1084; https://doi.org/10.3390/pr8091084 - 2 Sep 2020

Cited by 5 | Viewed by 1926

Abstract

Axial piston pumps are crucial for the safe operation of hydraulic systems and usually work under variable operating conditions. However, deterioration status recognition for such pumps under variable conditions has rarely been reported until now. Therefore, it is valuable to develop effective methods suitable for processing variable conditions. Firstly, considering that information entropy has strong robustness to variable conditions and empirical mode decomposition (EMD) has the advantages of processing nonlinear and nonstationary signals, a new degradation feature parameter, named local instantaneous energy moment entropy, which combines information entropy theory and EMD, is proposed in this paper. To obtain more accurate degradation feature, a waveform matching extrema mirror extension EMD, which is used to suppress the end effects of EMD decomposition, was employed to decompose the original pump’s outlet pressure signals, taking the quasi-periodic characteristics of the signals into consideration. Subsequently, given that different failure modes of pumps have different degradation rates in practice, which makes it difficult to effectively recognize degradation status when using the modeling methods that need the normal and failure data, a Gaussian mixture model (GMM), which has no need for failure data when building a degradation identification model, was introduced to capture the new degradation status index (DSI) to quantitatively assess the degradation state of the pumps. Finally, the effectiveness of the proposed approach was validated using both simulations and experiments. It was demonstrated that the defined local instantaneous energy moment entropy is able to effectively characterize the degree of degradation of the pumps under variable operating conditions, and the DSI derived from the GMM is able to accurately identify different degradation states when compared with the previously published methods. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Graphical abstract

18 pages, 5916 KiB

Open AccessArticle

Establish Induction Motor Fault Diagnosis System Based on Feature Selection Approaches with MRA

by Chun-Yao Lee and Meng-Syun Wen

Processes 2020, 8(9), 1055; https://doi.org/10.3390/pr8091055 - 29 Aug 2020

Cited by 11 | Viewed by 2957

Abstract

This paper proposes a feature selection (FS) approach, namely, correlation and fitness value-based feature selection (CFFS). CFFS is an improvement feature selection approach of correlation-based feature selection (CFS) for the common failure cases of the induction motor. CFFS establishes the induction motor fault detection (FD) system with artificial neural network (ANN). This study analyzes the current signal of the induction motor with multiresolution analysis (MRA), extracts the features, and uses feature selection approaches (ReliefF, CFS, and CFFS) to reduce the number of features and maintain the accuracy of the induction motor fault detection system. Finally, the induction motor fault detection system is trained by the feature selection approaches selected features. The best induction motor fault detection system will be established through the comparison of the efficiency of these FS approaches. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

26 pages, 11079 KiB

Open AccessArticle

A Non-Delay Error Compensation Method for Dual-Driving Gantry-Type Machine Tool

by Qi Liu, Hong Lu, Xinbao Zhang, Yu Qiao, Qian Cheng, Yongquan Zhang and Yongjing Wang

Processes 2020, 8(7), 748; https://doi.org/10.3390/pr8070748 - 27 Jun 2020

Cited by 6 | Viewed by 2930

Abstract

The drive at the center of gravity (DCG) principle has been adopted in computer numerical control (CNC) machines and industrial robots that require heavy-duty and quick feeds. Using this principle requires accurate corrections of positioning errors. Conventional error compensation methods may cause vibrations and unstable control performances due to the delay between compensation and motor motion. This paper proposes a new method to reduce the positioning errors of the dual-driving gantry-type machine tool (DDGTMT), namely, a typical DCG-principle-based machine tool. An error prediction method is proposed to characterize errors online. An algorithm is proposed to quickly and accurately compensate the errors of the DDGTMT. Experiment results verify that the non-delay error compensation method proposed in this paper can effectively improve the accuracy of the DDGTMT. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

26 pages, 3221 KiB

Open AccessFeature PaperArticle

Incremental Modeling and Monitoring of Embedded CPU-GPU Chips

by Oussama Djedidi and Mohand Djeziri

Processes 2020, 8(6), 678; https://doi.org/10.3390/pr8060678 - 9 Jun 2020

Cited by 2 | Viewed by 2861

Abstract

This paper presents a monitoring framework to detect drifts and faults in the behavior of the central processing unit (CPU)-graphics processing unit (GPU) chips powering them. To construct the framework, an incremental model and a fault detection and isolation (FDI) algorithm are hereby proposed. The reference model is composed of a set of interconnected exchangeable subsystems that allows it to be adapted to changes in the structure of the system or operating modes, by replacing or extending its components. It estimates a set of variables characterizing the operating state of the chip from only two global inputs. Then, through analytical redundancy, the estimated variables are compared to the output of the system in the FDI module, which generates alarms in the presence of faults or drifts in the system. Furthermore, the interconnected nature of the model allows for the direct localization and isolation of any detected abnormalities. The implementation of the proposed framework requires no additional instrumentation as the used variables are measured by the system. Finally, we use multiple experimental setups for the validation of our approach and also proving that it can be applied to most of the existing embedded systems. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

10 pages, 1421 KiB

Open AccessArticle

Progressive System: A Deep-Learning Framework for Real-Time Data in Industrial Production

by Yifeng Liu, Wei Zhang and Wenhao Du

Processes 2020, 8(6), 649; https://doi.org/10.3390/pr8060649 - 29 May 2020

Cited by 3 | Viewed by 2277

Abstract

Deep learning based on a large number of high-quality data plays an important role in many industries. However, deep learning is hard to directly embed in the real-time system, because the data accumulation of the system depends on real-time acquisitions. However, the analysis tasks of such systems need to be carried out in real time, which makes it impossible to complete the analysis tasks by accumulating data for a long time. In order to solve the problems of high-quality data accumulation, high timeliness of the data analysis, and difficulty in embedding deep-learning algorithms directly in real-time systems, this paper proposes a new progressive deep-learning framework and conducts experiments on image recognition. The experimental results show that the proposed framework is effective and performs well and can reach a conclusion similar to the deep-learning framework based on large-scale data. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

19 pages, 6016 KiB

Open AccessArticle

Research on State Recognition and Failure Prediction of Axial Piston Pump Based on Performance Degradation Data

by Rui Guo, Zhiqian Zhao, Saiyu Huo, Zhijie Jin, Jingyi Zhao and Dianrong Gao

Processes 2020, 8(5), 609; https://doi.org/10.3390/pr8050609 - 20 May 2020

Cited by 12 | Viewed by 3384

Abstract

Degradation state recognition and failure prediction are the key steps of prognostic and health management (PHM), which directly affect the reliability of the equipment and the selection of preventive maintenance strategy. Given the problem that the distinction between feature vectors is not obvious and the accuracy of fault prediction is low, a method based on multi-class Gaussian process classification and Gaussian process regression (GPR) is studied by the vibration signal and flow signal in six degraded states of the axial piston pump. For degradation state recognition, the variational mode decomposition (VMD) was used to decompose the vibration signal, and obtaining intrinsic mode function (IMF) components with rich information. Subsequently, multi-scale permutation entropy (MPE) was employed to select feature vectors of IMF components in different states. In order to reduce feature dimensions and improve recognition performance, ReliefF was used to select feature vectors with high weight, then a method based on multi-class Gaussian process classification was established by using these feature vectors to realize the research on the degradation state recognition. The test results demonstrate that the method can effectively identify the degradation state. Its recognition rate reaches 98.9%. Besides, for failure prediction, through the analysis of the wear process and wear mechanism of the valve plate, the curve fitting between the flow and the wear amount was performed by GPR to realize the failure prediction of the axial piston pump. Depending on the evaluation index, the GPR obtained a better failure prediction effect. The results will assist in the realization of predictive maintenance, and which also has significant practical value in project items. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

17 pages, 6035 KiB

Open AccessArticle

A General Stroke-Based Model for the Straightening Process of D-Type Shaft

by Hong Lu, Yue Zang, Xinbao Zhang, Yongquan Zhang and Le Li

Processes 2020, 8(5), 528; https://doi.org/10.3390/pr8050528 - 30 Apr 2020

Cited by 4 | Viewed by 3282

Abstract

D-type shaft is widely used in precision machinery products such as motors and intelligent robots. The straightness of the D-type shaft is an important factor influencing its machining accuracy and dynamic performance, which is normally improved by the three-point pressure straightening process. This paper proposes a general stroke-based model to predict the relevant parameters for the straightening process of D-type shaft, considering the bending deformations in three dimensions. The distribution of stress and strain inside the D-type shaft during the straightening process in arbitrary position of the cross section and the bending moment are analyzed by using linear hardening material model. The relationship between deflection and the internal stress on the loading position is explored, and a straightening stroke model of D-type shaft is obtained. The correctness of the stroke-based straightening model has been validated by finite element method (FEM) simulation analysis and bending experiments. The results show that the proposed model can improve the accuracy and efficiency of the D-type shaft straightening process. Furthermore, it provides a novel method for the modelling of the straightening process regarding the special shaped bar stock. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

Review

Jump to: Editorial, Research, Other

15 pages, 2112 KiB

Open AccessReview

Cyclostationary Analysis towards Fault Diagnosis of Rotating Machinery

by Shengnan Tang, Shouqi Yuan and Yong Zhu

Processes 2020, 8(10), 1217; https://doi.org/10.3390/pr8101217 - 28 Sep 2020

Cited by 6 | Viewed by 3114

Abstract

In the light of the significance of the rotating machinery and the possible severe losses resulted from its unexpected defects, it is vital and meaningful to exploit the effective and feasible diagnostic methods of its faults. Among them, the emphasis of the analysis approaches for fault type and severity is on the extraction of useful components in the fault features. On account of the common cyclostationarity of vibration signal under faulty states, fault diagnosis methods based on cyclostationary analysis play an essential role in the rotatory machine. Based on it, the fundamental definition and classification of cyclostationarity are introduced briefly. The mathematical principles of the essential cyclic spectral analysis are outlined. The significant applications of cyclostationary theory are highlighted in the fault diagnosis of the main rotating machinery, involving bearing, gear, and pump. Finally, the widely-used methods on the basis of cyclostationary theory are concluded, and the potential research directions are prospected. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

Other

Jump to: Editorial, Research, Review

21 pages, 5283 KiB

Open AccessCase Report

Designing and Manufacturing of Automatic Robotic Lawn Mower

by Juinne-Ching Liao, Shun-Hsing Chen, Zi-Yi Zhuang, Bo-Wei Wu and Yu-Jen Chen

Processes 2021, 9(2), 358; https://doi.org/10.3390/pr9020358 - 15 Feb 2021

Cited by 15 | Viewed by 16021

Abstract

This study is about the manufacturing of a personified automatic robotic lawn mower with image recognition. The system structure is that the platform above the crawler tracks is combined with the lawn mower, steering motor, slide rail, and webcam to achieve the purpose of personification. Crawler tracks with a strong grip and good ability to adapt to terrain are selected as a moving vehicle to simulate human feet. In addition, a lawn mower mechanism is designed to simulate the left and right swing of human mowing to promote efficiency and innovation, and then human eyes are replaced by Webcam to identify obstacles. A human-machine interface is added so that through the mobile phone remote operation, users can choose a slow mode, inching mode, and obstacle avoidance mode on the human-machine interface. When the length of both sides of the rectangular area is input to the program, the automatic robotic lawn mower will complete the instruction according to the specified path. The chip of a Digital Signal Processor (DSP) TMS320F2808 is used as the core controller, and Raspberry Pi is used as image recognition and human-machine interface design. This robot can reduce labor costs and improve the efficiency of mowing by remote control. In addition to the use as an automatic mower on farms, this study concept can also be used in the lawn maintenance of golf courses and school playgrounds. Full article

(This article belongs to the Special Issue Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances in Machine Learning and Deep Learning Based Machine Fault Diagnosis and Prognosis

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (13 papers)

Editorial

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI