Submit to Special Issue Submit Abstract to Special Issue Review for Entropy Propose a Special Issue

Journal Browser

New Trends in Fault Diagnosis and Prognosis for Engineering Applications: From Signal Processing to Machine Learning and Deep Learning

Special Issue Editors
Special Issue Information
Keywords
Related Special Issues
Published Papers

A special issue of Entropy (ISSN 1099-4300). This special issue belongs to the section "Multidisciplinary Applications".

Deadline for manuscript submissions: 31 December 2024 | Viewed by 6837

Share This Special Issue

Special Issue Editors

Prof. Dr. Claude Delpha

E-Mail
Guest Editor

CNRS, CentraleSupélec, Laboratoire des Signaux et Systèmes, Université Paris Saclay, 91400 Orsay, France
Interests: data and signal processing; incipient fault diagnosis; detection and estimation; data hiding; watermarking; complex systems; statistical learning
Special Issues, Collections and Topics in MDPI journals

Prof. Dr. Demba Diallo

E-Mail Website
Guest Editor

CNRS, CentraleSupélec, Group of Electrical Engineering of Paris, Université Paris Saclay, 91400 Orsay, France
Interests: electrical drives; incipient fault diagnosis; fault tolerant control; renewable energy
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Complex industrial systems require increasing performances to guaranty security and safety. Fault diagnosis and prognosis are two of the major concerns that lead to these requirements and provide the reduction in maintenance costs. Typical applications needing these requirements include the monitoring of transportation systems (automobiles, aircraft, and trains); green energy generation, transportation, storage, and distribution systems (e.g., nuclear power plants, wind turbines, photovoltaic panels, smart grids, hydro generators, etc.), and industrial processes.

In smart systems, faults are detected at an early stage and classified, and the system lifetime is predicted to optimize the maintenance operations. To meet these requirements, new monitoring algorithms are continuously developed. These algorithms integrate state-of-the-art signal and data analysis/processing techniques, entropy-based study, statistical learning, and machine learning or deep learning approaches.

This Issue will focus on the application of new trends in signal and analysis/learning/processing techniques for the health monitoring of complex systems. Particular attention is paid either to statistical-/entropy-based detection/estimation techniques or machine-learning-/deep-learning-based diagnosis techniques. Their particular use for engineering applications are also of interest. Many approaches are concerned with topics such as quantitative approaches with wide and efficient physical modeling, qualitative approaches, and data-driven ones. For this Issue, either theoretical or applicative works will be considered. Particular attention will be paid to applications in tune with time such as human health, renewable-energy-based systems, energy conversion systems, smart grids, mechanical systems, vehicular and industrial applications, etc.

Prof. Dr. Claude Delpha
Prof. Dr. Demba Diallo
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. Entropy 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 2600 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

fault and diagnosis and prognosis
fault detection and estimation
fault isolation and classification
time occurrence detection for diagnosis
engineering system health monitoring
fault and system modeling
data and signal processing for diagnosis
statistical analysis and learning for diagnosis
performance analysis for health monitoring
machine learning for fault diagnosis and prognosis
deep learning for fault diagnosis
predictive maintenance and RUL
application to industrial applications

Related Special Issues

Fault Diagnosis Method Based on Information Theoretic: From Theory to Applications in Entropy (13 articles)
Fault Diagnosis Methods Based on Information Theory or Machine Learning: From Theory to Application in Entropy (22 articles)

Published Papers (7 papers)

Download All Papers

Research

15 pages, 2610 KiB

Open AccessArticle

A Novel Fault Diagnosis Method of High-Speed Train Based on Few-Shot Learning

by Yunpu Wu, Jianhua Chen, Xia Lei and Weidong Jin

Entropy 2024, 26(5), 428; https://doi.org/10.3390/e26050428 - 16 May 2024

Viewed by 140

Abstract

Ensuring the safe and stable operation of high-speed trains necessitates real-time monitoring and diagnostics of their suspension systems. While machine learning technology is widely employed for industrial equipment fault diagnosis, its effective application relies on the availability of a large dataset with annotated fault data for model training. However, in practice, the availability of informational data samples is often insufficient, with most of them being unlabeled. The challenge arises when traditional machine learning methods encounter a scarcity of training data, leading to overfitting due to limited information. To address this issue, this paper proposes a novel few-shot learning method for high-speed train fault diagnosis, incorporating sensor-perturbation injection and meta-confidence learning to improve detection accuracy. Experimental results demonstrate the superior performance of the proposed method, which introduces perturbations, compared to existing methods. The impact of perturbation effects and class numbers on fault detection is analyzed, confirming the effectiveness of our learning strategy. Full article

(This article belongs to the Special Issue New Trends in Fault Diagnosis and Prognosis for Engineering Applications: From Signal Processing to Machine Learning and Deep Learning)

28 pages, 10836 KiB

Open AccessArticle

Fuzzy Entropy-Assisted Deconvolution Method and Its Application for Bearing Fault Diagnosis

by Di Pei, Jianhai Yue and Jing Jiao

Entropy 2024, 26(4), 304; https://doi.org/10.3390/e26040304 - 29 Mar 2024

Viewed by 594

Abstract

Vibration signal analysis is an important means for bearing fault diagnosis. Affected by the vibration of other machine parts, external noise and the vibration transmission path, the impulses induced by a bearing defect in the measured vibrations are very weak. Blind deconvolution (BD) methods can counteract the effect of the transmission path and enhance the fault impulses. Most BD methods highlight fault features of the filtered signals by impulse-featured objective functions (OFs). However, residual noise in the filtered signals has not been well tackled. To overcome this problem, a fuzzy entropy-assisted deconvolution (FEAD) method is proposed. First, FEAD takes advantage of the high noise sensitivity of fuzzy entropy (FuzzyEn) and constructs a weighted FuzzyEn–kurtosis OF to enhance the fault impulses while suppressing noise interference. Then, the PSO algorithm is used to iteratively solve the optimal inverse deconvolution filter. Finally, envelope spectrum analysis is performed on the filtered signal to realize bearing fault diagnosis. The feasibility of FEAD was first verified by the bearing fault simulation signals at constant and variable speeds. The bearing test signals from Case Western Reserve University (CWRU), the railway wheelset and the test bench validated the good performance of FEAD in fault feature enhancement. A comparison with and quantitative results for the other state-of-the-art BD methods indicated the superiority of the proposed method. Full article

(This article belongs to the Special Issue New Trends in Fault Diagnosis and Prognosis for Engineering Applications: From Signal Processing to Machine Learning and Deep Learning)

► Show Figures

Figure 1

16 pages, 1025 KiB

Open AccessArticle

Dynamic Feature Extraction-Based Quadratic Discriminant Analysis for Industrial Process Fault Classification and Diagnosis

by Hanqi Li, Mingxing Jia and Zhizhong Mao

Entropy 2023, 25(12), 1664; https://doi.org/10.3390/e25121664 - 16 Dec 2023

Cited by 1 | Viewed by 1151

Abstract

This paper introduces a novel method for enhancing fault classification and diagnosis in dynamic nonlinear processes. The method focuses on dynamic feature extraction within multivariate time series data and utilizes dynamic reconstruction errors to augment the feature set. A fault classification procedure is then developed, using the weighted maximum scatter difference (WMSD) dimensionality reduction criterion and quadratic discriminant analysis (QDA) classifier. This method addresses the challenge of high-dimensional, sample-limited fault classification, offering early diagnosis capabilities for online samples with smaller amplitudes than the training set. Validation is conducted using a cold rolling mill simulation model, with performance compared to classical methods like linear discriminant analysis (LDA) and kernel Fisher discriminant analysis (KFD). The results demonstrate the superiority of the proposed method for reliable industrial process monitoring and fault diagnosis. Full article

(This article belongs to the Special Issue New Trends in Fault Diagnosis and Prognosis for Engineering Applications: From Signal Processing to Machine Learning and Deep Learning)

► Show Figures

Figure 1

19 pages, 2575 KiB

Open AccessArticle

A Multi-Featured Factor Analysis and Dynamic Window Rectification Method for Remaining Useful Life Prognosis of Rolling Bearings

by Cheng Peng, Yuanyuan Zhao, Changyun Li, Zhaohui Tang and Weihua Gui

Entropy 2023, 25(11), 1539; https://doi.org/10.3390/e25111539 - 13 Nov 2023

Cited by 1 | Viewed by 873

Abstract

Currently, the research on the predictions of remaining useful life (RUL) of rotating machinery mainly focuses on the process of health indicator (HI) construction and the determination of the first prediction time (FPT). In complex industrial environments, the influence of environmental factors such as noise may affect the accuracy of RUL predictions. Accurately estimating the remaining useful life of bearings plays a vital role in reducing costly unscheduled maintenance and increasing machine reliability. To overcome these problems, a health indicator construction and prediction method based on multi-featured factor analysis are proposed. Compared with the existing methods, the advantages of this method are the use of factor analysis, to mine hidden common factors from multiple features, and the construction of health indicators based on the maximization of variance contribution after rotation. A dynamic window rectification method is designed to reduce and weaken the stochastic fluctuations in the health indicators. The first prediction time was determined by the cumulative gradient change in the trajectory of the HI. A regression-based adaptive prediction model is used to learn the evolutionary trend of the HI and estimate the RUL of the bearings. The experimental results of two publicly available bearing datasets show the advantages of the method. Full article

(This article belongs to the Special Issue New Trends in Fault Diagnosis and Prognosis for Engineering Applications: From Signal Processing to Machine Learning and Deep Learning)

► Show Figures

Figure 1

15 pages, 499 KiB

Open AccessArticle

Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis

by Christoph Bienefeld, Florian Michael Becker-Dombrowsky, Etnik Shatri and Eckhard Kirchner

Entropy 2023, 25(9), 1278; https://doi.org/10.3390/e25091278 - 30 Aug 2023

Cited by 1 | Viewed by 1035

Abstract

The engineering challenge of rolling bearing condition monitoring has led to a large number of method developments over the past few years. Most commonly, vibration measurement data are used for fault diagnosis using machine learning algorithms. In current research, purely data-driven deep learning methods are becoming increasingly popular, aiming for accurate predictions of bearing faults without requiring bearing-specific domain knowledge. Opposing this trend in popularity, the present paper takes a more traditional approach, incorporating domain knowledge by evaluating a variety of feature engineering methods in combination with a random forest classifier. For a comprehensive feature engineering study, a total of 42 mathematical feature formulas are combined with the preprocessing methods of envelope analysis, empirical mode decomposition, wavelet transforms, and frequency band separations. While each single processing method and feature formula is known from the literature, the presented paper contributes to the body of knowledge by investigating novel series connections of processing methods and feature formulas. Using the CWRU bearing fault data for performance evaluation, feature calculation based on the processing method of frequency band separation leads to particularly high prediction accuracies, while at the same time being very efficient in terms of low computational effort. Additionally, in comparison with deep learning approaches, the proposed feature engineering method provides excellent accuracies and enables explainability. Full article

(This article belongs to the Special Issue New Trends in Fault Diagnosis and Prognosis for Engineering Applications: From Signal Processing to Machine Learning and Deep Learning)

► Show Figures

Figure 1

18 pages, 1613 KiB

Open AccessArticle

A Multiscale Recursive Attention Gate Federation Method for Multiple Working Conditions Fault Diagnosis

by Zhiqiang Zhang, Funa Zhou, Chaoge Wang, Chenglin Wen, Xiong Hu and Tianzhen Wang

Entropy 2023, 25(8), 1165; https://doi.org/10.3390/e25081165 - 4 Aug 2023

Viewed by 774

Abstract

Federated learning (FL) is an effective method when a single client cannot provide enough samples for multiple condition fault diagnosis of bearings since it can combine the information provided by multiple clients. However, some of the client’s working conditions are different; for example, different clients are in different stages of the whole life cycle, and different clients have different loads. At this point, the status of each client is not equal, and the traditional FL approach will lead to some clients’ useful information being ignored. The purpose of this paper is to investigate a multiscale recursive FL framework that makes the server more focused on the useful information provided by the clients to ensure the effectiveness of FL. The proposed FL method can build reliable multiple working condition fault diagnosis models due to the increased focus on useful information in the FL process and the full utilization of server information through local multiscale feature fusion. The validity of the proposed method was verified with the Case Western Reserve University benchmark dataset. With less local client training data and complex fault types, the proposed method improves the accuracy of fault diagnosis by 23.21% over the existing FL fault diagnosis. Full article

(This article belongs to the Special Issue New Trends in Fault Diagnosis and Prognosis for Engineering Applications: From Signal Processing to Machine Learning and Deep Learning)

► Show Figures

Figure 1

15 pages, 4993 KiB

Open AccessArticle

EnRDeA U-Net Deep Learning of Semantic Segmentation on Intricate Noise Roads

by Xiaodong Yu, Ta-Wen Kuan, Shih-Pang Tseng, Ying Chen, Shuo Chen, Jhing-Fa Wang, Yuhang Gu and Tuoli Chen

Entropy 2023, 25(7), 1085; https://doi.org/10.3390/e25071085 - 19 Jul 2023

Cited by 5 | Viewed by 1386

Abstract

Road segmentation is beneficial to build a vision-controllable mission-oriented self-driving bot, e.g., the Self-Driving Sweeping Bot, or SDSB, for working in restricted areas. Using road segmentation, the bot itself and physical facilities may be protected and the sweeping efficiency of the SDSB promoted. However, roads in the real world are generally exposed to intricate noise conditions as a result of changing weather and climate effects; these include sunshine spots, shadowing caused by trees or physical facilities, traffic obstacles and signs, and cracks or sealing signs resulting from long-term road usage, as well as different types of road materials, such as cement or asphalt; all of these factors greatly influence the effectiveness of road segmentation. In this work, we investigate the extension of Primordial U-Net by the proposed EnRDeA U-Net, which uses an input channel applying a Residual U-Net block as an encoder and an attention gate in the output channel as a decoder, to validate a dataset of intricate road noises. In addition, we carry out a detailed analysis of the nets’ features and segmentation performance to validate the intricate noises dataset on three U-Net extensions, i.e., the Primordial U-Net, Residual U-Net, and EnRDeA U-Net. Finally, the nets’ structures, parameters, training losses, performance indexes, etc., are presented and discussed in the experimental results. Full article

(This article belongs to the Special Issue New Trends in Fault Diagnosis and Prognosis for Engineering Applications: From Signal Processing to Machine Learning and Deep Learning)

► Show Figures