Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
3.0
2.1
Journals
Machines
Special Issues
Application of Deep Learning in Fault Diagnosis
share announcement

Application of Deep Learning in Fault Diagnosis

A special issue of Machines (ISSN 2075-1702). This special issue belongs to the section "Machines Testing and Maintenance".

Deadline for manuscript submissions: closed (31 August 2024) | Viewed by 6900

Special Issue Editor

Dr. Junseong Bang

E-Mail
Guest Editor
1. Electronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Korea
2. Defense & Safety ICT Research Department, University of Science & Technology (UST), Daejeon 34113, Korea
Interests: deep learning; contextual computing; AR/VR/MR/XR; computer vision; speech recognition; NLP; artificial intelligence; HCI

Special Issue Information

Dear Colleagues,

Fault diagnosis is one of the main phases for online monitoring and control. This guarantees that systems have high performance and reliability in the presence of faults, where the faults can be caused not only by unexpected natural disasters or equipment aging, but also by malicious attacks. For fault-tolerant control, accurate and real-time fault diagnosis is required. Recent deep learning technology has led to the development of technology related to fault diagnosis as well as fault-tolerant control. This Special Issue focuses on deep learning technology related to fault diagnosis and its applications (including development and implementation for communication/network systems, traffic systems, aircraft/spacecraft control systems, etc.). The main purpose of this Special Issue is to share the latest novel studies on deep learning technology for fault diagnosis.

Topics for this Special Issue include the following, but are not limited to:

  • Deep learning for fault detection/diagnosis (or fault detectability analysis);
  • Fault-tolerant control with deep learning based fault diagnosis (and its performance analysis);
  • Reliable systems with deep learning based fault detection/diagnosis/control;
  • Decision intelligence with fault detection/diagnosis;
  • Deep learning-based implementations/applications for fault diagnosis. 

Dr. Junseong Bang
Guest Editor

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. Machines 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.

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (6 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

22 pages, 3975 KiB  
Article
Efficiency-Centered Fault Diagnosis of In-Service Induction Motors for Digital Twin Applications: A Case Study on Broken Rotor Bars
by Adamou Amadou Adamou and Chakib Alaoui
Machines 2024, 12(9), 604; https://doi.org/10.3390/machines12090604 - 1 Sep 2024
Viewed by 570
Abstract
The uninterrupted operation of induction motors is crucial for industries, ensuring reliability and continuous functionality. To achieve this, we propose an innovative approach that utilizes an efficiency model-based digital shadow system for in situ failure detection and diagnosis (FDD) in induction motors (IMs). [...] Read more.
The uninterrupted operation of induction motors is crucial for industries, ensuring reliability and continuous functionality. To achieve this, we propose an innovative approach that utilizes an efficiency model-based digital shadow system for in situ failure detection and diagnosis (FDD) in induction motors (IMs). The shadow model accurately estimates IM losses and efficiency across various operational conditions. Our proposed method utilizes efficiency as the primary indicator for fault detection, while losses serve as condition indicators for fault diagnosis based on real-time motor parameters and loss sources. We introduce a bond graph as a fault diagnosis network, linking loss sources, motor parameters, and faults. This interconnected approach is the key aspect of our proposed diagnostic method and aims to be used in fault diagnosis as a general method. A case study of a broken rotor bar is used to validate the proposed method using a dataset of five motors. Among these, one motor operates without failure, while the remaining four exhibit broken rotor faults categorized as 1, 2, 3, and 4. The proposed method achieves 99.99% precision in identifying one to four defective rotor bars in IMs. Comparative analysis demonstrates good performance compared to vibration-based FDD approaches. Moreover, our methodology is computationally efficient and aligned with Industry 4.0 requirements. Full article
(This article belongs to the Special Issue Application of Deep Learning in Fault Diagnosis)
►▼ Show Figures

Figure 1

13 pages, 4238 KiB  
Article
Research on Sintering Machine Axle Fault Detection Based on Wheel Swing Characteristics
by Bo Chen, Husheng Yang, Jiarui Mei, Yueming Wang and Hao Zhang
Machines 2024, 12(8), 498; https://doi.org/10.3390/machines12080498 - 23 Jul 2024
Viewed by 647
Abstract
During the sintering process in iron production, wheel swing is a sign of sintering machine trolley axle faults, which may lead to the wheel falling off and affect the production operation of the sintering machine system in serious cases. To solve this problem, [...] Read more.
During the sintering process in iron production, wheel swing is a sign of sintering machine trolley axle faults, which may lead to the wheel falling off and affect the production operation of the sintering machine system in serious cases. To solve this problem, this paper proposes a fault detection and localization method based on the You Only Look Once version 9 (YOLOv9) object detection algorithm and frame difference method for detecting sintering machine trolley wheel swing. The wheel images transmitted from the camera were sent to a trolley wheel and side panel number detection model that was trained on YOLOv9 for recognition. The wheel recognition boxes of the previous and subsequent frames were fused into the wheel region of interest. In the wheel region of interest, the difference operation was carried out. The result of the difference operation was compared with the preset threshold to determine whether the trolley wheel swings. When a wheel swing fault occurs, the image of the side plate at the time of the fault is collected, and the number on the side plate is identified so as to accurately locate the faulty trolley and to assist the field personnel in troubleshooting the fault. The experimental results show that this method can detect wheel swing faults in the industrial field, and the detection accuracy of wheel swing faults was 93.33%. The trolley side plate numbers’ average precision was 99.2% in fault localization. Utilizing the aforementioned method to construct a system for detecting wheel swing can provide technical support for fault detection of the trolley axle on the sintering machine. Full article
(This article belongs to the Special Issue Application of Deep Learning in Fault Diagnosis)
►▼ Show Figures

Figure 1

14 pages, 2194 KiB  
Article
Fault Diagnosis in Induction Motors through Infrared Thermal Images Using Convolutional Neural Network Feature Extraction
by Uriel Calderon-Uribe, Rocio A. Lizarraga-Morales and Igor V. Guryev
Machines 2024, 12(8), 497; https://doi.org/10.3390/machines12080497 - 23 Jul 2024
Cited by 1 | Viewed by 791
Abstract
The development of diagnostic systems for rotating machines such as induction motors (IMs) is a task of utmost importance for the industrial sector. Reliable diagnostic systems allow for the accurate detection of different faults. Different methods based on the acquisition of thermal images [...] Read more.
The development of diagnostic systems for rotating machines such as induction motors (IMs) is a task of utmost importance for the industrial sector. Reliable diagnostic systems allow for the accurate detection of different faults. Different methods based on the acquisition of thermal images (TIs) have emerged as diagnosis systems for the detection of IM faults to prevent the further generation of faults. However, these methods are based on artisanal feature selection, so obtaining high accuracy rates is usually challenging. For this reason, in this work, a new system for fault detection in IMs based on convolutional neural networks (CNNs) and thermal images (TIs) is presented. The system is based on the training of a CNN using TIs to select and extract the most salient features of each fault present in the IM. Subsequently, a classifier based on a decision tree (DT) algorithm is trained using the features learned by the CNN to infer the motor conditions. The results of this methodology show an improvement in the accuracy, precision, recall, and F1-score metrics for 11 different conditions. Full article
(This article belongs to the Special Issue Application of Deep Learning in Fault Diagnosis)
►▼ Show Figures

Figure 1

28 pages, 18980 KiB  
Article
A Real-Time Dual-Task Defect Segmentation Network for Grinding Wheels with Coordinate Attentioned-ASP and Masked Autoencoder
by Yifan Li, Chuanbao Li, Ping Zhang and Han Wang
Machines 2024, 12(4), 276; https://doi.org/10.3390/machines12040276 - 21 Apr 2024
Viewed by 1105
Abstract
The current network for the dual-task grinding wheel defect semantic segmentation lacks high-precision lightweight designs, making it challenging to balance lightweighting and segmentation accuracy, thus severely limiting its practical application in grinding wheel production lines. Additionally, recent approaches for addressing the natural class [...] Read more.
The current network for the dual-task grinding wheel defect semantic segmentation lacks high-precision lightweight designs, making it challenging to balance lightweighting and segmentation accuracy, thus severely limiting its practical application in grinding wheel production lines. Additionally, recent approaches for addressing the natural class imbalance in defect segmentation fail to leverage the inexhaustible unannotated raw data on the production line, posing huge data wastage. Targeting these two issues, firstly, by discovering the similarity between Coordinate Attention (CA) and ASPP, this study has introduced a novel lightweight CA-ASP module to the DeeplabV3+, which is 45.3% smaller in parameter size and 53.2% lower in FLOPs compared to the ASPP, while achieving better segmentation precision. Secondly, we have innovatively leveraged the Masked Autoencoder (MAE) to address imbalance. By developing a new Hybrid MAE and applying it to self-supervised pretraining on tremendous unannotated data, we have significantly uplifted the network’s semantic understanding on the minority classes, which leads to further rises in both the overall accuracy and accuracy of the minorities without additional computational growth. Lastly, transfer learning has been deployed to fully utilize the highly related dual tasks. Experimental results demonstrate that the proposed methods with a real-time latency of 9.512 ms obtain a superior segmentation accuracy on the mIoU score over the compared real-time state-of-the-art methods, excelling in managing the imbalance and ensuring stability on the complicated scenes across the dual tasks. Full article
(This article belongs to the Special Issue Application of Deep Learning in Fault Diagnosis)
►▼ Show Figures

Figure 1

15 pages, 3934 KiB  
Article
Improved Support Vector Machine for Voiceprint Diagnosis of Typical Faults in Power Transformers
by Jianxin Wang, Zhishan Zhao, Jun Zhu, Xin Li, Fan Dong and Shuting Wan
Machines 2023, 11(5), 539; https://doi.org/10.3390/machines11050539 - 10 May 2023
Cited by 7 | Viewed by 1514
Abstract
The traditional power transformer diagnosis method relies on a lot of experience knowledge and a complex sampling process, which brings great difficulties to the fault diagnosis work. To solve this problem, a fault feature extraction method based on fully adaptive noise set empirical [...] Read more.
The traditional power transformer diagnosis method relies on a lot of experience knowledge and a complex sampling process, which brings great difficulties to the fault diagnosis work. To solve this problem, a fault feature extraction method based on fully adaptive noise set empirical mode decomposition (CEEMDAN) is proposed, and the hunter–prey optimization (HPO) algorithm is used to optimize the support vector machine (SVM) to identify and classify the voice print faults of power transformers. Firstly, the CEEMDAN algorithm is used to decompose the voicemarks into several IMF components. IMF components containing fault information are selected according to the envelope kurtosis index and reconstructed to generate new signal sequences. PCA dimensionality reduction is performed on the reconstructed signal, and the principal components are extracted with a high cumulative contribution rate as input to SVM. Then, the HPO-SVM algorithm is used to classify and identify transformer faults. Apply the proposed method to the diagnosis of typical faults in power transformers. The results show that the accuracy of this method in identifying various fault states of power transformers can reach 98.5%, and it has better classification performance than other similar methods. Full article
(This article belongs to the Special Issue Application of Deep Learning in Fault Diagnosis)
►▼ Show Figures

Figure 1

20 pages, 4120 KiB  
Article
An Indirect Procedure for Real-Time Monitoring the Neutral Conductor Deterioration in Three-Phase Distribution Networks
by Vicente León-Martínez, Joaquín Montañana-Romeu, Elisa Peñalvo-López, Amparo León-Vinet and Jorge Cano-Martínez
Machines 2023, 11(4), 444; https://doi.org/10.3390/machines11040444 - 1 Apr 2023
Viewed by 1329
Abstract
An indirect procedure for real-time monitoring the neutral conductor condition in three-phase distribution networks, based on watching over the growth of a novel parameter (∆τ), has been described in this paper. The parameter ∆τ has been defined as the relationship [...] Read more.
An indirect procedure for real-time monitoring the neutral conductor condition in three-phase distribution networks, based on watching over the growth of a novel parameter (∆τ), has been described in this paper. The parameter ∆τ has been defined as the relationship between the neutral-displacement power and Buchholz’s apparent power measured at the fundamental frequency in the loads of the distribution networks for any condition of the neutral conductor and in its nominal conditions. The effectiveness of this procedure has been compared with other traditional indirect procedures, such as the surveillance of the RMS values of the line-to-neutral load voltages or their zero-sequence component. The practical application on a real distribution network reveals that the growth of the parameter ∆τ in the early stages of the breaking process of the neutral conductor follows a straight line whose equation is known for each length and section of that conductor, regardless of the loads and the voltage regulation of the transformer of the distribution network. This characteristic of the ∆τ parameter shows that the proposed procedure is suitable for monitoring neutral conductor deterioration and can be used for preventive maintenance of distribution networks. Full article
(This article belongs to the Special Issue Application of Deep Learning in Fault Diagnosis)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop