Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention Mechanism
Applying deep learning to unsupervised bearing fault diagnosis in complex industrial environments is challenging. Traditional fault detection methods rely on labeled data, which is costly and labor-intensive to obtain. This paper proposes a novel unsupervised approach, WDCAE-LKA, combining a wide ke...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/24/8053 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846102778991083520 |
|---|---|
| author | Hao Yan Xiangfeng Si Jianqiang Liang Jian Duan Tielin Shi |
| author_facet | Hao Yan Xiangfeng Si Jianqiang Liang Jian Duan Tielin Shi |
| author_sort | Hao Yan |
| collection | DOAJ |
| description | Applying deep learning to unsupervised bearing fault diagnosis in complex industrial environments is challenging. Traditional fault detection methods rely on labeled data, which is costly and labor-intensive to obtain. This paper proposes a novel unsupervised approach, WDCAE-LKA, combining a wide kernel convolutional autoencoder (WDCAE) with a large kernel attention (LKA) mechanism to improve fault detection under unlabeled conditions, and the adaptive threshold module based on a multi-layer perceptron (MLP) dynamically adjusts thresholds, boosting model robustness in imbalanced scenarios. Experimental validation on two datasets (CWRU and a customized ball screw dataset) demonstrates that the proposed model outperforms both traditional and state-of-the-art methods. Notably, WDCAE-LKA achieved an average diagnostic accuracy of 90.29% in varying fault scenarios on the CWRU dataset and 72.89% in the customized ball screw dataset and showed remarkable robustness under imbalanced conditions; compared with advanced models, it shortens training time by 10–26% and improves average fault diagnosis accuracy by 5–10%. The results underscore the potential of the WDCAE-LKA model as a robust and effective solution for intelligent fault diagnosis in industrial applications. |
| format | Article |
| id | doaj-art-47c009dfb2ce42d3acd188e02e9fd097 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-47c009dfb2ce42d3acd188e02e9fd0972024-12-27T14:52:50ZengMDPI AGSensors1424-82202024-12-012424805310.3390/s24248053Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention MechanismHao Yan0Xiangfeng Si1Jianqiang Liang2Jian Duan3Tielin Shi4State Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaState Key Laboratory of Digital Manufacturing Equipment and Technology, Huazhong University of Science and Technology, Wuhan 430074, ChinaApplying deep learning to unsupervised bearing fault diagnosis in complex industrial environments is challenging. Traditional fault detection methods rely on labeled data, which is costly and labor-intensive to obtain. This paper proposes a novel unsupervised approach, WDCAE-LKA, combining a wide kernel convolutional autoencoder (WDCAE) with a large kernel attention (LKA) mechanism to improve fault detection under unlabeled conditions, and the adaptive threshold module based on a multi-layer perceptron (MLP) dynamically adjusts thresholds, boosting model robustness in imbalanced scenarios. Experimental validation on two datasets (CWRU and a customized ball screw dataset) demonstrates that the proposed model outperforms both traditional and state-of-the-art methods. Notably, WDCAE-LKA achieved an average diagnostic accuracy of 90.29% in varying fault scenarios on the CWRU dataset and 72.89% in the customized ball screw dataset and showed remarkable robustness under imbalanced conditions; compared with advanced models, it shortens training time by 10–26% and improves average fault diagnosis accuracy by 5–10%. The results underscore the potential of the WDCAE-LKA model as a robust and effective solution for intelligent fault diagnosis in industrial applications.https://www.mdpi.com/1424-8220/24/24/8053unsupervised feature learningmachinery fault detectionauto-encoderkernelized attentionadaptive thresholding |
| spellingShingle | Hao Yan Xiangfeng Si Jianqiang Liang Jian Duan Tielin Shi Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention Mechanism Sensors unsupervised feature learning machinery fault detection auto-encoder kernelized attention adaptive thresholding |
| title | Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention Mechanism |
| title_full | Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention Mechanism |
| title_fullStr | Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention Mechanism |
| title_full_unstemmed | Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention Mechanism |
| title_short | Unsupervised Learning for Machinery Adaptive Fault Detection Using Wide-Deep Convolutional Autoencoder with Kernelized Attention Mechanism |
| title_sort | unsupervised learning for machinery adaptive fault detection using wide deep convolutional autoencoder with kernelized attention mechanism |
| topic | unsupervised feature learning machinery fault detection auto-encoder kernelized attention adaptive thresholding |
| url | https://www.mdpi.com/1424-8220/24/24/8053 |
| work_keys_str_mv | AT haoyan unsupervisedlearningformachineryadaptivefaultdetectionusingwidedeepconvolutionalautoencoderwithkernelizedattentionmechanism AT xiangfengsi unsupervisedlearningformachineryadaptivefaultdetectionusingwidedeepconvolutionalautoencoderwithkernelizedattentionmechanism AT jianqiangliang unsupervisedlearningformachineryadaptivefaultdetectionusingwidedeepconvolutionalautoencoderwithkernelizedattentionmechanism AT jianduan unsupervisedlearningformachineryadaptivefaultdetectionusingwidedeepconvolutionalautoencoderwithkernelizedattentionmechanism AT tielinshi unsupervisedlearningformachineryadaptivefaultdetectionusingwidedeepconvolutionalautoencoderwithkernelizedattentionmechanism |