EUVIMEDEUVIMED entdecken
Crossref

Multiscale Conditional Adversarial Networks based domain-adaptive method for rotating machinery fault diagnosis under variable working conditions

Zhendong Hei, Haiyang Yang, Weifang Sun, Meipeng Zhong, Gonghai Wang, Anil Kumar, Jiawei Xiang, Yuqing Zhou

ISA Transactions · 2024-11 · 154 · 352-370

DOI: 10.1016/j.isatra.2024.08.027 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ISA Transactions, 2024-11. Verfasst von Zhendong Hei und 7 weiteren Autor:innen. Beteiligte Einrichtung: College of Mechanical and Electrical Engineering, Jiaxing Nanhu University, Jiaxing, China; College of Mechanical and Electrical Engineering, Wenzhou…. Die Arbeit wurde bisher 36-mal zitiert (Crossref) und nennt 43 Literaturangaben. Gefördert von: Natural Science Foundation of Zhejiang Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning has been increasingly used in health management and maintenance decision-making for rotating machinery. However, some challenges must be addressed to make this technology more effective. For example, the collected data is assumed to follow the same feature distribution, and sufficient labeled training data are available. Unfortunately, domain shifts occur inevitably in real-world scenarios due to different working conditions, and acquiring sufficient labeled samples is time-consuming and expensive in complex environments. This study proposes a novel domain adaptive framework called deep Multiscale Conditional Adversarial Networks (MCAN) for machinery fault diagnosis to address these shortcomings. The MCAN model comprises two key components. Constructed by a novel multiscale module with an attention mechanism, the first component is a shared feature generator that captures rich features at different internal perceptual scales, and the attention mechanism determines the weights assigned to each scale, enhancing the model's dynamic adjustment and self-adaptation capabilities. The second component consists of two domain classifiers based on Bidirectional Long Short-Term Memory (BiLSTM) leveraging spatiotemporal features at various levels to achieve domain adaptation in the output space. The deep domain classifier also captures the cross-covariance dependencies between feature representations and classifier predictions, thereby improving the predictions' discriminability. The proposed method has been evaluated using two publicly available fault diagnosis datasets and one condition monitoring experiment. The results of cross-domain transfer tasks demonstrated that the proposed method outperformed several state-of-the-art methods in terms of transferability and stability. This result is a significant step forward in deep learning for health management and maintenance decision-making for rotating machinery, and it has the potential to revolutionize its future application.

Schlagwörter

Stichwörter der Autor:innen

Attention mechanismCross-covarianceFault diagnosisFeature distributionMultiscale domain adaptive

Autor:innen und Institutionen

  • College of Mechanical and Electrical Engineering, Jiaxing Nanhu University, Jiaxing, China; College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou, China. Electronic address: 21461440022@stu.wzu.e…
  • College of Mechanical and Electrical Engineering, Jiaxing Nanhu University, Jiaxing, China; Jiaxing Key Laboratory of Intelligent Manufacturing and Operation & Maintenance of Automotive Parts, Jiaxing, China. Electronic…
  • College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou, China. Electronic address: vincent_suen@126.com.
  • College of Mechanical and Electrical Engineering, Jiaxing Nanhu University, Jiaxing, China. Electronic address: wgh_0621@163.com.
  • College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou, China. Electronic address: 20210129@wzu.edu.cn.
  • College of Mechanical and Electrical Engineering, Wenzhou University, Wenzhou, China. Electronic address: jwxiang@wzu.edu.cn.

Förderung

  • Natural Science Foundation of Zhejiang Province
  • National Natural Science Foundation of China

Zitieren

APA

Hei, Z., Yang, H., Sun, W., Zhong, M., Wang, G., Kumar, A., Xiang, J., & Zhou, Y. (2024). Multiscale Conditional Adversarial Networks based domain-adaptive method for rotating machinery fault diagnosis under variable working conditions. ISA Transactions, 154, 352-370. https://doi.org/10.1016/j.isatra.2024.08.027

Vancouver

Hei Z, Yang H, Sun W, Zhong M, Wang G, Kumar A, et al. Multiscale Conditional Adversarial Networks based domain-adaptive method for rotating machinery fault diagnosis under variable working conditions. ISA Transactions. 2024;154:352-370. doi:10.1016/j.isatra.2024.08.027

BibTeX
@article{Hei2024,
  author = {Hei, Zhendong and Yang, Haiyang and Sun, Weifang and Zhong, Meipeng and Wang, Gonghai and Kumar, Anil and Xiang, Jiawei and Zhou, Yuqing},
  title = {Multiscale Conditional Adversarial Networks based domain-adaptive method for rotating machinery fault diagnosis under variable working conditions},
  journal = {ISA Transactions},
  year = {2024},
  volume = {154},
  pages = {352--370},
  doi = {10.1016/j.isatra.2024.08.027}
}
Kostenlos starten →