Conditional contrastive domain generalization for fault diagnosis
Data-driven fault diagnosis plays a key role in stability and reliability of operations in modern industries. Recently, deep learning has achieved remarkable performance in fault classification tasks. However, in reality, the model can be deployed under highly varying working environments. As a resu...
Saved in:
Main Authors: | , , , , , , |
---|---|
Other Authors: | |
Format: | Article |
Language: | English |
Published: |
2022
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/163780 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-163780 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1637802023-04-03T02:10:44Z Conditional contrastive domain generalization for fault diagnosis Ragab, Mohamed Chen, Zhenghua Zhang, Wenyu Eldele, Emadeldeen Wu, Min Kwoh, Chee Keong Li, Xiaoli School of Computer Science and Engineering Institute for Infocomm Research, A*STAR Engineering::Computer science and engineering Contrasting Learning Domain Generalization Data-driven fault diagnosis plays a key role in stability and reliability of operations in modern industries. Recently, deep learning has achieved remarkable performance in fault classification tasks. However, in reality, the model can be deployed under highly varying working environments. As a result, the model trained under a certain working environment (i.e., certain distribution) can fail to generalize well on data from different working environments (i.e., different distributions). The naive approach of training a new model for each new working environment would be infeasible in practice. To address this issue, we propose a novel conditional contrastive domain generalization (CCDG) approach for fault diagnosis of rolling machinery, which is able to capture shareable class information and learn environment-independent representation among data collected from different environments (also known as domains). Specifically, our CCDG attempts to maximize the mutual information of similar classes across different domains while minimizing mutual information among different classes, such that it can learn domain-independent class representation that can be transferable to new unseen domains. Our proposed approach significantly outperforms state-of-the-art methods on two real-world fault diagnosis datasets with an average improvement of 7.75% and 2.60%, respectively. The promising performance of our proposed CCDG on new unseen target domain contributes toward more practical data-driven approaches that can work under challenging real-world environments. Agency for Science, Technology and Research (A*STAR) This work was supported in part by the Agency for Science, Technology and Research (A*STAR) through its AME Programmatic Funds under Grant A20H6b0151 and in part by the Career Development Award under Grant C210112046. 2022-12-16T06:41:50Z 2022-12-16T06:41:50Z 2022 Journal Article Ragab, M., Chen, Z., Zhang, W., Eldele, E., Wu, M., Kwoh, C. K. & Li, X. (2022). Conditional contrastive domain generalization for fault diagnosis. IEEE Transactions On Instrumentation and Measurement, 71, 3506912-. https://dx.doi.org/10.1109/TIM.2022.3154000 0018-9456 https://hdl.handle.net/10356/163780 10.1109/TIM.2022.3154000 2-s2.0-85125355675 71 3506912 en A20H6b0151 C210112046 IEEE Transactions on Instrumentation and Measurement 10.21979/N9/8QPQHL © 2022 IEEE. All rights reserved. |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Computer science and engineering Contrasting Learning Domain Generalization |
spellingShingle |
Engineering::Computer science and engineering Contrasting Learning Domain Generalization Ragab, Mohamed Chen, Zhenghua Zhang, Wenyu Eldele, Emadeldeen Wu, Min Kwoh, Chee Keong Li, Xiaoli Conditional contrastive domain generalization for fault diagnosis |
description |
Data-driven fault diagnosis plays a key role in stability and reliability of operations in modern industries. Recently, deep learning has achieved remarkable performance in fault classification tasks. However, in reality, the model can be deployed under highly varying working environments. As a result, the model trained under a certain working environment (i.e., certain distribution) can fail to generalize well on data from different working environments (i.e., different distributions). The naive approach of training a new model for each new working environment would be infeasible in practice. To address this issue, we propose a novel conditional contrastive domain generalization (CCDG) approach for fault diagnosis of rolling machinery, which is able to capture shareable class information and learn environment-independent representation among data collected from different environments (also known as domains). Specifically, our CCDG attempts to maximize the mutual information of similar classes across different domains while minimizing mutual information among different classes, such that it can learn domain-independent class representation that can be transferable to new unseen domains. Our proposed approach significantly outperforms state-of-the-art methods on two real-world fault diagnosis datasets with an average improvement of 7.75% and 2.60%, respectively. The promising performance of our proposed CCDG on new unseen target domain contributes toward more practical data-driven approaches that can work under challenging real-world environments. |
author2 |
School of Computer Science and Engineering |
author_facet |
School of Computer Science and Engineering Ragab, Mohamed Chen, Zhenghua Zhang, Wenyu Eldele, Emadeldeen Wu, Min Kwoh, Chee Keong Li, Xiaoli |
format |
Article |
author |
Ragab, Mohamed Chen, Zhenghua Zhang, Wenyu Eldele, Emadeldeen Wu, Min Kwoh, Chee Keong Li, Xiaoli |
author_sort |
Ragab, Mohamed |
title |
Conditional contrastive domain generalization for fault diagnosis |
title_short |
Conditional contrastive domain generalization for fault diagnosis |
title_full |
Conditional contrastive domain generalization for fault diagnosis |
title_fullStr |
Conditional contrastive domain generalization for fault diagnosis |
title_full_unstemmed |
Conditional contrastive domain generalization for fault diagnosis |
title_sort |
conditional contrastive domain generalization for fault diagnosis |
publishDate |
2022 |
url |
https://hdl.handle.net/10356/163780 |
_version_ |
1764208025868959744 |