Multi-Target Adversarial Learning for Partial Fault Detection Applied to Electric Motor-Driven Systems
Source abstract
Abstract
Deep neural network-based fault diagnosis is gaining significant attention within the Industry 4.0 framework, yet practical deployment is still hindered by domain shift, partial label mismatch, and class imbalance. In this regard, this paper proposes a Multi-Target Adversarial Learning for Partial Fault Diagnosis (MTAL-PFD), an extension of adversarial and discrepancy-based domain adaptation tailored to single-source, multi-target (1SmT) partial fault diagnosis in electric motor-driven systems. The framework transfers knowledge from a labeled source to multiple unlabeled target domains by combining dual 1D-CNN feature extractors with adversarial domain discriminators, an inconsistency-based regularizer to stabilize learning, and class-aware weighting to mitigate partial label shift by down-weighting outlier source classes. Thus, the proposed scheme combines a multi-objective approach with partial domain adaptation applied to the diagnosis of electric motor-driven systems. The proposed model is evaluated across 24 cross-domain tasks and varying operating conditions on two motor test benches, showing consistent improvements over representative baselines.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Fault Detection and Control Systems · Anomaly Detection Techniques and Applications
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
MCIA Research Center, Department of Electronic Engineering, Universitat Politècnica de Catalunya, Rambla Sant Nebridi 22, 08222 Terrassa, Barcelona, Spain
Energy Systems Analytics, Catalonia Institute for Energy Research, 08930 Sant Adrià de Besòs, Barcelona, Spain
MCIA Research Center, Department of Automatic Control, Universitat Politècnica de Catalunya, Rambla Sant Nebridi 22, 08222 Terrassa, Barcelona, Spain
Engineering Faculty, Autonomous University of Queretaro, Av. Rio Moctezuma 249, San Juan del Rio 76807, Mexico
Funding
Catalan Agency for Management of University
References (38)
Show source-provided references
1. Data Analytics in Industry 4.0: A Survey10.1007/s10796-021-10190-0 ↗
2. A New Multisensor Partial Domain Adaptation Method for Machinery Fault Diagnosis Under Different Working Conditions10.1109/TIM.2023.3318679 ↗
3. Jeong, H., Kim, S., Seo, D., and Kwon, J. (2025). Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis. Sensors, 25.10.3390/s25144383 ↗
4. A federated transfer learning method with low-quality knowledge filtering and dynamic model aggregation for rolling bearing fault diagnosis10.1016/j.ymssp.2023.110413 ↗
5. Li, H., Wang, G., Shi, N., Li, Y., Hao, W., and Pang, C. (2025). A Lightweight Multi-Angle Feature Fusion CNN for Bearing Fault Diagnosis. Electronics, 14.10.3390/electronics14142774 ↗
6. Adversarial Multiple-Target Domain Adaptation for Fault Classification10.1109/TIM.2020.3009341 ↗
7. Siddika, A., Begum, M., Al Farid, F., Uddin, J., and Karim, H.A. (2025). Enhancing Software Defect Prediction Using Ensemble Techniques and Diverse Machine Learning Paradigms. Eng, 6.10.3390/eng6070161 ↗
8. Domain Adversarial Graph Convolutional Network for Fault Diagnosis Under Variable Working Conditions
9. A fault diagnosis method for wind turbines with limited labeled data based on balanced joint adaptive network10.1016/j.neucom.2022.01.067 ↗
10. Deep-Learning-Based Open Set Fault Diagnosis by Extreme Value Theory10.1109/TII.2021.3070324 ↗
11. Unsupervised Cross-Domain Fault Diagnosis Using Feature Representation Alignment Networks for Rotating Machinery10.1109/TMECH.2020.3046277 ↗
12. Pikramenos, G., Spyrou, E., and Perantonis, S.J. (2022). Extending Partial Domain Adaptation Algorithms to the Open-Set Setting. Appl. Sci., 12.10.3390/app121910052 ↗
13. Unsupervised Machine Anomaly Detection Using Autoencoder and Temporal Convolutional Network10.1109/TIM.2022.3218574 ↗
14. An improved fault diagnosis method for rolling bearings based on wavelet packet decomposition and network parameter optimization10.1088/1361-6501/ad0691 ↗
15. Effective Fault Diagnosis Based on Wavelet and Convolutional Attention Neural Network for Induction Motors10.1109/TIM.2021.3139706 ↗
16. A novel deep autoencoder feature learning method for rotating machinery fault diagnosis10.1016/j.ymssp.2017.03.034 ↗
17. A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method10.1109/TIE.2017.2774777 ↗
18. Electric Locomotive Bearing Fault Diagnosis Using a Novel Convolutional Deep Belief Network10.1109/TIE.2017.2745473 ↗
19. A novel bearing fault diagnosis method based joint attention adversarial domain adaptation10.1016/j.ress.2023.109345 ↗
20. Cross-Domain Fault Diagnosis of Rolling Element Bearings Using Deep Generative Neural Networks10.1109/TIE.2018.2868023 ↗
21. A Hierarchical Deep Domain Adaptation Approach for Fault Diagnosis of Power Plant Thermal System10.1109/TII.2019.2899118 ↗
22. Reconstruction Domain Adaptation Transfer Network for Partial Transfer Learning of Machinery Fault Diagnostics
23. Transferable common feature space mining for fault diagnosis with imbalanced data10.1016/j.ymssp.2021.107645 ↗
24. A Deep Transfer Learning Fault Diagnosis Method Based on WGAN and Minimum Singular Value for Non-Homologous Bearing10.1109/TIM.2022.3160533 ↗
25. An adversarial denoising convolutional neural network for fault diagnosis of rotating machinery under noisy environment and limited sample size case10.1016/j.neucom.2020.04.074 ↗
26. Domain Adversarial Transfer Network for Cross-Domain Fault Diagnosis of Rotary Machinery10.1109/TIM.2020.2995441 ↗
27. Intelligent fault diagnosis method based on full 1-D convolutional generative adversarial network10.1109/TII.2019.2934901 ↗
28. A novel adversarial learning framework in deep convolutional neural network for intelligent diagnosis of mechanical faults10.1016/j.knosys.2018.12.019 ↗
29. Zhang, J., Ding, Z., Li, W., and Ogunbona, P. (2018, January 18–23). Importance weighted adversarial nets for partial domain adaptation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00851 ↗
30. Partial transfer learning in machinery cross-domain fault diagnostics using class-weighted adversarial networks10.1016/j.neunet.2020.06.014 ↗
31. Classifier Inconsistency-Based Domain Adaptation Network for Partial Transfer Intelligent Diagnosis10.1109/TII.2019.2956294 ↗
32. Optimal Active Disturbance Rejection Control for Second Order Systems10.1109/ACCESS.2024.3401079 ↗
33. Deep Model Based Domain Adaptation for Fault Diagnosis10.1109/TIE.2016.2627020 ↗
34. Fault characteristic frequency analysis of elliptically shaped bearing10.1016/j.measurement.2020.107544 ↗
35. Ishikawa, T., and Igarashi, N. (2019). Failure Diagnosis of Demagnetization in Interior Permanent Magnet Synchronous Motors Using Vibration Characteristics. Appl. Sci., 9.10.3390/app9153111 ↗
36. Gearbox localized fault detection based on meshing frequency modulation analysis10.1016/j.apacoust.2024.109943 ↗
37. Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals10.1016/j.measurement.2022.110759 ↗
38. Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study10.1016/j.ymssp.2015.04.021 ↗