Self-degraded contrastive domain adaptation for industrial fault diagnosis with bi-imbalanced data
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914817732771840 |
|---|---|
| author | Chen, Gecheng Yang, Zeyu Luo, Chengwen Li, Jianqiang |
| author_facet | Chen, Gecheng Yang, Zeyu Luo, Chengwen Li, Jianqiang |
| contents | Modern industrial fault diagnosis tasks often face the combined challenge of distribution discrepancy and bi-imbalance. Existing domain adaptation approaches pay little attention to the prevailing bi-imbalance, leading to poor domain adaptation performance or even negative transfer. In this work, we propose a self-degraded contrastive domain adaptation (Sd-CDA) diagnosis framework to handle the domain discrepancy under the bi-imbalanced data. It first pre-trains the feature extractor via imbalance-aware contrastive learning based on model pruning to learn the feature representation efficiently in a self-supervised manner. Then it forces the samples away from the domain boundary based on supervised contrastive domain adversarial learning (SupCon-DA) and ensures the features generated by the feature extractor are discriminative enough. Furthermore, we propose the pruned contrastive domain adversarial learning (PSupCon-DA) to pay automatically re-weighted attention to the minorities to enhance the performance towards bi-imbalanced data. We show the superiority of the proposed method via two experiments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_20700 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Self-degraded contrastive domain adaptation for industrial fault diagnosis with bi-imbalanced data Chen, Gecheng Yang, Zeyu Luo, Chengwen Li, Jianqiang Artificial Intelligence Modern industrial fault diagnosis tasks often face the combined challenge of distribution discrepancy and bi-imbalance. Existing domain adaptation approaches pay little attention to the prevailing bi-imbalance, leading to poor domain adaptation performance or even negative transfer. In this work, we propose a self-degraded contrastive domain adaptation (Sd-CDA) diagnosis framework to handle the domain discrepancy under the bi-imbalanced data. It first pre-trains the feature extractor via imbalance-aware contrastive learning based on model pruning to learn the feature representation efficiently in a self-supervised manner. Then it forces the samples away from the domain boundary based on supervised contrastive domain adversarial learning (SupCon-DA) and ensures the features generated by the feature extractor are discriminative enough. Furthermore, we propose the pruned contrastive domain adversarial learning (PSupCon-DA) to pay automatically re-weighted attention to the minorities to enhance the performance towards bi-imbalanced data. We show the superiority of the proposed method via two experiments. |
| title | Self-degraded contrastive domain adaptation for industrial fault diagnosis with bi-imbalanced data |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2405.20700 |