Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929681598513152 |
|---|---|
| author | Zhang, Hanrong Yao, Yifei Wang, Zixuan Su, Jiayuan Li, Mengxuan Peng, Peng Wang, Hongwei |
| author_facet | Zhang, Hanrong Yao, Yifei Wang, Zixuan Su, Jiayuan Li, Mengxuan Peng, Peng Wang, Hongwei |
| contents | Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot fault data is challenging, and adding new fault classes often demands costly model retraining. Moreover, incremental training of existing methods risks catastrophic forgetting, and severe class imbalance can bias the model's decisions toward normal classes. To tackle these issues, we introduce a Supervised Contrastive knowledge distiLlation for class Incremental Fault Diagnosis (SCLIFD) framework proposing supervised contrastive knowledge distillation for improved representation learning capability and less forgetting, a novel prioritized exemplar selection method for sample replay to alleviate catastrophic forgetting, and the Random Forest Classifier to address the class imbalance. Extensive experimentation on simulated and real-world industrial datasets across various imbalance ratios demonstrates the superiority of SCLIFD over existing approaches. Our code can be found at https://github.com/Zhang-Henry/SCLIFD_TII. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_09525 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation Zhang, Hanrong Yao, Yifei Wang, Zixuan Su, Jiayuan Li, Mengxuan Peng, Peng Wang, Hongwei Machine Learning Artificial Intelligence Class-incremental fault diagnosis requires a model to adapt to new fault classes while retaining previous knowledge. However, limited research exists for imbalanced and long-tailed data. Extracting discriminative features from few-shot fault data is challenging, and adding new fault classes often demands costly model retraining. Moreover, incremental training of existing methods risks catastrophic forgetting, and severe class imbalance can bias the model's decisions toward normal classes. To tackle these issues, we introduce a Supervised Contrastive knowledge distiLlation for class Incremental Fault Diagnosis (SCLIFD) framework proposing supervised contrastive knowledge distillation for improved representation learning capability and less forgetting, a novel prioritized exemplar selection method for sample replay to alleviate catastrophic forgetting, and the Random Forest Classifier to address the class imbalance. Extensive experimentation on simulated and real-world industrial datasets across various imbalance ratios demonstrates the superiority of SCLIFD over existing approaches. Our code can be found at https://github.com/Zhang-Henry/SCLIFD_TII. |
| title | Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2501.09525 |