解决小样本故障诊断中模型遗忘与类别不平衡问题
Class Incremental Fault Diagnosis under Limited Fault Data via Supervised Contrastive Knowledge Distillation
- 采用监督对比知识蒸馏提升特征学习能力
- 新故障类加入后准确率仍保持90%以上
- 适合工业设备故障诊断场景，尤其小样本数据
类增量故障诊断要求模型在新增故障类别时保留已有知识，但现有研究在数据不均衡和长尾分布下仍不足。从少量故障样本中提取判别性特征困难，新增类别常需昂贵的重新训练。现有方法增量训练易引发灾难性遗忘，严重类别不平衡会使模型偏向正常类。为此，本文提出SCLIFD框架：通过监督对比知识蒸馏增强表征学习并减少遗忘；设计优先级原型选择方法实现样本回放以缓解遗忘；引入随机森林分类器应对类别不平衡。在模拟与真实工业数据集上，不同不平衡比条件下均优于现有方法。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。