用大模型框架解决小数据下的跨域轴承故障诊断难题
An LLM-based Two-Stage Transformer Framework for Cross-Domain Bearing Fault Diagnosis with Limited Data
- 分两阶段的轻量Transformer，用预训练权重和故障原型传递知识
- 仅用10%标注数据就达92.61%准确率，比顶尖方法高17.24个百分点
- 适合工业界在数据少、场景杂时做低成本预测性维护
轴承故障诊断在工业环境中常面临数据异构、工况变化和标注数据有限的多重挑战。现有方法多孤立处理问题，依赖隐式特征对齐，难以应对并发难题。本文提出一种基于大模型的两阶段迁移学习框架，采用轻量级GPT-2风格Transformer与因果自注意力机制，从振动信号中提取分层特征；通过预训练编码器权重与故障原型嵌入作为知识载体，实现从多源预训练到目标域适配的显式知识传递。框架通过多源学习获得泛化表征，基于原型的知识调制实现目标域适应，结合分类体系自适应完成异构故障类别的无缝迁移。在四个真实数据集上的实验表明，仅需10%标注目标数据即达到92.61%平均准确率，相比最先进方法提升17.24个百分点，为工业4.0环境下的低成本预测性维护提供了实用路径。
原文摘要 · Abstract (English)
Bearing fault diagnosis faces critical challenges when dataset heterogeneity, operating condition variations, and limited labeled data occur simultaneously in industrial environments. Existing approaches address these issues in isolation and rely on implicit feature alignment, limiting effectiveness under concurrent challenges. This paper proposes a knowledge-guided two-stage transfer learning framework that employs a lightweight GPT-2-style Transformer with causal self-attention for hierarchical feature extraction from vibration signals, establishing explicit pathways where pre-trained encoder weights and fault prototype embeddings serve as knowledge carriers from multi-source pre-training to target adaptation. The framework addresses the dual-shift challenge through multi-source learning for generalizable representations, prototype-based knowledge modulation for target adaptation, and taxonomy-adaptive classification for seamless transfer across heterogeneous fault categories. Experimental validation on four real-world datasets demonstrates 92.61% average accuracy with only 10% labeled target data, outperforming state-of-the-art methods by 17.24 percentage points, establishing a practical pathway toward cost-effective predictive maintenance in Industry 4.0 applications.
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。