提出工业信号多模态表征基础模型FISHER，解决采样率异构难题。
FISHER: A Foundation Model for Multi-Modal Industrial Signal Comprehensive Representation
- 用子带建模处理不同采样率，无需重采样即可融合全带宽信号
- 在19个数据集上超越24个大模型，参数量小16倍仍保持高精度
- 适合工业故障诊断、多源信号融合场景的科研与工程人员
工业信号分析受严重数据异构性制约，我们将其归纳为M5问题。现有方法依赖专用模型，泛化性与可扩展性差，大规模预训练在此领域几乎未被探索。本文提出FISHER——面向多模态工业信号综合表征的基础模型，并构建包含19个数据集、覆盖四种模态的RMIS基准。针对核心的多采样率问题，FISHER采用新型子带建模方法，将采样率增量视为串联的子带信息，实现无需重采样的全带宽自适应利用。模型通过外部音频与音乐数据进行教师-学生自蒸馏预训练。实验表明，FISHER在性能上超越24个状态领先序列编码器（最大达20亿参数），且自身参数规模最小仅16倍，展现出突破性诊断准确率与卓越泛化能力。进一步验证：1）无缝适配变采样率是泛化关键；2）音频与音乐数据具备更优的时间变异性，对预训练至关重要。FISHER与RMIS均已开源。
原文摘要 · Abstract (English)
Industrial signal analysis is hindered by severe data heterogeneity, which we characterize as the M5 problem. Existing solutions rely on specialized models that lack robustness and scalability, while large-scale pre-training has rarely been investigated in this area. In this work, we derive a prioritized roadmap for the M5 problem and propose FISHER, a Foundation model for multi-modal Industrial Signal compreHEnsive Representation. To address the foremost multi-sampling-rate problem, FISHER utilizes a novel sub-band modeling approach that treats sampling rate increments as concatenated sub-band information, enabling the adaptive usage of full signal bandwidth without resampling. FISHER is pre-trained by teacher-student self-distillation over external audio and music data. We also establish the RMIS benchmark, comprising 19 datasets across four modalities. In the experiment, FISHER outperforms 24 state-of-the-art series encoders (up to 2B) with much smaller sizes (up to 16x), showcasing groundbreaking diagnostic accuracy and remarkable versatility. We further demonstrate that 1) seamless adaptation to variable sampling rates is the key to generalization 2) audio and music data provide better temporal variability, which is essential for pre-training. Both FISHER and RMIS are open-sourced.
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。