发表机构
Laboratoire Génie Industriel, CentraleSupélec, Université Paris-Saclay（巴黎萨克雷大学中央理工高等电力学院工业工程实验室）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出FreqCondNorm，一种频率条件化Transformer基础模型，通过FiLM式归一化统一异构时间序列，在故障诊断上跨采样频率迁移显著，但未改善剩余寿命预测。
AI 中文摘要
深度学习预测性维护模型在不同机器和运行条件下的可迁移性较差，尤其是在标记数据稀缺且信号采样频率跨越五个数量级（1 Hz至约100 kHz）的情况下。我们提出了FreqCondNorm，一种基于Transformer的架构，引入FiLM风格的频率条件化归一化层，以在单一模型中统一异构时间序列。该架构在五个公开的预测性维护数据集（CWRU、MFPT、UOC18、PRONOSTIA、CMAPSS）上使用掩码自编码和对比学习以及平衡域采样进行预训练。在故障诊断方面，该模型在CWRU上达到99.2%的准确率（较CNN提升6.4个百分点），在MFPT上达到82.1%的零样本准确率，展示了跨采样频率的强大迁移能力。然而，该方法未能改善剩余使用寿命预测，表明预训练与RUL目标之间存在不匹配，值得未来进一步研究。
英文摘要
Deep learning predictive maintenance models suffer from poor transferability across machines and operating conditions, especially when labelled data are scarce and signals span five orders of magnitude in sampling frequency (1 Hz to ~100 kHz). We propose FreqCondNorm, a Transformer-based architecture that introduces a FiLM-style frequency-conditioned normalization layer to unify heterogeneous time-series within a single model. The architecture is pretrained on five public predictive maintenance datasets (CWRU, MFPT, UOC18, PRONOSTIA, CMAPSS) using masked auto-encoding and contrastive learning with balanced domain sampling. On fault diagnosis, the model achieves 99.2% accuracy on CWRU (+6.4 pp over CNN) and 82.1% zero-shot accuracy on MFPT, demonstrating strong transfer across sampling frequencies. However, the approach does not improve remaining useful life prediction, suggesting a mismatch between pretraining and RUL objectives that warrants future investigation.
