An uncertainty decomposition-based automated out-of-distribution detection framework- for trustworthy machinery fault diagnosis
Tao Zeng, Hongkai Jiang, Xin Wang, Yan Bai, Zichun Yi
Northwestern Polytechnical University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
In modern industrial systems, machinery frequently encounters out-of-distribution (OOD) samples due to unknown faults and abnormal operating conditions. However, conventional deep learning methods, which rely on point estimation and lack uncertainty quantification capabilities, struggle to provide reliable judgments under such circumstances. Existing Bayesian deep learning methods have made progress in identifying unknown faults. However, their quantification accuracy under unknown conditions is still limited. In addition, these methods lack the ability to effectively distinguish between different types of anomalies in such conditions. To address this issue, this paper proposes an uncertainty decomposition-based automatic detection framework to enhance the model’s ability to detect OOD faults. First, a dynamic Kullback–Leibler divergence weighting mechanism is introduced to improve the model’s capability to capture uncertainties at different network layers. Then, a more refined uncertainty decomposition method is designed to enhance the interpretability of uncertainty quantification. Finally, an automatic detection mechanism based on statistical analysis is developed to enable automatic identification of OOD samples. Experimental results on two datasets demonstrate the effectiveness of the proposed framework. It significantly improves the diagnostic accuracy of Bayesian deep learning models. Moreover, it achieves more precise uncertainty quantification. These improvements enhance the reliability of the diagnostic results.
逐年被引趋势
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
工程Machine Fault Diagnosis Techniques
Fault Detection and Control Systems · Anomaly Detection Techniques and Applications
参考文献 39
此处列出前 3 条
引用本文 1
按被引量排序,此处列出前 3 条