文献类型：期刊文献

英文题名：Plant-Wide Process Incipient Fault Detection via Double-Layer Subspace Weighted Moving Window Reconstruction ICA

作者：Song, Bing[1]; Song, YiMeng[1]; Shi, Hongbo[1]; Jiang, QingChao[1]

机构：[1] East China University of Science and Technology, Key Laboratory of Advanced Control and Optimization for Chemical Processes of the Ministry of Education, Shanghai, China

年份：2024

期号：2024

起止页码：174

外文期刊名：Proceedings of the IEEE International Conference on Cybernetics and Intelligent Systems, CIS

收录：EI(收录号：20244617343280)

语种：英文

外文关键词：Image reconstruction - Inference engines

摘要：With the widespread use of distributed systems, multi-subspace whole-flow industrial monitoring methods are evolving. However, due to the lack of distinctive features, incipient faults in plant-wide processes are more difficult to detect. To improve the detection rate of incipient faults in plant-wide processes while maintaining the generality of the algorithm, a novel double-layer subspace weighted moving window reconstruction independent component analysis (DS-WRICA) method is proposed. In DS-WRICA, process variables are first divided into different subspaces based on process knowledge and data-driven partitioning methods. Secondly, a weighted moving window is used to increase the offset of incipient faults, and monitoring statistics are constructed by combining optimized reconstructed independent component analysis (RICA) and local outlier factor (LOF) in each subspace. Then, the monitoring statistics in each subspace are fused with information by Bayesian inference fusion method to obtain distributed monitoring results. Finally, the effectiveness and superiority of the DS-WRICA method are verified by industrial examples. ? 2024 IEEE.