文献类型：期刊文献

英文题名：Hierarchical fault root cause diagnosis in multimode process using direct causality and causal polarity analysis

作者：Yu, Zhenhua[1];Wang, Guan[2];Sun, Lihua[1];Jiang, Qingchao[1];Zhong, Weimin[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, State Key Lab Bioreactor Engn, Shanghai 200237, Peoples R China

年份：2026

卷号：363

期号：6

外文期刊名：JOURNAL OF THE FRANKLIN INSTITUTE

收录：;EI(收录号：20261320379227);WOS:【SCI-EXPANDED(收录号:WOS:001705690500001)】；

基金：The authors gratefully acknowledge the support from the following foundations: the National Natural Science Foundation of China (62322309, U25A20468) , Shanghai Explorer Program (24TS1411700) .

语种：英文

外文关键词：Root cause diagnosis; Causal inference; Direct causality; Causal polarity analysis

摘要：Fault root cause diagnosis is crucial for ensuring safety and improving efficiency in industrial processes. Traditional methods, such as granger causality and partial cross mapping, cannot identify the causal polarity (positive or negative) between variables, resulting in incorrect causal relationships and inability to effectively locate the root cause variable of the fault. Therefore, this paper proposes a hierarchical direct causal polarity identification (HDCPI) framework that infers direct causality and provides causal polarity between variables for root cause diagnosis. First, a continual learning variational autoencoder based multimode monitoring approach is used to detect fault occurrences, and candidate root cause variables are identified through contribution plot. Then, sparse nonlinear dynamics identification improved by dual domain sampling is applied to mining dynamic. Finally, a model-based causal detection function is used to eliminate indirect causality and identify causal polarity, thereby constructing a causal graph for fault root cause diagnosis. Extensive evaluations on both simulated and real-world datasets demonstrate that the proposed HDCPI substantially improves diagnostic precision and interpretability, consistently outperforming existing methods.