文献类型：期刊文献

英文题名：PCA-ICA Integrated with Bayesian Method for Non-Gaussian Fault Diagnosis

作者：Jiang, Qingchao[1];Yan, Xuefeng[1];Li, Juan[2]

机构：[1]E China Univ Sci & Technol, Minist Educ, Key Lab Adv Control & Optimizat Chem Proc, Shanghai 200237, Peoples R China;[2]Qingdao Agr Univ, Coll Mech & Elect Engn, Qingdao 266109, Peoples R China

年份：2016

卷号：55

期号：17

起止页码：4979

外文期刊名：INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH

收录：;EI(收录号：20162102417248);WOS:【SCI-EXPANDED(收录号:WOS:000375521200020)】；

基金：The authors gratefully acknowledge the support from the following foundations: 973 project of China (Grant 2013CB733600), National Natural Science Foundation of China (Grants 21176073 and 61374126), Program for New Century Excellent Talents in University (Grant NCET-09-0346), the Fundamental Research Funds for the Central Universities, Natural Science Foundation of Shandong Province (Grant ZR2013FM021), and the Funding Provided by the Alexander von Humboldt Foundation.

语种：英文

外文关键词：Process monitoring - Gaussian distribution - Failure analysis - Optimization - Gaussian noise (electronic) - Bayesian networks - Principal component analysis - Fault detection - Numerical methods

摘要：Recent work has demonstrated the effectiveness of the principal component analysis (PCA)-independent component analysis (ICA) method for non-Gaussian process monitoring; however, the focus is on fault detection and isolation. The fault diagnosis issue has not been sufficiently investigated. This paper aims to introduce a PCA-ICA integrated with a Bayesian fault diagnosis method for non-Gaussian processes. First, PCA is employed to project the source signals into the dominant subspace. Second, ICA is employed to extract the independent components from the PCA dominant subspace. Then fault signature evidence is generated, and a Bayesian fault diagnosis system is established to identify the process status. Considering the significant amount of calculation in Bayesian diagnosis, a subset of optimal evidence sources are selected via a stochastic optimization algorithm. The efficiency and feasibility of the proposed method are exemplified by a numerical example and, the Tennessee Eastman benchmark process.