Structured sparsity modeling for improved multivariate statistical analysis based fault isolation. (February 2021)

• Record Type: Journal Article
• Authors: Chen, Wei; Zeng, Jiusun; Xu, Xiaobin; Luo, Shihua; Gao, Chuanhou
• Is Part Of: Journal of process control. Volume 98(2021)
• Page Start: 66
• Page End: 78
• Publication Date: 2021-02
• Subjects: Fault isolation -- Structured sparsity -- Multivariate statistical analysis -- ADMM; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2020.12.007
• Languages: English
• ISSNs: 0959-1524

Abstract

Abstract: In order to improve the fault diagnosis capability of multivariate statistical methods, this article introduces a fault isolation framework based on structured sparsity modeling. The developed method relies on the reconstruction based contribution analysis and the process structure information can be incorporated into the reconstruction objective function in the form of structured sparsity regularization terms. The structured sparsity terms allow selection of fault variables over structures like blocks or networks of process variables, hence more accurate fault isolation can be achieved. Four structured sparsity terms corresponding to different kinds of process information are considered, namely, partially known sparse support, block sparsity, clustered sparsity and tree-structured sparsity. The optimization problems involving the structured sparsity terms can be solved using the Alternating Direction Method of Multipliers (ADMM) algorithm, which is fast and efficient. Through a simulation example and an application study to a coal-fired power plant, it is verified that the proposed method can better isolate faulty variables by incorporating process structure information. Highlights: A structured sparsity modeling framework for improved multivariate statistical analysis based fault isolation is proposed. Four kinds of structured sparsity, namely, partially known sparse support, block sparsity, clustered sparsity and tree-structured sparsity, are considered. The structured sparsity allows selection of fault variables over structures like blocks or networks of process variables. Simulation and application studies show the effectiveness of the proposed method.