Key principal components with recursive local outlier factor for multimode chemical process monitoring. (November 2016)

• Record Type: Journal Article
• Authors: Song, Bing; Tan, Shuai; Shi, Hongbo
• Is Part Of: Journal of process control. Volume 47(2016:Nov.)
• Page Start: 136
• Page End: 149
• Publication Date: 2016-11
• Subjects: Multimode process monitoring -- Principal component analysis -- Recursive local outlier factor -- Cumulative percent expression -- Key principal components; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2016.09.006
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: A novel multimode process monitoring method (KPCs-RLOF) is developed. A novel mode identification approach is proposed on the basis of the sequential information in the time scale and the density information in the spatial scale. A new strategy named cumulative percent expression is developed to select key PCs. Abstract: Owing to various manufacturing strategies and demands of markets, chemical processes often involve multiple operating modes. How to identify mode from multimode process data collected under both stable and transitional modes is an important issue. This paper proposes a novel mode identification algorithm-recursive local outlier factor (RLOF) based on the sequential information in the time scale and the density information in the spatial scale. In this algorithm, not only the number of modes does not need to be determined in advance, but also details of mode switching can be acquired. In addition, the principal components (PCs) chosen by the variance of overall dataset in principal component analysis (PCA) cannot guarantee that all variables express information as completely as possible. Using the defined cumulative percent expression (CPE), this study chooses key PCs (KPCs) according to each variable. Moreover, fault diagnosis is realized via the contribution of every variable to key PCs. Finally, the monitoring performance is evaluated under the Tennessee Eastman (TE) benchmark and the continuous stirred tank reactor (CSTR) process.