Parallel quality-related dynamic principal component regression method for chemical process monitoring. (January 2019)

• Record Type: Journal Article
• Authors: Tao, Yang; Shi, Hongbo; Song, Bing; Tan, Shuai
• Is Part Of: Journal of process control. Volume 73(2019)
• Page Start: 33
• Page End: 45
• Publication Date: 2019-01
• Subjects: Additive fault -- Multiplicative fault -- Principal -- Component regression -- Process monitoring; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2018.08.009
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: A novel quality-related process monitoring method named parallel dynamic principal component regression (P-DPCR) is proposed. Both the magnitude and volatility of the quality-related process variables are monitored. A new quality-related process variables selection method is developed. Two dynamic extension strategies are presented for process and quality variables respectively. Abstract: Traditional quality-related process monitoring mainly focuses on the magnitude change of the quality variables caused by additive faults. However, the abnormal fluctuations in the quality variables caused by multiplicative faults are often overlooked. In this paper, a novel parallel dynamic principal component regression (P-DPCR) algorithm is proposed to monitor the changes in the magnitude and fluctuation of the quality variables simultaneously. Firstly, in order to eliminate the interference of quality-unrelated variables, the quality-related process variables are selected on the basis of correlation analysis. Secondly, the dynamic extension and moving window are carried out for process variables and quality variables, in which the dynamic variables space (called X-space/Y-space) and the variance space (called VX-space/VY-space) are constructed. Afterwards, double quality-related statistics based on the regression model of these four spaces are given, and the comprehensive monitoring decision can be obtained. Finally, two numerical cases and the Tennessee Eastman process are used to show the effectiveness of the proposed method.