Title: Multi-mode process monitoring based on multi-block information extraction PCA method with local neighbourhood standardisation

Authors: Bingbin Gu; Weili Xiong

Addresses: School of Internet of Things Engineering, Jiangnnan University, Wuxi, Jiangsu Province, China ' School of Internet of Things Engineering, Jiangnnan University, Wuxi, Jiangsu Province, China; Key Laboratory of Advanced Process Control for Light Industry of Ministry of Education, Jiangnan University, Wuxi, Jiangsu Province, China

Abstract: In order to solve the problem of multi-mode process data in complex industrial processes, a multi-mode industrial process fault monitoring method based on multi-block information extraction PCA with local neighbourhood standardisation is proposed. Firstly, define the cumulative observation information and rate of change information of the process variable. Then extract the two kinds of information from the existing observation information and obtain the data sub-blocks of the three kinds of information. Secondly, the three data sets are separately standardised by the local neighbourhood standardisation method. Accordingly, three PCA models were built based on the three information datasets obtained and each PCA model will get a monitoring result. Finally, the Bayesian inference method is used to fuse the results of the three models to obtain a final BIC monitoring index. The effectiveness and feasibility of the proposed method are proved by a numerical example and applications in Tennessee-Eastman (TE) process monitoring.

Keywords: principal component analysis; information extraction; multi-block modelling; multimode process; local neighbourhood standardisation.

DOI: 10.1504/IJMIC.2019.103656

International Journal of Modelling, Identification and Control, 2019 Vol.32 No.3/4, pp.264 - 273

Received: 09 Jan 2019
Accepted: 07 Mar 2019
Published online: 18 Nov 2019 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article