Title: Enhanced monitoring of batch process using just-in-time learning-based kernel independent component analysis

Authors: Li Wang

Addresses: School of Electrical and Electronic Engineering, Shanghai Institute of Technology, Shanghai 200230, China

Abstract: A new method is developed for batch process monitoring in this paper. In the developed method, just-in-time learning (JITL) and kernel independent component analysis (KICA) are integrated to build JITL-KICA monitoring scheme. JITL is employed to tackle with the characteristics of batch process such as inherent time-varying dynamics, multiple operating phases, and especially the case of uneven length stage. According to new coming test data, the most correlated segmentation is obtained from batch-wise unfolded training data by JITL. Then, KICA serves as the principal components extraction approach. Therefore, the non-Gaussian distributed data can also be addressed under this modelling framework. The effectiveness and superiority of JITL-KICA-based monitoring method is demonstrated through benchmark data of DuPont industrial batch polymerisation reactor.

Keywords: batch process; process modelling; process monitoring; time varying dynamics; multiple operating phases; uneven length stage; non-Gaussian distribution; kernel independent component analysis; KICA; just-in-time learning; JITL; online fault detection.

DOI: 10.1504/IJESMS.2017.085043

International Journal of Engineering Systems Modelling and Simulation, 2017 Vol.9 No.3, pp.136 - 142

Received: 06 Feb 2016
Accepted: 23 Jul 2016

Published online: 08 Jun 2017 *

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