Enhanced high‐order information extraction for multiphase batch process fault monitoring

Abstract

Conventional independent component analysis (ICA) monitoring methods extract the feature information of process data by selecting more important independent components (ICs), which discard a small part of ICs that may contain useful information for faults, leading to unsatisfactory monitoring results. However, when the number of sampling points is greater than that of process variables, the ICA monitoring model does not work well. To address the aforementioned problems, a novel monitoring method, multiphase enhanced high‐order information extraction (MEHOIE), is proposed in this paper. The entire production process was first divided into several steady phases and transition phases by the affinity propagation (AP) phase partitioning method. The enhanced high‐order information extraction (EHOIE) model was then built in each phase for fault monitoring. Finally, the algorithm was applied in the penicillin simulation platform and industrial microbial pharmaceutical process. The flexibility and superiority of this algorithm were verified by comparing it with other conventional methods.

Batch process monitoring based on sequential phase division multiway sparse weighted neighborhood preserving embedding

“…Zhu et al [17] proposed a multiphase batch process method based on a 2D time-slice dynamic system which characterized the batch-wise and variable-wise dynamics simultaneously. Chunhao et al [19] proposed an affinity propagation phase partition method to divide the whole process into several steady and transition phases. However, most of these multiphase methods assume that each batch has the same length and that critical events occur at the same time.…”