Transfer learning for batch process optimal control using LV-PTM and adaptive control strategy. (September 2019)

• Record Type: Journal Article
• Authors: Chu, Fei; Zhao, Xu; Yao, Yuan; Chen, Tao; Wang, Fuli
• Is Part Of: Journal of process control. Volume 81(2019)
• Page Start: 197
• Page End: 208
• Publication Date: 2019-09
• Subjects: Transfer learning -- Data-driven -- LV-PTM -- Optimal control -- Adaptive control strategy; Process control -- Periodicals; Fabrication -- Contrôle -- Périodiques; Process control; Periodicals; Electronic journals; 660.281
• DOI: 10.1016/j.jprocont.2019.06.010
• Languages: English
• ISSNs: 0959-1524

Abstract

Highlights: An LV-PTM based batch-to-batch optimization methodology is proposed and applied to the quality optimization between similar batch processes. The new plant-LV-PTM mismatch problem resulted from process transfer, differ from the traditional one is firstly proposed and formalized. An LV-PTM-based adaptive optimal control strategy for the NCO mismatch problem of the optimization between similar batch processes is proposed. The main algorithm framework of batch-to-batch optimization based on process transfer is given. Abstract: In this study, we investigate a data-driven optimal control for a new batch process. Existing data-driven optimal control methods often ignore an important problem, namely, because of the short operation time of the new batch process, the modeling data in the initial stage can be insufficient. To address this issue, we introduce the idea of transfer learning, i.e., a latent variable process transfer model (LV-PTM) is adopted to transfer sufficient data and process information from similar processes to a new one to assist its modeling and quality optimization control. However, due to fluctuations in raw materials, equipment, etc., differences between similar batch process are always inevitable, which lead to the serious and complicated mismatch of the necessary condition of optimality (NCO) between the new batch process and the LV-PTM-based optimization problem. In this work, we propose an LV-PTM-based batch-to-batch adaptive optimal control strategy, which consists of three stages, to ensure the best optimization performance during the whole operation lifetime of the new batch process. This adaptive control strategy includes model updating, data removal, and modifier-adaptation methodology using final quality measurements in response. Finally, the feasibility of the proposed method is demonstrated by simulations.