Efficient economic model predictive control of water treatment process with the learning-based Koopman operator

• Main Authors: Han, Minghao, Yao, Jingshi, Law, Adrian Wing-Keung, Yin, Xunyuan
• Other Authors: School of Chemistry, Chemical Engineering and Biotechnology
• Format: Article
• Language: English
• Published: 2024
• Subjects: Computer and Information Science; Engineering; Economic model predictive control; Koopman operator; Learning-based modeling and control; Water treatment process
• Online Access: https://hdl.handle.net/10356/176190
• Institution: Nanyang Technological University

Used water treatment plays a pivotal role in advancing environmental sustainability. Economic model predictive control holds the promise of enhancing the overall operational performance of the water treatment facilities. In this study, we propose a data-driven economic predictive control approach within the Koopman modeling framework. First, we propose a deep learning-enabled input-output Koopman modeling approach, which predicts the overall economic operational cost of the water treatment processes based on input data and available outputs that are directly linked to the operational costs. Subsequently, by leveraging this learned input-output Koopman model, a convex economic predictive control scheme is developed. The resulting predictive control problem can be efficiently solved by leveraging quadratic programming solvers, and complex non-convex optimization problems are bypassed. The proposed method is applied to a benchmark water treatment configuration, and the results show that it significantly improves the overall economic operational performance. Additionally, the computational efficiency of the proposed method is significantly enhanced as compared to benchmark control solutions.