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

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...

Full description

Saved in:
Bibliographic Details
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:
Online Access:https://hdl.handle.net/10356/176190
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-176190
record_format dspace
spelling sg-ntu-dr.10356-1761902024-05-31T07:06:18Z Efficient economic model predictive control of water treatment process with the learning-based Koopman operator Han, Minghao Yao, Jingshi Law, Adrian Wing-Keung Yin, Xunyuan School of Chemistry, Chemical Engineering and Biotechnology School of Civil and Environmental Engineering Environmental Process Modelling Centre Nanyang Environment and Water Research Institute Computer and Information Science Engineering Economic model predictive control Koopman operator Learning-based modeling and control Water treatment process 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. Ministry of Education (MOE) National Research Foundation (NRF) Public Utilities Board (PUB) Submitted/Accepted version This research is supported by the Ministry of Education, Singapore, under its Academic Research Fund Tier 1 (RG63/22). This research is also supported by the National Research Foundation, Singapore, and PUB, Singapore’s National Water Agency under its RIE2025 Urban Solutions and Sustainability (USS) (Water) Centre of Excellence (CoE) Programme, awarded to Nanyang Environment & Water Research Institute (NEWRI), Nanyang Technological University, Singapore (NTU). 2024-05-31T07:06:18Z 2024-05-31T07:06:18Z 2024 Journal Article Han, M., Yao, J., Law, A. W. & Yin, X. (2024). Efficient economic model predictive control of water treatment process with the learning-based Koopman operator. Control Engineering Practice, 149, 105975-. https://dx.doi.org/10.1016/j.conengprac.2024.105975 0967-0661 https://hdl.handle.net/10356/176190 10.1016/j.conengprac.2024.105975 149 105975 en RG63/22 Control Engineering Practice © 2024 Elsevier Ltd. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1016/j.conengprac.2024.105975. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Computer and Information Science
Engineering
Economic model predictive control
Koopman operator
Learning-based modeling and control
Water treatment process
spellingShingle Computer and Information Science
Engineering
Economic model predictive control
Koopman operator
Learning-based modeling and control
Water treatment process
Han, Minghao
Yao, Jingshi
Law, Adrian Wing-Keung
Yin, Xunyuan
Efficient economic model predictive control of water treatment process with the learning-based Koopman operator
description 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.
author2 School of Chemistry, Chemical Engineering and Biotechnology
author_facet School of Chemistry, Chemical Engineering and Biotechnology
Han, Minghao
Yao, Jingshi
Law, Adrian Wing-Keung
Yin, Xunyuan
format Article
author Han, Minghao
Yao, Jingshi
Law, Adrian Wing-Keung
Yin, Xunyuan
author_sort Han, Minghao
title Efficient economic model predictive control of water treatment process with the learning-based Koopman operator
title_short Efficient economic model predictive control of water treatment process with the learning-based Koopman operator
title_full Efficient economic model predictive control of water treatment process with the learning-based Koopman operator
title_fullStr Efficient economic model predictive control of water treatment process with the learning-based Koopman operator
title_full_unstemmed Efficient economic model predictive control of water treatment process with the learning-based Koopman operator
title_sort efficient economic model predictive control of water treatment process with the learning-based koopman operator
publishDate 2024
url https://hdl.handle.net/10356/176190
_version_ 1800916421576753152