Salvato in:
Dettagli Bibliografici
Autori principali: Li, Zhaoyang, Han, Minghao, Vo, Dat-Nguyen, Yin, Xunyuan
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2408.02315
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917741297926144
author Li, Zhaoyang
Han, Minghao
Vo, Dat-Nguyen
Yin, Xunyuan
author_facet Li, Zhaoyang
Han, Minghao
Vo, Dat-Nguyen
Yin, Xunyuan
contents Koopman-based modeling and model predictive control have been a promising alternative for optimal control of nonlinear processes. Good Koopman modeling performance significantly depends on an appropriate nonlinear mapping from the original state-space to a lifted state space. In this work, we propose an input-augmented Koopman modeling and model predictive control approach. Both the states and the known inputs are lifted using two deep neural networks (DNNs), and a Koopman model with nonlinearity in inputs is trained within the higher-dimensional state-space. A Koopman-based model predictive control problem is formulated. To bypass non-convex optimization induced by the nonlinearity in the Koopman model, we further present an iterative implementation algorithm, which approximates the optimal control input via solving a convex optimization problem iteratively. The proposed method is applied to a chemical process and a biological water treatment process via simulations. The efficacy and advantages of the proposed modeling and control approach are demonstrated.
format Preprint
id arxiv_https___arxiv_org_abs_2408_02315
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Machine learning-based input-augmented Koopman modeling and predictive control of nonlinear processes
Li, Zhaoyang
Han, Minghao
Vo, Dat-Nguyen
Yin, Xunyuan
Systems and Control
Koopman-based modeling and model predictive control have been a promising alternative for optimal control of nonlinear processes. Good Koopman modeling performance significantly depends on an appropriate nonlinear mapping from the original state-space to a lifted state space. In this work, we propose an input-augmented Koopman modeling and model predictive control approach. Both the states and the known inputs are lifted using two deep neural networks (DNNs), and a Koopman model with nonlinearity in inputs is trained within the higher-dimensional state-space. A Koopman-based model predictive control problem is formulated. To bypass non-convex optimization induced by the nonlinearity in the Koopman model, we further present an iterative implementation algorithm, which approximates the optimal control input via solving a convex optimization problem iteratively. The proposed method is applied to a chemical process and a biological water treatment process via simulations. The efficacy and advantages of the proposed modeling and control approach are demonstrated.
title Machine learning-based input-augmented Koopman modeling and predictive control of nonlinear processes
topic Systems and Control
url https://arxiv.org/abs/2408.02315