Economic Machine-Learning-Based Predictive Control of Nonlinear Systems

Economic Machine-Learning-Based Predictive Control of Nonlinear Systems

In this work, a Lyapunov-based economic model predictive control (LEMPC) method is developed to address economic optimality and closed-loop stability of nonlinear systems using machine learning-based models to make predictions. Specifically, an ensemble of recurrent neural network (RNN) models via a...

Full description

Bibliographic Details
Main Authors: Zhe Wu, Panagiotis D. Christofides
Format: Article
Language:English
Published: MDPI AG 2019-06-01
Series:Mathematics
Subjects:
economic model predictive control
recurrent neural networks
ensemble learning
nonlinear systems
parallel computing
Online Access:https://www.mdpi.com/2227-7390/7/6/494
id doaj-4244bd08c4854d5c8ebfad8009421f28
record_format Article
spelling doaj-4244bd08c4854d5c8ebfad8009421f282020-11-25T01:16:17ZengMDPI AGMathematics2227-73902019-06-017649410.3390/math7060494math7060494Economic Machine-Learning-Based Predictive Control of Nonlinear SystemsZhe Wu0Panagiotis D. Christofides1Department of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA 90095-1592, USADepartment of Chemical and Biomolecular Engineering, University of California, Los Angeles, CA 90095-1592, USAIn this work, a Lyapunov-based economic model predictive control (LEMPC) method is developed to address economic optimality and closed-loop stability of nonlinear systems using machine learning-based models to make predictions. Specifically, an ensemble of recurrent neural network (RNN) models via a <i>k</i>-fold cross validation is first developed to capture process dynamics in an operating region. Then, the LEMPC using an RNN ensemble is designed to maintain the closed-loop state in a stability region and optimize process economic benefits simultaneously. Parallel computing is employed to improve computational efficiency of real-time implementation of LEMPC with an RNN ensemble. The proposed machine-learning-based LEMPC method is demonstrated using a nonlinear chemical process example.https://www.mdpi.com/2227-7390/7/6/494economic model predictive controlrecurrent neural networksensemble learningnonlinear systemsparallel computing
collection DOAJ
language English
format Article
sources DOAJ
author Zhe Wu
Panagiotis D. Christofides
spellingShingle Zhe Wu
Panagiotis D. Christofides
Economic Machine-Learning-Based Predictive Control of Nonlinear Systems
Mathematics
economic model predictive control
recurrent neural networks
ensemble learning
nonlinear systems
parallel computing
author_facet Zhe Wu
Panagiotis D. Christofides
author_sort Zhe Wu
title Economic Machine-Learning-Based Predictive Control of Nonlinear Systems
title_short Economic Machine-Learning-Based Predictive Control of Nonlinear Systems
title_full Economic Machine-Learning-Based Predictive Control of Nonlinear Systems
title_fullStr Economic Machine-Learning-Based Predictive Control of Nonlinear Systems
title_full_unstemmed Economic Machine-Learning-Based Predictive Control of Nonlinear Systems
title_sort economic machine-learning-based predictive control of nonlinear systems
publisher MDPI AG
series Mathematics
issn 2227-7390
publishDate 2019-06-01
description In this work, a Lyapunov-based economic model predictive control (LEMPC) method is developed to address economic optimality and closed-loop stability of nonlinear systems using machine learning-based models to make predictions. Specifically, an ensemble of recurrent neural network (RNN) models via a <i>k</i>-fold cross validation is first developed to capture process dynamics in an operating region. Then, the LEMPC using an RNN ensemble is designed to maintain the closed-loop state in a stability region and optimize process economic benefits simultaneously. Parallel computing is employed to improve computational efficiency of real-time implementation of LEMPC with an RNN ensemble. The proposed machine-learning-based LEMPC method is demonstrated using a nonlinear chemical process example.
topic economic model predictive control
recurrent neural networks
ensemble learning
nonlinear systems
parallel computing
url https://www.mdpi.com/2227-7390/7/6/494
work_keys_str_mv AT zhewu economicmachinelearningbasedpredictivecontrolofnonlinearsystems
AT panagiotisdchristofides economicmachinelearningbasedpredictivecontrolofnonlinearsystems
_version_ 1725150419544440832

Similar Items