Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach
This work has two objectives. Firstly, it describes a novel physics-informed hybrid neural network (PIHNN) model based on the long short-term memory (LSTM) neural network. The presented model structure combines the first-principle process description and data-driven neural sub-models using a special...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/23/21/8898 |
_version_ | 1797631250732679168 |
---|---|
author | Krzysztof Zarzycki Maciej Ławryńczuk |
author_facet | Krzysztof Zarzycki Maciej Ławryńczuk |
author_sort | Krzysztof Zarzycki |
collection | DOAJ |
description | This work has two objectives. Firstly, it describes a novel physics-informed hybrid neural network (PIHNN) model based on the long short-term memory (LSTM) neural network. The presented model structure combines the first-principle process description and data-driven neural sub-models using a specialized data fusion block that relies on fuzzy logic. The second objective of this work is to detail a computationally efficient model predictive control (MPC) algorithm that employs the PIHNN model. The validity of the presented modeling and MPC approaches is demonstrated for a simulated polymerization reactor. It is shown that the PIHNN structure gives very good modeling results, while the MPC controller results in excellent control quality. |
first_indexed | 2024-03-11T11:21:11Z |
format | Article |
id | doaj.art-318e6f9ab55c4584a07cfbec33f29fdc |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-03-11T11:21:11Z |
publishDate | 2023-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-318e6f9ab55c4584a07cfbec33f29fdc2023-11-10T15:12:38ZengMDPI AGSensors1424-82202023-11-012321889810.3390/s23218898Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed ApproachKrzysztof Zarzycki0Maciej Ławryńczuk1Institute of Control and Computation Engineering, Faculty of Electronics and Information Technology, Warsaw University of Technology, ul. Nowowiejska 15/19, 00-665 Warsaw, PolandInstitute of Control and Computation Engineering, Faculty of Electronics and Information Technology, Warsaw University of Technology, ul. Nowowiejska 15/19, 00-665 Warsaw, PolandThis work has two objectives. Firstly, it describes a novel physics-informed hybrid neural network (PIHNN) model based on the long short-term memory (LSTM) neural network. The presented model structure combines the first-principle process description and data-driven neural sub-models using a specialized data fusion block that relies on fuzzy logic. The second objective of this work is to detail a computationally efficient model predictive control (MPC) algorithm that employs the PIHNN model. The validity of the presented modeling and MPC approaches is demonstrated for a simulated polymerization reactor. It is shown that the PIHNN structure gives very good modeling results, while the MPC controller results in excellent control quality.https://www.mdpi.com/1424-8220/23/21/8898dynamical systemsLSTM neural networksphysics-informed neural networksmodel predictive control |
spellingShingle | Krzysztof Zarzycki Maciej Ławryńczuk Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach Sensors dynamical systems LSTM neural networks physics-informed neural networks model predictive control |
title | Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach |
title_full | Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach |
title_fullStr | Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach |
title_full_unstemmed | Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach |
title_short | Long Short-Term Memory Neural Networks for Modeling Dynamical Processes and Predictive Control: A Hybrid Physics-Informed Approach |
title_sort | long short term memory neural networks for modeling dynamical processes and predictive control a hybrid physics informed approach |
topic | dynamical systems LSTM neural networks physics-informed neural networks model predictive control |
url | https://www.mdpi.com/1424-8220/23/21/8898 |
work_keys_str_mv | AT krzysztofzarzycki longshorttermmemoryneuralnetworksformodelingdynamicalprocessesandpredictivecontrolahybridphysicsinformedapproach AT maciejławrynczuk longshorttermmemoryneuralnetworksformodelingdynamicalprocessesandpredictivecontrolahybridphysicsinformedapproach |