Online Tuning of a PID Controller with a Fuzzy Reinforcement Learning MAS for Flow Rate Control of a Desalination Unit
This paper proposes a hybrid Zeigler-Nichols (Z-N) fuzzy reinforcement learning MAS (Multi-Agent System) approach for online tuning of a Proportional Integral Derivative (PID) controller in order to control the flow rate of a desalination unit. The PID gains are set by the Z-N method and then are ad...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-02-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/8/2/231 |
id |
doaj-845cfcf905a9488689fb4c48a6a25757 |
---|---|
record_format |
Article |
spelling |
doaj-845cfcf905a9488689fb4c48a6a257572020-11-25T02:53:17ZengMDPI AGElectronics2079-92922019-02-018223110.3390/electronics8020231electronics8020231Online Tuning of a PID Controller with a Fuzzy Reinforcement Learning MAS for Flow Rate Control of a Desalination UnitPanagiotis Kofinas0Anastasios I. Dounis1Department of Industrial Design and Production Engineering, University of West Attica, 12243 Egaleo-Athens, GreeceDepartment of Industrial Design and Production Engineering, University of West Attica, 12243 Egaleo-Athens, GreeceThis paper proposes a hybrid Zeigler-Nichols (Z-N) fuzzy reinforcement learning MAS (Multi-Agent System) approach for online tuning of a Proportional Integral Derivative (PID) controller in order to control the flow rate of a desalination unit. The PID gains are set by the Z-N method and then are adapted online through the fuzzy Q-learning MAS. The fuzzy Q-learning is introduced in each agent in order to confront with the continuous state-action space. The global state of the MAS is defined by the value of the error and the derivative of error. The MAS consists of three agents and the output signal of each agent defines the percentage change of each gain. The increment or the reduction of each gain can be in the range of 0% to 100% of its initial value. The simulation results highlight the performance of the suggested hybrid control strategy through comparison with the conventional PID controller tuned by Z-N.https://www.mdpi.com/2079-9292/8/2/231reinforcement learningPID controlleronline tuningdesalination plantfuzzy reinforcement learningMAS |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Panagiotis Kofinas Anastasios I. Dounis |
spellingShingle |
Panagiotis Kofinas Anastasios I. Dounis Online Tuning of a PID Controller with a Fuzzy Reinforcement Learning MAS for Flow Rate Control of a Desalination Unit Electronics reinforcement learning PID controller online tuning desalination plant fuzzy reinforcement learning MAS |
author_facet |
Panagiotis Kofinas Anastasios I. Dounis |
author_sort |
Panagiotis Kofinas |
title |
Online Tuning of a PID Controller with a Fuzzy Reinforcement Learning MAS for Flow Rate Control of a Desalination Unit |
title_short |
Online Tuning of a PID Controller with a Fuzzy Reinforcement Learning MAS for Flow Rate Control of a Desalination Unit |
title_full |
Online Tuning of a PID Controller with a Fuzzy Reinforcement Learning MAS for Flow Rate Control of a Desalination Unit |
title_fullStr |
Online Tuning of a PID Controller with a Fuzzy Reinforcement Learning MAS for Flow Rate Control of a Desalination Unit |
title_full_unstemmed |
Online Tuning of a PID Controller with a Fuzzy Reinforcement Learning MAS for Flow Rate Control of a Desalination Unit |
title_sort |
online tuning of a pid controller with a fuzzy reinforcement learning mas for flow rate control of a desalination unit |
publisher |
MDPI AG |
series |
Electronics |
issn |
2079-9292 |
publishDate |
2019-02-01 |
description |
This paper proposes a hybrid Zeigler-Nichols (Z-N) fuzzy reinforcement learning MAS (Multi-Agent System) approach for online tuning of a Proportional Integral Derivative (PID) controller in order to control the flow rate of a desalination unit. The PID gains are set by the Z-N method and then are adapted online through the fuzzy Q-learning MAS. The fuzzy Q-learning is introduced in each agent in order to confront with the continuous state-action space. The global state of the MAS is defined by the value of the error and the derivative of error. The MAS consists of three agents and the output signal of each agent defines the percentage change of each gain. The increment or the reduction of each gain can be in the range of 0% to 100% of its initial value. The simulation results highlight the performance of the suggested hybrid control strategy through comparison with the conventional PID controller tuned by Z-N. |
topic |
reinforcement learning PID controller online tuning desalination plant fuzzy reinforcement learning MAS |
url |
https://www.mdpi.com/2079-9292/8/2/231 |
work_keys_str_mv |
AT panagiotiskofinas onlinetuningofapidcontrollerwithafuzzyreinforcementlearningmasforflowratecontrolofadesalinationunit AT anastasiosidounis onlinetuningofapidcontrollerwithafuzzyreinforcementlearningmasforflowratecontrolofadesalinationunit |
_version_ |
1724725488246587392 |