Adaptive Nonlinear Proportional–Integral–Derivative Control of a Continuous Stirred Tank Reactor Process Using a Radial Basis Function Neural Network

Temperature control in a continuous stirred tank reactor (CSTR) poses significant challenges due to the process’s inherent nonlinearities and uncertain parameters. This study proposes an innovative solution by developing an adaptive nonlinear proportional–integral–derivative (NPID) controller. The n...

Full description

Saved in:
Bibliographic Details
Main Authors: Joo-Yeon Lee, Gang-Gyoo Jin, Gun-Baek So
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Algorithms
Subjects:
Online Access:https://www.mdpi.com/1999-4893/18/7/442
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849409599584600064
author Joo-Yeon Lee
Gang-Gyoo Jin
Gun-Baek So
author_facet Joo-Yeon Lee
Gang-Gyoo Jin
Gun-Baek So
author_sort Joo-Yeon Lee
collection DOAJ
description Temperature control in a continuous stirred tank reactor (CSTR) poses significant challenges due to the process’s inherent nonlinearities and uncertain parameters. This study proposes an innovative solution by developing an adaptive nonlinear proportional–integral–derivative (NPID) controller. The nonlinear gain that dynamically scales the error fed to the integrator is enhanced for optimized performance. The network’s ability to approximate nonlinear functions and its online learning capabilities are leveraged by effectively integrating an NPID control scheme with a radial basis function neural network (RBFNN). This synergistic approach provides a more robust and reliable control strategy for CSTRs. To assess the proposed method’s feasibility, a set of simulations was conducted for tracking, disturbance rejection, and parameter variations. These results were compared with those of an adaptive RBFNN-based PID (APID) controller under identical conditions. The simulations indicated that the proposed method achieved reductions in maximum overshoot of 33.7% and settling time of 54.2% for upward and downward setpoint changes and 27.2% and 5.3% for downward and upward setpoint changes compared to the APID controller. For disturbance changes, the proposed method reduced the peak magnitude (<i>M<sub>peak</sub></i>) by 4.9%, recovery time (<i>t<sub>rcy</sub></i>) by 23.6%, and integral absolute error by 16.2%. Similarly, for parameter changes, the reductions were 3.0% (<i>M<sub>peak</sub></i>), 26.4% (<i>t<sub>rcy</sub></i>), and 24.4% (<i>IAE</i>).
format Article
id doaj-art-75bbd986434b4252afd2b51957450dd0
institution Kabale University
issn 1999-4893
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Algorithms
spelling doaj-art-75bbd986434b4252afd2b51957450dd02025-08-20T03:35:27ZengMDPI AGAlgorithms1999-48932025-07-0118744210.3390/a18070442Adaptive Nonlinear Proportional–Integral–Derivative Control of a Continuous Stirred Tank Reactor Process Using a Radial Basis Function Neural NetworkJoo-Yeon Lee0Gang-Gyoo Jin1Gun-Baek So2Ocean Space Development & Energy Research Department, Korea Institute of Ocean Science and Technology, Busan 49111, Republic of KoreaDepartment of Electrical Power and Control Engineering, Adama Science and Technology University, Adama 1888, EthiopiaDepartment of Maritime Industry Convergence, Mokpo National Maritime University, Mokpo 58628, Republic of KoreaTemperature control in a continuous stirred tank reactor (CSTR) poses significant challenges due to the process’s inherent nonlinearities and uncertain parameters. This study proposes an innovative solution by developing an adaptive nonlinear proportional–integral–derivative (NPID) controller. The nonlinear gain that dynamically scales the error fed to the integrator is enhanced for optimized performance. The network’s ability to approximate nonlinear functions and its online learning capabilities are leveraged by effectively integrating an NPID control scheme with a radial basis function neural network (RBFNN). This synergistic approach provides a more robust and reliable control strategy for CSTRs. To assess the proposed method’s feasibility, a set of simulations was conducted for tracking, disturbance rejection, and parameter variations. These results were compared with those of an adaptive RBFNN-based PID (APID) controller under identical conditions. The simulations indicated that the proposed method achieved reductions in maximum overshoot of 33.7% and settling time of 54.2% for upward and downward setpoint changes and 27.2% and 5.3% for downward and upward setpoint changes compared to the APID controller. For disturbance changes, the proposed method reduced the peak magnitude (<i>M<sub>peak</sub></i>) by 4.9%, recovery time (<i>t<sub>rcy</sub></i>) by 23.6%, and integral absolute error by 16.2%. Similarly, for parameter changes, the reductions were 3.0% (<i>M<sub>peak</sub></i>), 26.4% (<i>t<sub>rcy</sub></i>), and 24.4% (<i>IAE</i>).https://www.mdpi.com/1999-4893/18/7/442CSTRadaptive controlnonlinear PID controllerRBFNNsystem identification
spellingShingle Joo-Yeon Lee
Gang-Gyoo Jin
Gun-Baek So
Adaptive Nonlinear Proportional–Integral–Derivative Control of a Continuous Stirred Tank Reactor Process Using a Radial Basis Function Neural Network
Algorithms
CSTR
adaptive control
nonlinear PID controller
RBFNN
system identification
title Adaptive Nonlinear Proportional–Integral–Derivative Control of a Continuous Stirred Tank Reactor Process Using a Radial Basis Function Neural Network
title_full Adaptive Nonlinear Proportional–Integral–Derivative Control of a Continuous Stirred Tank Reactor Process Using a Radial Basis Function Neural Network
title_fullStr Adaptive Nonlinear Proportional–Integral–Derivative Control of a Continuous Stirred Tank Reactor Process Using a Radial Basis Function Neural Network
title_full_unstemmed Adaptive Nonlinear Proportional–Integral–Derivative Control of a Continuous Stirred Tank Reactor Process Using a Radial Basis Function Neural Network
title_short Adaptive Nonlinear Proportional–Integral–Derivative Control of a Continuous Stirred Tank Reactor Process Using a Radial Basis Function Neural Network
title_sort adaptive nonlinear proportional integral derivative control of a continuous stirred tank reactor process using a radial basis function neural network
topic CSTR
adaptive control
nonlinear PID controller
RBFNN
system identification
url https://www.mdpi.com/1999-4893/18/7/442
work_keys_str_mv AT jooyeonlee adaptivenonlinearproportionalintegralderivativecontrolofacontinuousstirredtankreactorprocessusingaradialbasisfunctionneuralnetwork
AT ganggyoojin adaptivenonlinearproportionalintegralderivativecontrolofacontinuousstirredtankreactorprocessusingaradialbasisfunctionneuralnetwork
AT gunbaekso adaptivenonlinearproportionalintegralderivativecontrolofacontinuousstirredtankreactorprocessusingaradialbasisfunctionneuralnetwork