Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning

The time cost of first-principles dynamic modelling and the complexity of nonlinear control strategies may limit successful implementation of advanced process control. The maximum return on fixed capital within the processing industries is thus compromised. This study introduces a neurocontrol metho...

Full description

Bibliographic Details
Main Authors: Conradie, A., Aldrich, Chris
Format: Journal Article
Published: Pergamon 2010
Subjects:
Online Access:http://hdl.handle.net/20.500.11937/20241
_version_ 1848750251786108928
author Conradie, A.
Aldrich, Chris
author_facet Conradie, A.
Aldrich, Chris
author_sort Conradie, A.
building Curtin Institutional Repository
collection Online Access
description The time cost of first-principles dynamic modelling and the complexity of nonlinear control strategies may limit successful implementation of advanced process control. The maximum return on fixed capital within the processing industries is thus compromised. This study introduces a neurocontrol methodology that uses partial system identification and symbiotic memetic neuro-evolution (SMNE) for the development of neurocontrollers. Partial system identification is achieved using singular spectrum analysis (SSA) to extract state variables from time series data. The SMNE algorithm uses a symbiotic evolutionary algorithm and particle swarm optimisation to learn optimal neurocontroller weights from the partially identified system within a reinforcement learning framework. A multi-effect batch distillation (MEBAD) pilot plant was constructed to demonstrate the real world application of the neurocontrol methodology, motivated by the nonsteady state operation and nonlinear process interaction between multiple distillation columns. Multi-loop proportional integral (PI) control was implemented as a reduced model, reflecting an approach involving no modelling or significant controller tuning. Rapid multiple input multiple out nonlinear controller development was achieved using SSA and the SMNE algorithm, demonstrating comparable time and cost to implementation in relation to the reduced model. The optimal neurocontroller reduced the batch time and therefore the energy consumption by 45% compared to conventional multi-loop SISO PI control.
first_indexed 2025-11-14T07:33:52Z
format Journal Article
id curtin-20.500.11937-20241
institution Curtin University Malaysia
institution_category Local University
last_indexed 2025-11-14T07:33:52Z
publishDate 2010
publisher Pergamon
recordtype eprints
repository_type Digital Repository
spelling curtin-20.500.11937-202412017-09-13T15:40:42Z Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning Conradie, A. Aldrich, Chris Nonlinear dynamics Evolutionary programming Neural networks Distillation Process control Mathematical modelling The time cost of first-principles dynamic modelling and the complexity of nonlinear control strategies may limit successful implementation of advanced process control. The maximum return on fixed capital within the processing industries is thus compromised. This study introduces a neurocontrol methodology that uses partial system identification and symbiotic memetic neuro-evolution (SMNE) for the development of neurocontrollers. Partial system identification is achieved using singular spectrum analysis (SSA) to extract state variables from time series data. The SMNE algorithm uses a symbiotic evolutionary algorithm and particle swarm optimisation to learn optimal neurocontroller weights from the partially identified system within a reinforcement learning framework. A multi-effect batch distillation (MEBAD) pilot plant was constructed to demonstrate the real world application of the neurocontrol methodology, motivated by the nonsteady state operation and nonlinear process interaction between multiple distillation columns. Multi-loop proportional integral (PI) control was implemented as a reduced model, reflecting an approach involving no modelling or significant controller tuning. Rapid multiple input multiple out nonlinear controller development was achieved using SSA and the SMNE algorithm, demonstrating comparable time and cost to implementation in relation to the reduced model. The optimal neurocontroller reduced the batch time and therefore the energy consumption by 45% compared to conventional multi-loop SISO PI control. 2010 Journal Article http://hdl.handle.net/20.500.11937/20241 10.1016/j.ces.2009.11.003 Pergamon restricted
spellingShingle Nonlinear dynamics
Evolutionary programming
Neural networks
Distillation
Process control
Mathematical modelling
Conradie, A.
Aldrich, Chris
Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning
title Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning
title_full Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning
title_fullStr Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning
title_full_unstemmed Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning
title_short Neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning
title_sort neurocontrol of a multi-effect batch distillation pilot plant based on evolutionary reinforcement learning
topic Nonlinear dynamics
Evolutionary programming
Neural networks
Distillation
Process control
Mathematical modelling
url http://hdl.handle.net/20.500.11937/20241