Genetic algorithm for control and optimisation of exothermic batch process

The aim of this research is to control and optimise the production of the desired product while minimising the waste production for an exothermic batch process. During the process, a large amount of heat is released rapidly when the reactants are mixed together. The exothermic behaviour causes the r...

Full description

Saved in:

Bibliographic Details
Main Author:	Tan, Min Keng
Format:	Thesis
Language:	English English
Published:	2013
Subjects:	QA76.75-76.765 Computer software
Online Access:	https://eprints.ums.edu.my/id/eprint/41807/1/24%20PAGES.pdf https://eprints.ums.edu.my/id/eprint/41807/2/FULLTEXT.pdf
Tags:	Add Tag No Tags, Be the first to tag this record!

id	my-ums-ep.41807
record_format	uketd_dc
spelling	my-ums-ep.418072024-12-04T07:16:56Z Genetic algorithm for control and optimisation of exothermic batch process 2013 Tan, Min Keng QA76.75-76.765 Computer software The aim of this research is to control and optimise the production of the desired product while minimising the waste production for an exothermic batch process. During the process, a large amount of heat is released rapidly when the reactants are mixed together. The exothermic behaviour causes the reaction to become unstable and consequently poses safety concern to the plant personnel. Commonly, dual-mode controller (DMC) is employed in the industries to control the process. However, this approach is not robust in dealing with sudden disturbance. Hence, various advanced control strategies have been introduced. In general, most of the studies use predictive approach to estimate the process behaviour and a slave controller, usually proportional-integral-derivative (PID), is employed to control the process based on the estimated plant behaviour. Nevertheless, these methods require huge batch of data for tuning its parameters. Therefore, genetic algorithm (GA) is proposed in this work since precise mathematical model is not required. Although the proposed genetic algorithm controller (GAC) is able to regulate the process temperature to the desired path, it does not limit the waste production effectively. As such, another approach, GA is proposed to optimise the productivity without referring to a predetermined profile, namely genetic algorithm optimiser (GAO). The results show that GiAO is able to improve the yield ratio from 0.77 to 0.97 or approximate 25.0 % as comparecd to the GAC. Further evaluations have shown that GA with predetermined fitness function is unable to cope with the environmental changes. As a result, improved multivariable genetic algorithm (IMGA) with adaptable fitness function ability is introduced in this work. Results show that the IMGA is able to improve the yield ratio from 0.25 to 0.79 as compared to GAO in handling the p. rameter variant conditions. 2013 Thesis https://eprints.ums.edu.my/id/eprint/41807/ https://eprints.ums.edu.my/id/eprint/41807/1/24%20PAGES.pdf text en public https://eprints.ums.edu.my/id/eprint/41807/2/FULLTEXT.pdf text en validuser masters Universiti Malaysia Sabah School of Engineering And Information Technology
institution	Universiti Malaysia Sabah
collection	UMS Institutional Repository
language	English English
topic	QA76.75-76.765 Computer software
spellingShingle	QA76.75-76.765 Computer software Tan, Min Keng Genetic algorithm for control and optimisation of exothermic batch process
description	The aim of this research is to control and optimise the production of the desired product while minimising the waste production for an exothermic batch process. During the process, a large amount of heat is released rapidly when the reactants are mixed together. The exothermic behaviour causes the reaction to become unstable and consequently poses safety concern to the plant personnel. Commonly, dual-mode controller (DMC) is employed in the industries to control the process. However, this approach is not robust in dealing with sudden disturbance. Hence, various advanced control strategies have been introduced. In general, most of the studies use predictive approach to estimate the process behaviour and a slave controller, usually proportional-integral-derivative (PID), is employed to control the process based on the estimated plant behaviour. Nevertheless, these methods require huge batch of data for tuning its parameters. Therefore, genetic algorithm (GA) is proposed in this work since precise mathematical model is not required. Although the proposed genetic algorithm controller (GAC) is able to regulate the process temperature to the desired path, it does not limit the waste production effectively. As such, another approach, GA is proposed to optimise the productivity without referring to a predetermined profile, namely genetic algorithm optimiser (GAO). The results show that GiAO is able to improve the yield ratio from 0.77 to 0.97 or approximate 25.0 % as comparecd to the GAC. Further evaluations have shown that GA with predetermined fitness function is unable to cope with the environmental changes. As a result, improved multivariable genetic algorithm (IMGA) with adaptable fitness function ability is introduced in this work. Results show that the IMGA is able to improve the yield ratio from 0.25 to 0.79 as compared to GAO in handling the p. rameter variant conditions.
format	Thesis
qualification_level	Master's degree
author	Tan, Min Keng
author_facet	Tan, Min Keng
author_sort	Tan, Min Keng
title	Genetic algorithm for control and optimisation of exothermic batch process
title_short	Genetic algorithm for control and optimisation of exothermic batch process
title_full	Genetic algorithm for control and optimisation of exothermic batch process
title_fullStr	Genetic algorithm for control and optimisation of exothermic batch process
title_full_unstemmed	Genetic algorithm for control and optimisation of exothermic batch process
title_sort	genetic algorithm for control and optimisation of exothermic batch process
granting_institution	Universiti Malaysia Sabah
granting_department	School of Engineering And Information Technology
publishDate	2013
url	https://eprints.ums.edu.my/id/eprint/41807/1/24%20PAGES.pdf https://eprints.ums.edu.my/id/eprint/41807/2/FULLTEXT.pdf
_version_	1818611431610777600

Genetic algorithm for control and optimisation of exothermic batch process

Similar Items