DEVELOPMENT OF A MULTI-OBJECTIVE OPTIMIZATION FRAMEWORK FOR INDUSTRIAL PROCESSES
Multi objective (MO) optimization is an emerging field which is increasingly being applied in many engineering-based industries globally. Whilst MO optimization problems have been actively researched for the past years, industrial-scale problems involving objectives more than two are rarely studi...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2013
|
| Subjects: | |
| Online Access: | http://utpedia.utp.edu.my/22105/1/2013%20-CHEMICAL%20-%20DEVELOPMENT%20OF%20A%20MULTI-OBJECTIVE%20OPTIMIZATION%20FRAMEWORK%20FOR%20INDUSTRIAL%20PROCESSES%20-%20TIMOTHY%20GANESAN.pdf http://utpedia.utp.edu.my/22105/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Multi objective (MO) optimization is an emerging field which is increasingly being
applied in many engineering-based industries globally. Whilst MO optimization
problems have been actively researched for the past years, industrial-scale problems
involving objectives more than two are rarely studied although frequently
encountered. Thus, this work focuses on industrial MO problems encountered in
process engineering with more than two objectives.
This work investigates the performance and solution characteristics of
metaheuristic algorithms when applied to such problems. In addition, the solution
characteristics produced by these algorithms were also analysed and its influence on
the algorithmic performance was ascertained. The knowledge obtained from the
above explorations was then used to construct a novel framework for solving these
problems efficiently. The proposed framework is introduced as the 'surgery
framework (SF)' since its prime functionality is to dissect the algorithm and add
certain mechanisms into it. The SF introduced here comprises of the measuring the
solutions of multiple algorithms as well as modifying them by adding certain
mechanisms into chosen algorithms.
The SF was then used to solve four real-world industrial MO process optimization
problems. The industrial problems are as follows; Application I: MO Optimization of
Extraction Process of Bioactive Compounds from Gardenia, Application II: MO
Optimization of Bioethanol Production during Cold Enzyme Starch Hydrolysis,
Application Ill: MO Optimization of Synthesis Gas for Production Process and
Application IV: MO Optimization of Pre-treatment Strategy for Bioethanol
Production from Rice Husk.
The SF applies four metaheuristic algorithms such as differential evolution (DE),
genetic algorithm (GA), gravitational search algorithm (GSA) and particle swarm
optimization (PSO) to solve each of the industrial MO process optimization problems. |
|---|