Enhanced multi-objective optimization of a microchannel heat sink through evolutionary algorithm coupled with multiple surrogate models

Afzal Husain, Kwang Yong Kim

Research output: Contribution to journalArticle

62 Citations (Scopus)

Abstract

A liquid flow microchannel heat sink has been optimized with the help of three-dimensional numerical analysis and multiple surrogate methods. Two objective functions, thermal resistance and pumping power have been selected to assess the performance of the microchannel heat sink. The design variables related to the width of the microchannel at the top and bottom, depth of the microchannel, and width of fin, which contribute to objective functions, have been identified and a three-level full factorial design was selected to exploit the design space. The numerical solutions obtained at these design points were utilized to construct surrogate models, namely Response Surface Approximations, Kriging and Radial Basis Neural Network. A hybrid multi-objective evolutionary algorithm coupled with surrogate models is applied to find out global Pareto-optimal solutions. The accuracy of the surrogate models has been discussed in view of their predictions and trade-off analysis was performed in view of conflicting nature of the two objectives. The Pareto-optimal sensitivity of the design variables has been found out to economically compromise with the design variables. The application of the multiple surrogate methods not only improves quality of multi-objective optimization but also gives the feedback of the fidelity of the optimization model.

Original languageEnglish
Pages (from-to)1683-1691
Number of pages9
JournalApplied Thermal Engineering
Volume30
Issue number13
DOIs
Publication statusPublished - Sep 2010

Fingerprint

Heat sinks
Multiobjective optimization
Microchannels
Evolutionary algorithms
Heat resistance
Numerical analysis
Neural networks
Feedback
Liquids

Keywords

  • Electronic cooling
  • Evolutionary algorithm
  • Multi-objective optimization
  • Multiple surrogate analysis
  • Numerical simulation

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Industrial and Manufacturing Engineering

Cite this

Enhanced multi-objective optimization of a microchannel heat sink through evolutionary algorithm coupled with multiple surrogate models. / Husain, Afzal; Kim, Kwang Yong.

In: Applied Thermal Engineering, Vol. 30, No. 13, 09.2010, p. 1683-1691.

Research output: Contribution to journalArticle

@article{e43f8871cb874a6fa2f770015a84398e,
title = "Enhanced multi-objective optimization of a microchannel heat sink through evolutionary algorithm coupled with multiple surrogate models",
abstract = "A liquid flow microchannel heat sink has been optimized with the help of three-dimensional numerical analysis and multiple surrogate methods. Two objective functions, thermal resistance and pumping power have been selected to assess the performance of the microchannel heat sink. The design variables related to the width of the microchannel at the top and bottom, depth of the microchannel, and width of fin, which contribute to objective functions, have been identified and a three-level full factorial design was selected to exploit the design space. The numerical solutions obtained at these design points were utilized to construct surrogate models, namely Response Surface Approximations, Kriging and Radial Basis Neural Network. A hybrid multi-objective evolutionary algorithm coupled with surrogate models is applied to find out global Pareto-optimal solutions. The accuracy of the surrogate models has been discussed in view of their predictions and trade-off analysis was performed in view of conflicting nature of the two objectives. The Pareto-optimal sensitivity of the design variables has been found out to economically compromise with the design variables. The application of the multiple surrogate methods not only improves quality of multi-objective optimization but also gives the feedback of the fidelity of the optimization model.",
keywords = "Electronic cooling, Evolutionary algorithm, Multi-objective optimization, Multiple surrogate analysis, Numerical simulation",
author = "Afzal Husain and Kim, {Kwang Yong}",
year = "2010",
month = "9",
doi = "10.1016/j.applthermaleng.2010.03.027",
language = "English",
volume = "30",
pages = "1683--1691",
journal = "Applied Thermal Engineering",
issn = "1359-4311",
publisher = "Elsevier Limited",
number = "13",

}

TY - JOUR

T1 - Enhanced multi-objective optimization of a microchannel heat sink through evolutionary algorithm coupled with multiple surrogate models

AU - Husain, Afzal

AU - Kim, Kwang Yong

PY - 2010/9

Y1 - 2010/9

N2 - A liquid flow microchannel heat sink has been optimized with the help of three-dimensional numerical analysis and multiple surrogate methods. Two objective functions, thermal resistance and pumping power have been selected to assess the performance of the microchannel heat sink. The design variables related to the width of the microchannel at the top and bottom, depth of the microchannel, and width of fin, which contribute to objective functions, have been identified and a three-level full factorial design was selected to exploit the design space. The numerical solutions obtained at these design points were utilized to construct surrogate models, namely Response Surface Approximations, Kriging and Radial Basis Neural Network. A hybrid multi-objective evolutionary algorithm coupled with surrogate models is applied to find out global Pareto-optimal solutions. The accuracy of the surrogate models has been discussed in view of their predictions and trade-off analysis was performed in view of conflicting nature of the two objectives. The Pareto-optimal sensitivity of the design variables has been found out to economically compromise with the design variables. The application of the multiple surrogate methods not only improves quality of multi-objective optimization but also gives the feedback of the fidelity of the optimization model.

AB - A liquid flow microchannel heat sink has been optimized with the help of three-dimensional numerical analysis and multiple surrogate methods. Two objective functions, thermal resistance and pumping power have been selected to assess the performance of the microchannel heat sink. The design variables related to the width of the microchannel at the top and bottom, depth of the microchannel, and width of fin, which contribute to objective functions, have been identified and a three-level full factorial design was selected to exploit the design space. The numerical solutions obtained at these design points were utilized to construct surrogate models, namely Response Surface Approximations, Kriging and Radial Basis Neural Network. A hybrid multi-objective evolutionary algorithm coupled with surrogate models is applied to find out global Pareto-optimal solutions. The accuracy of the surrogate models has been discussed in view of their predictions and trade-off analysis was performed in view of conflicting nature of the two objectives. The Pareto-optimal sensitivity of the design variables has been found out to economically compromise with the design variables. The application of the multiple surrogate methods not only improves quality of multi-objective optimization but also gives the feedback of the fidelity of the optimization model.

KW - Electronic cooling

KW - Evolutionary algorithm

KW - Multi-objective optimization

KW - Multiple surrogate analysis

KW - Numerical simulation

UR - http://www.scopus.com/inward/record.url?scp=77955272546&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955272546&partnerID=8YFLogxK

U2 - 10.1016/j.applthermaleng.2010.03.027

DO - 10.1016/j.applthermaleng.2010.03.027

M3 - Article

VL - 30

SP - 1683

EP - 1691

JO - Applied Thermal Engineering

JF - Applied Thermal Engineering

SN - 1359-4311

IS - 13

ER -