A multi-objective evolutionary algorithm-based decision support system: A case study on job-shop scheduling in manufacturing

2015 Annual IEEE Systems Conference (SysCon) Proceedings Pub Date : 2015-04-13 DOI:10.1109/SYSCON.2015.7116747

Choo Jun Tan, Samer Hanoun, C. Lim

{"title":"A multi-objective evolutionary algorithm-based decision support system: A case study on job-shop scheduling in manufacturing","authors":"Choo Jun Tan, Samer Hanoun, C. Lim","doi":"10.1109/SYSCON.2015.7116747","DOIUrl":null,"url":null,"abstract":"In this paper, an evolutionary algorithm is used for developing a decision support tool to undertake multi-objective job-shop scheduling problems. A modified micro genetic algorithm (MmGA) is adopted to provide optimal solutions according to the Pareto optimality principle in solving multi-objective optimisation problems. MmGA operates with a very small population size to explore a wide search space of function evaluations and to improve the convergence score towards the true Pareto optimal front. To evaluate the effectiveness of the MmGA-based decision support tool, a multi-objective job-shop scheduling problem with actual information from a manufacturing company is deployed. The statistical bootstrap method is used to evaluate the experimental results, and compared with those from the enumeration method. The outcome indicates that the decision support tool is able to achieve those optimal solutions as generated by the enumeration method. In addition, the proposed decision support tool has advantage of achieving the results within a fraction of the time.","PeriodicalId":251318,"journal":{"name":"2015 Annual IEEE Systems Conference (SysCon) Proceedings","volume":"19 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2015-04-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"8","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2015 Annual IEEE Systems Conference (SysCon) Proceedings","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/SYSCON.2015.7116747","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 8

Abstract

In this paper, an evolutionary algorithm is used for developing a decision support tool to undertake multi-objective job-shop scheduling problems. A modified micro genetic algorithm (MmGA) is adopted to provide optimal solutions according to the Pareto optimality principle in solving multi-objective optimisation problems. MmGA operates with a very small population size to explore a wide search space of function evaluations and to improve the convergence score towards the true Pareto optimal front. To evaluate the effectiveness of the MmGA-based decision support tool, a multi-objective job-shop scheduling problem with actual information from a manufacturing company is deployed. The statistical bootstrap method is used to evaluate the experimental results, and compared with those from the enumeration method. The outcome indicates that the decision support tool is able to achieve those optimal solutions as generated by the enumeration method. In addition, the proposed decision support tool has advantage of achieving the results within a fraction of the time.

查看原文本刊更多论文

基于进化算法的多目标决策支持系统——以制造业作业车间调度为例

本文采用进化算法开发多目标作业车间调度问题的决策支持工具。在求解多目标优化问题时，采用一种改进的微遗传算法(MmGA)，根据Pareto最优原理给出最优解。MmGA在很小的种群规模下运行，以探索更大的函数评估搜索空间，并提高向真帕累托最优前沿的收敛得分。为了评估基于mmga的决策支持工具的有效性，应用了一个多目标作业车间调度问题，该问题具有制造企业的实际信息。采用统计自举法对实验结果进行了评价，并与枚举法进行了比较。结果表明，决策支持工具能够实现由枚举方法生成的最优解。此外，所提出的决策支持工具具有在短时间内实现结果的优点。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

2015 Annual IEEE Systems Conference (SysCon) Proceedings

自引率

0.00%

发文量