{"title":"Hybrid evolutionary algorithm for maximizing medical equipment supply during pandemic✰","authors":"C. D James , Sandeep Mondal","doi":"10.1016/j.sasc.2025.200275","DOIUrl":null,"url":null,"abstract":"<div><div>Inadequate capacity and delayed delivery of electronic life support equipment was a major impediment in saving human lives during COVID-19. Capital intensive mass customised electronics and semiconductor manufacturing formed critical raw material for the same. Targeted efficiency achievement fails when variety and flexibility are prioritised in chip production. Digital manufacturing involves artificial intelligence for planning and autonomous execution with robotic hi-tech machines. However, large number of controlling factors fluctuate at extreme levels in the manufacturing environment leading to capacity shrinkage risk of these machines. In this paper, we make use of a simulation-based model to demonstrate solution to this problem because experimental setups involve high cost and delivery risks.</div><div>Firstly, we identified thirty-one factors that affect hi-tech machine efficiency. Of these, thirteen factors were shortlisted through confidential voting by the industry experts to mirror the actual challenges during pandemic. We developed a model, and simulated problem scenarios for shortlisted factors at three levels. Design of experiments was performed using Taguchi based orthogonal arrays. Signal to noise ratios were used to determine the main effects and robust combination of factor levels for high efficiency. Significant factors were identified from ANOVA for variance-reduction based robustness design.</div><div>A better solution was created using a learning-based fruit fly optimization algorithm and further using a hybrid fruit fly grasshopper leap optimization. This algorithm successfully supported the high customization scenario for manufacturing efficiency during pandemic for any pre-set parameters by accelerating learning cycles. In addition, a multifactor particle swarm optimization was also performed for managing dynamic changes in all 31 factors together and the results were compared with previous techniques. The managerial implications and conclusion are explained for the benefit of the electronics industry and academia.</div></div>","PeriodicalId":101205,"journal":{"name":"Systems and Soft Computing","volume":"7 ","pages":"Article 200275"},"PeriodicalIF":0.0000,"publicationDate":"2025-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Systems and Soft Computing","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2772941925000936","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
Inadequate capacity and delayed delivery of electronic life support equipment was a major impediment in saving human lives during COVID-19. Capital intensive mass customised electronics and semiconductor manufacturing formed critical raw material for the same. Targeted efficiency achievement fails when variety and flexibility are prioritised in chip production. Digital manufacturing involves artificial intelligence for planning and autonomous execution with robotic hi-tech machines. However, large number of controlling factors fluctuate at extreme levels in the manufacturing environment leading to capacity shrinkage risk of these machines. In this paper, we make use of a simulation-based model to demonstrate solution to this problem because experimental setups involve high cost and delivery risks.
Firstly, we identified thirty-one factors that affect hi-tech machine efficiency. Of these, thirteen factors were shortlisted through confidential voting by the industry experts to mirror the actual challenges during pandemic. We developed a model, and simulated problem scenarios for shortlisted factors at three levels. Design of experiments was performed using Taguchi based orthogonal arrays. Signal to noise ratios were used to determine the main effects and robust combination of factor levels for high efficiency. Significant factors were identified from ANOVA for variance-reduction based robustness design.
A better solution was created using a learning-based fruit fly optimization algorithm and further using a hybrid fruit fly grasshopper leap optimization. This algorithm successfully supported the high customization scenario for manufacturing efficiency during pandemic for any pre-set parameters by accelerating learning cycles. In addition, a multifactor particle swarm optimization was also performed for managing dynamic changes in all 31 factors together and the results were compared with previous techniques. The managerial implications and conclusion are explained for the benefit of the electronics industry and academia.