{"title":"基于进化方向差分进化算法的冷连轧轧制规程鲁棒多目标优化","authors":"Yong Li , Lei Fang","doi":"10.1016/S1006-706X(17)30119-X","DOIUrl":null,"url":null,"abstract":"<div><p>According to the actual requirements, profile and rolling energy consumption are selected as objective functions of rolling schedule optimization for tandem cold rolling. Because of mechanical wear, roll diameter has some uncertainty during the rolling process, ignoring which will cause poor robustness of rolling schedule. In order to solve this problem, a robust multi-objective optimization model of rolling schedule for tandem cold rolling was established. A differential evolution algorithm based on the evolutionary direction was proposed. The algorithm calculated the horizontal angle of the vector, which was used to choose mutation vector. The chosen vector contained converging direction and it changed the random mutation operation in differential evolution algorithm. Efficiency of the proposed algorithm was verified by two benchmarks. Meanwhile, in order to ensure that delivery thicknesses have descending order like actual rolling schedule during evolution, a modified Latin Hypercube Sampling process was proposed. Finally, the proposed algorithm was applied to the model above. Results showed that profile was improved and rolling energy consumption was reduced compared with the actual rolling schedule. Meanwhile, robustness of solutions was ensured.</p></div>","PeriodicalId":64470,"journal":{"name":"Journal of Iron and Steel Research(International)","volume":"24 8","pages":"Pages 795-802"},"PeriodicalIF":3.1000,"publicationDate":"2017-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1016/S1006-706X(17)30119-X","citationCount":"10","resultStr":"{\"title\":\"Robust multi-objective optimization of rolling schedule for tandem cold rolling based on evolutionary direction differential evolution algorithm\",\"authors\":\"Yong Li , Lei Fang\",\"doi\":\"10.1016/S1006-706X(17)30119-X\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>According to the actual requirements, profile and rolling energy consumption are selected as objective functions of rolling schedule optimization for tandem cold rolling. Because of mechanical wear, roll diameter has some uncertainty during the rolling process, ignoring which will cause poor robustness of rolling schedule. In order to solve this problem, a robust multi-objective optimization model of rolling schedule for tandem cold rolling was established. A differential evolution algorithm based on the evolutionary direction was proposed. The algorithm calculated the horizontal angle of the vector, which was used to choose mutation vector. The chosen vector contained converging direction and it changed the random mutation operation in differential evolution algorithm. Efficiency of the proposed algorithm was verified by two benchmarks. Meanwhile, in order to ensure that delivery thicknesses have descending order like actual rolling schedule during evolution, a modified Latin Hypercube Sampling process was proposed. Finally, the proposed algorithm was applied to the model above. Results showed that profile was improved and rolling energy consumption was reduced compared with the actual rolling schedule. Meanwhile, robustness of solutions was ensured.</p></div>\",\"PeriodicalId\":64470,\"journal\":{\"name\":\"Journal of Iron and Steel Research(International)\",\"volume\":\"24 8\",\"pages\":\"Pages 795-802\"},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2017-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1016/S1006-706X(17)30119-X\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Iron and Steel Research(International)\",\"FirstCategoryId\":\"1087\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1006706X1730119X\",\"RegionNum\":2,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"METALLURGY & METALLURGICAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Iron and Steel Research(International)","FirstCategoryId":"1087","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1006706X1730119X","RegionNum":2,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}
Robust multi-objective optimization of rolling schedule for tandem cold rolling based on evolutionary direction differential evolution algorithm
According to the actual requirements, profile and rolling energy consumption are selected as objective functions of rolling schedule optimization for tandem cold rolling. Because of mechanical wear, roll diameter has some uncertainty during the rolling process, ignoring which will cause poor robustness of rolling schedule. In order to solve this problem, a robust multi-objective optimization model of rolling schedule for tandem cold rolling was established. A differential evolution algorithm based on the evolutionary direction was proposed. The algorithm calculated the horizontal angle of the vector, which was used to choose mutation vector. The chosen vector contained converging direction and it changed the random mutation operation in differential evolution algorithm. Efficiency of the proposed algorithm was verified by two benchmarks. Meanwhile, in order to ensure that delivery thicknesses have descending order like actual rolling schedule during evolution, a modified Latin Hypercube Sampling process was proposed. Finally, the proposed algorithm was applied to the model above. Results showed that profile was improved and rolling energy consumption was reduced compared with the actual rolling schedule. Meanwhile, robustness of solutions was ensured.