基于有限元和人工神经网络的钢板V形弯曲回弹工艺参数优化

IF 1.7 3区材料科学 Q2 METALLURGY & METALLURGICAL ENGINEERING

Ironmaking & Steelmaking Pub Date : 2023-05-18 DOI:10.1080/03019233.2023.2210465

Varsha M. Magar, N. Agrawal

{"title":"基于有限元和人工神经网络的钢板V形弯曲回弹工艺参数优化","authors":"Varsha M. Magar, N. Agrawal","doi":"10.1080/03019233.2023.2210465","DOIUrl":null,"url":null,"abstract":"ABSTRACT Spring back compensation is essential for accurate geometry of sheet metal components. In this paper the effect of process parameters namely sheet thickness, bend angle and tool travel rate on spring back in SS304 and C80 material sheets under V-bending is predicted by using finite element method and artificial neural network approaches. Total nine experiments were designed considering three process parameters, each with three levels, by using Taguchi`s L9 orthogonal array. The results obtained by ANN model are in good agreement with FEM model. This establish the robustness of ANN model for predicting spring back value and may be used an alternative to FEM model as the latter is more expensive and time consuming. The optimized value of sheet thickness, bend angle and tool travel rate are 2 mm, 80° and 6 mm ms–1 respectively for SS 304 material and 2 mm, 80° and 2 mm ms–1 for C80 material.","PeriodicalId":14753,"journal":{"name":"Ironmaking & Steelmaking","volume":"50 1","pages":"1352 - 1362"},"PeriodicalIF":1.7000,"publicationDate":"2023-05-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Process parameter optimization for spring back in steel grade sheet materials under V-bending using FEM and ANN approach\",\"authors\":\"Varsha M. Magar, N. Agrawal\",\"doi\":\"10.1080/03019233.2023.2210465\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"ABSTRACT Spring back compensation is essential for accurate geometry of sheet metal components. In this paper the effect of process parameters namely sheet thickness, bend angle and tool travel rate on spring back in SS304 and C80 material sheets under V-bending is predicted by using finite element method and artificial neural network approaches. Total nine experiments were designed considering three process parameters, each with three levels, by using Taguchi`s L9 orthogonal array. The results obtained by ANN model are in good agreement with FEM model. This establish the robustness of ANN model for predicting spring back value and may be used an alternative to FEM model as the latter is more expensive and time consuming. The optimized value of sheet thickness, bend angle and tool travel rate are 2 mm, 80° and 6 mm ms–1 respectively for SS 304 material and 2 mm, 80° and 2 mm ms–1 for C80 material.\",\"PeriodicalId\":14753,\"journal\":{\"name\":\"Ironmaking & Steelmaking\",\"volume\":\"50 1\",\"pages\":\"1352 - 1362\"},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2023-05-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Ironmaking & Steelmaking\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1080/03019233.2023.2210465\",\"RegionNum\":3,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"METALLURGY & METALLURGICAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Ironmaking & Steelmaking","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1080/03019233.2023.2210465","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}

引用次数: 0

摘要

摘要回弹补偿对于精确的钣金零件几何结构至关重要。本文采用有限元方法和人工神经网络方法，预测了SS304和C80材料板材V形弯曲时，板材厚度、弯曲角度和刀具行程速率等工艺参数对回弹的影响。利用田口L9正交阵列设计了总共九个实验，考虑了三个工艺参数，每个参数有三个水平。人工神经网络模型的计算结果与有限元模型吻合较好。这建立了用于预测回弹值的ANN模型的鲁棒性，并且可以用作FEM模型的替代方案，因为后者更昂贵且更耗时。对于SS 304材料，板材厚度、弯曲角度和刀具移动速率的优化值分别为2 mm、80°和6 mm ms–1，对于C80材料，则分别为2 mm。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Process parameter optimization for spring back in steel grade sheet materials under V-bending using FEM and ANN approach

ABSTRACT Spring back compensation is essential for accurate geometry of sheet metal components. In this paper the effect of process parameters namely sheet thickness, bend angle and tool travel rate on spring back in SS304 and C80 material sheets under V-bending is predicted by using finite element method and artificial neural network approaches. Total nine experiments were designed considering three process parameters, each with three levels, by using Taguchi`s L9 orthogonal array. The results obtained by ANN model are in good agreement with FEM model. This establish the robustness of ANN model for predicting spring back value and may be used an alternative to FEM model as the latter is more expensive and time consuming. The optimized value of sheet thickness, bend angle and tool travel rate are 2 mm, 80° and 6 mm ms–1 respectively for SS 304 material and 2 mm, 80° and 2 mm ms–1 for C80 material.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Ironmaking & Steelmaking 工程技术-冶金工程

CiteScore

3.70

自引率

9.50%

发文量

125

审稿时长

2.9 months

期刊介绍： Ironmaking & Steelmaking: Processes, Products and Applications monitors international technological advances in the industry with a strong element of engineering and product related material. First class refereed papers from the international iron and steel community cover all stages of the process, from ironmaking and its attendant technologies, through casting and steelmaking, to rolling, forming and delivery of the product, including monitoring, quality assurance and environmental issues. The journal also carries research profiles, features on technological and industry developments and expert reviews on major conferences.