用神经网络预测注塑成型部件的纤维取向及其几何影响

IF 2.3 3区 材料科学 Q3 MATERIALS SCIENCE, COMPOSITES Journal of Composite Materials Pub Date : 2024-04-15 DOI:10.1177/00219983241248216
Till Hermann, Dariusz Niedziela, Diyora Salimova, Timo Schweiger
{"title":"用神经网络预测注塑成型部件的纤维取向及其几何影响","authors":"Till Hermann, Dariusz Niedziela, Diyora Salimova, Timo Schweiger","doi":"10.1177/00219983241248216","DOIUrl":null,"url":null,"abstract":"The injection molding simulation of short fiber reinforced plastics (SFRP) is time consuming. However, until now it is necessary for predicting the local fiber orientation, to optimize the molding process and to predict the mechanical behavior of the material. This research presents the capabilities of artificial neural networks (NN) in predicting fiber orientation tensor (FOT) during injection molding processes, with a focus on enhancing computational efficiency compared to traditional simulation methods. Three NN architectures are compared based on simulated injection molded plates, with the goal of predicting the effect of the plate geometry on the local fiber orientation. Results indicate that NN outperform the baseline assumption of aligned fibers and demonstrate significant potential for accurate FOT prediction. The computational efficiency of NN, especially during the prediction phase, showcases a reduction in processing time by a factor of 10<jats:sup>4</jats:sup> compared to traditional simulation methods. This research lays a foundation for further exploration into the feasibility of NN in partly replacing time-consuming simulations for practical applications in injection molding processes.","PeriodicalId":15489,"journal":{"name":"Journal of Composite Materials","volume":null,"pages":null},"PeriodicalIF":2.3000,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Predicting the fiber orientation of injection molded components and the geometry influence with neural networks\",\"authors\":\"Till Hermann, Dariusz Niedziela, Diyora Salimova, Timo Schweiger\",\"doi\":\"10.1177/00219983241248216\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"The injection molding simulation of short fiber reinforced plastics (SFRP) is time consuming. However, until now it is necessary for predicting the local fiber orientation, to optimize the molding process and to predict the mechanical behavior of the material. This research presents the capabilities of artificial neural networks (NN) in predicting fiber orientation tensor (FOT) during injection molding processes, with a focus on enhancing computational efficiency compared to traditional simulation methods. Three NN architectures are compared based on simulated injection molded plates, with the goal of predicting the effect of the plate geometry on the local fiber orientation. Results indicate that NN outperform the baseline assumption of aligned fibers and demonstrate significant potential for accurate FOT prediction. The computational efficiency of NN, especially during the prediction phase, showcases a reduction in processing time by a factor of 10<jats:sup>4</jats:sup> compared to traditional simulation methods. This research lays a foundation for further exploration into the feasibility of NN in partly replacing time-consuming simulations for practical applications in injection molding processes.\",\"PeriodicalId\":15489,\"journal\":{\"name\":\"Journal of Composite Materials\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":2.3000,\"publicationDate\":\"2024-04-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Composite Materials\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.1177/00219983241248216\",\"RegionNum\":3,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MATERIALS SCIENCE, COMPOSITES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Composite Materials","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.1177/00219983241248216","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MATERIALS SCIENCE, COMPOSITES","Score":null,"Total":0}
引用次数: 0

摘要

短纤维增强塑料(SFRP)的注塑成型模拟非常耗时。然而,迄今为止,它对于预测局部纤维取向、优化成型工艺和预测材料的机械性能是非常必要的。本研究介绍了人工神经网络(NN)在注塑成型过程中预测纤维取向张量(FOT)的能力,重点是与传统模拟方法相比提高计算效率。以模拟注塑成型板为基础,比较了三种 NN 架构,目的是预测板的几何形状对局部纤维取向的影响。结果表明,NN 优于对齐纤维的基线假设,并展示了准确预测 FOT 的巨大潜力。NN 的计算效率,尤其是在预测阶段,与传统模拟方法相比,减少了 104 倍的处理时间。这项研究为进一步探索 NN 在注塑成型工艺实际应用中部分取代耗时模拟的可行性奠定了基础。
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
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
Predicting the fiber orientation of injection molded components and the geometry influence with neural networks
The injection molding simulation of short fiber reinforced plastics (SFRP) is time consuming. However, until now it is necessary for predicting the local fiber orientation, to optimize the molding process and to predict the mechanical behavior of the material. This research presents the capabilities of artificial neural networks (NN) in predicting fiber orientation tensor (FOT) during injection molding processes, with a focus on enhancing computational efficiency compared to traditional simulation methods. Three NN architectures are compared based on simulated injection molded plates, with the goal of predicting the effect of the plate geometry on the local fiber orientation. Results indicate that NN outperform the baseline assumption of aligned fibers and demonstrate significant potential for accurate FOT prediction. The computational efficiency of NN, especially during the prediction phase, showcases a reduction in processing time by a factor of 104 compared to traditional simulation methods. This research lays a foundation for further exploration into the feasibility of NN in partly replacing time-consuming simulations for practical applications in injection molding processes.
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
Journal of Composite Materials
Journal of Composite Materials 工程技术-材料科学:复合
CiteScore
5.40
自引率
6.90%
发文量
274
审稿时长
6.8 months
期刊介绍: Consistently ranked in the top 10 of the Thomson Scientific JCR, the Journal of Composite Materials publishes peer reviewed, original research papers from internationally renowned composite materials specialists from industry, universities and research organizations, featuring new advances in materials, processing, design, analysis, testing, performance and applications. This journal is a member of the Committee on Publication Ethics (COPE).
期刊最新文献
Micromechanics-based multi-scale framework with strain-rate effects for the simulation of ballistic impact on composite laminates Recycling catfish bone for additive manufacturing of silicone composite structures Mechanical performances of unsatured polyester composite reinforced by OleaEuropea var. Sylvestris fibers: Characterization, modeling and optimization of fiber textural properties Elastic properties identification of a bio-based material in tertiary packaging: Tools and methods development Parametric process optimisation of automated fibre placement (AFP) based AS4/APC-2 composites for mode I and mode II fracture toughness
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1