D. Görick , L. Larsen , M. Engelschall , A. Schuster
{"title":"Quality Prediction of Continuous Ultrasonic Welded Seams of High-Performance Thermoplastic Composites by means of Artificial Intelligence","authors":"D. Görick , L. Larsen , M. Engelschall , A. Schuster","doi":"10.1016/j.promfg.2021.10.017","DOIUrl":null,"url":null,"abstract":"<div><p>Thermoplastic composites (TCs) are a famous choice when it comes to high performance designs for industrial applications. Since the growing demand on the use of this material, it is important to be able to evaluate suitable processing technologies. One of those technologies is continuous ultrasonic welding (CUSW) which creates continuous joints, also called seams, between two or more TCs parts. In CUSW mechanical oscillations are applied to the material and result in melting and connecting of the welding parts.</p><p>The approach to predict joint strength (qualities) of continuous ultrasonic welded TCs by training different neural networks is investigated in this study. Quality class prediction around 72 % accuracy is achieved with a fully connected neural network. Concluding, quality prediction of welded TCs with the help of artificial intelligence seems to be a suitable approach for quality observation but more research could lead to more reliable neural networks for industrial applications.</p></div>","PeriodicalId":91947,"journal":{"name":"Procedia manufacturing","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2351978921002146/pdf?md5=40cac27e61437d063f733b91d0e4f424&pid=1-s2.0-S2351978921002146-main.pdf","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Procedia manufacturing","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2351978921002146","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Thermoplastic composites (TCs) are a famous choice when it comes to high performance designs for industrial applications. Since the growing demand on the use of this material, it is important to be able to evaluate suitable processing technologies. One of those technologies is continuous ultrasonic welding (CUSW) which creates continuous joints, also called seams, between two or more TCs parts. In CUSW mechanical oscillations are applied to the material and result in melting and connecting of the welding parts.
The approach to predict joint strength (qualities) of continuous ultrasonic welded TCs by training different neural networks is investigated in this study. Quality class prediction around 72 % accuracy is achieved with a fully connected neural network. Concluding, quality prediction of welded TCs with the help of artificial intelligence seems to be a suitable approach for quality observation but more research could lead to more reliable neural networks for industrial applications.