{"title":"Research on Visual Detection Method of Laser Welding Seam","authors":"Binyu Wang, Wusheng Chou","doi":"10.1109/CISCE58541.2023.10142667","DOIUrl":null,"url":null,"abstract":"Weld defects produced by welding will destroy the quality of products. The visual detection method of weld seam using artificial neural network has been applied in industry, but few researchers have established a method to measure the shape of weld seam. In this paper, a feasible scheme based on image processing and artificial neural network is proposed, which not only detects the location of weld defects, but also measures the geometric dimensions of welds. The effectiveness of the method was verified by testing on the self-built dataset and the average accuracy of the size measurement reached 95.9%.","PeriodicalId":145263,"journal":{"name":"2023 5th International Conference on Communications, Information System and Computer Engineering (CISCE)","volume":" 18","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2023 5th International Conference on Communications, Information System and Computer Engineering (CISCE)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/CISCE58541.2023.10142667","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
Weld defects produced by welding will destroy the quality of products. The visual detection method of weld seam using artificial neural network has been applied in industry, but few researchers have established a method to measure the shape of weld seam. In this paper, a feasible scheme based on image processing and artificial neural network is proposed, which not only detects the location of weld defects, but also measures the geometric dimensions of welds. The effectiveness of the method was verified by testing on the self-built dataset and the average accuracy of the size measurement reached 95.9%.