WeldNet: An ultra fast measurement algorithm for precision laser stripe extraction in robotic welding

IF 5.2 2区工程技术 Q1 ENGINEERING, MULTIDISCIPLINARY

Measurement Pub Date : 2024-11-19 DOI:10.1016/j.measurement.2024.116219

Chuyi Dai , Congcong Wang , Zhixuan Zhou , Zhen Wang , Ding Liu

{"title":"WeldNet: An ultra fast measurement algorithm for precision laser stripe extraction in robotic welding","authors":"Chuyi Dai , Congcong Wang , Zhixuan Zhou , Zhen Wang , Ding Liu","doi":"10.1016/j.measurement.2024.116219","DOIUrl":null,"url":null,"abstract":"<div><div>The integration of laser vision sensors in robotic welding improves seam tracking accuracy, but welding noise poses significant challenges. Our research introduces WeldNet, enhances laser stripe extraction, significantly outperforming traditional and deep neural network (DNN) solutions in efficiency and measurement precision. WeldNet comprises lightweight modules for optimal feature extraction, including Multi-Part Channel Convolution (MPC) blocks, Parallel Shift Multilayer Perceptrons (PS-MLP), and Serial Shift MLP (SS-MLP). A specially designed data augmentation strategy is also integrated to address the complex noise encountered in robotic welding. Experimental results demonstrate WeldNet’s effectiveness in reducing welding noise interference, achieving a real-time processing speed of 145 FPS on RTX 2080 Ti GPU, approximately 5x faster than existing state-of-the-art methods. With a Dice coefficient of 87.52% and an IoU value of 77.82%, WeldNet not only enhances operational efficiency but also markedly improves precision in industrial robotic welding.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"242 ","pages":"Article 116219"},"PeriodicalIF":5.2000,"publicationDate":"2024-11-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Measurement","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0263224124021043","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, MULTIDISCIPLINARY","Score":null,"Total":0}

引用次数: 0

Abstract

The integration of laser vision sensors in robotic welding improves seam tracking accuracy, but welding noise poses significant challenges. Our research introduces WeldNet, enhances laser stripe extraction, significantly outperforming traditional and deep neural network (DNN) solutions in efficiency and measurement precision. WeldNet comprises lightweight modules for optimal feature extraction, including Multi-Part Channel Convolution (MPC) blocks, Parallel Shift Multilayer Perceptrons (PS-MLP), and Serial Shift MLP (SS-MLP). A specially designed data augmentation strategy is also integrated to address the complex noise encountered in robotic welding. Experimental results demonstrate WeldNet’s effectiveness in reducing welding noise interference, achieving a real-time processing speed of 145 FPS on RTX 2080 Ti GPU, approximately 5x faster than existing state-of-the-art methods. With a Dice coefficient of 87.52% and an IoU value of 77.82%, WeldNet not only enhances operational efficiency but also markedly improves precision in industrial robotic welding.

查看原文本刊更多论文

求助全文

约1分钟内获得全文求助全文

来源期刊

Measurement 工程技术-工程：综合

CiteScore

10.20

自引率

12.50%

发文量

1589

审稿时长

12.1 months

期刊介绍： Contributions are invited on novel achievements in all fields of measurement and instrumentation science and technology. Authors are encouraged to submit novel material, whose ultimate goal is an advancement in the state of the art of: measurement and metrology fundamentals, sensors, measurement instruments, measurement and estimation techniques, measurement data processing and fusion algorithms, evaluation procedures and methodologies for plants and industrial processes, performance analysis of systems, processes and algorithms, mathematical models for measurement-oriented purposes, distributed measurement systems in a connected world.