Wenze Ren , Keyi Huang , Jiahui Feng , Yuxing Feng , Jinsong Lin , Jun Zheng
{"title":"一种基于激光视觉的机器人焊接相交曲线路径提取与跟踪方法","authors":"Wenze Ren , Keyi Huang , Jiahui Feng , Yuxing Feng , Jinsong Lin , Jun Zheng","doi":"10.1016/j.measurement.2025.119207","DOIUrl":null,"url":null,"abstract":"<div><div>With the continuous advancement of manufacturing, automated and intelligent welding technologies have seen increasingly widespread application across industrial fields. As a typical form of complex spatial curves, intersecting weld seams are widely used in the joining of pipelines, trusses, and other structural components. This paper proposes an extraction and real-time tracking method for intersecting weld seams based on a line laser vision sensor. First, a large–depth-of-field line laser vision sensor is employed to scan the workpiece. By combining the RANSAC algorithm with an adaptive genetic particle swarm optimization algorithm (GA-APSO), the weld seam curve is extracted with high accuracy. The extracted seam is then reconstructed using a NURBS curve, with parameter interpolation applied to ensure uniform robot welding motion. During the welding process, the sensor continuously scans the seam, and a proposed bidirectional sliding-window point extraction method enables fast and reliable identification of weld points under arc light and spatter interference. Together with a local curve correction algorithm, the welding trajectory is adjusted in real time, significantly improving weld precision. Experimental results show that the maximum deviation between the welding trajectory and the true seam is 0.83 mm, demonstrating strong potential for practical engineering applications.</div></div>","PeriodicalId":18349,"journal":{"name":"Measurement","volume":"258 ","pages":"Article 119207"},"PeriodicalIF":5.6000,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A novel laser vision-based robotic welding path extraction and tracking method for intersecting curves\",\"authors\":\"Wenze Ren , Keyi Huang , Jiahui Feng , Yuxing Feng , Jinsong Lin , Jun Zheng\",\"doi\":\"10.1016/j.measurement.2025.119207\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>With the continuous advancement of manufacturing, automated and intelligent welding technologies have seen increasingly widespread application across industrial fields. As a typical form of complex spatial curves, intersecting weld seams are widely used in the joining of pipelines, trusses, and other structural components. This paper proposes an extraction and real-time tracking method for intersecting weld seams based on a line laser vision sensor. First, a large–depth-of-field line laser vision sensor is employed to scan the workpiece. By combining the RANSAC algorithm with an adaptive genetic particle swarm optimization algorithm (GA-APSO), the weld seam curve is extracted with high accuracy. The extracted seam is then reconstructed using a NURBS curve, with parameter interpolation applied to ensure uniform robot welding motion. During the welding process, the sensor continuously scans the seam, and a proposed bidirectional sliding-window point extraction method enables fast and reliable identification of weld points under arc light and spatter interference. Together with a local curve correction algorithm, the welding trajectory is adjusted in real time, significantly improving weld precision. Experimental results show that the maximum deviation between the welding trajectory and the true seam is 0.83 mm, demonstrating strong potential for practical engineering applications.</div></div>\",\"PeriodicalId\":18349,\"journal\":{\"name\":\"Measurement\",\"volume\":\"258 \",\"pages\":\"Article 119207\"},\"PeriodicalIF\":5.6000,\"publicationDate\":\"2025-10-01\",\"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/S0263224125025667\",\"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}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Measurement","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0263224125025667","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}
A novel laser vision-based robotic welding path extraction and tracking method for intersecting curves
With the continuous advancement of manufacturing, automated and intelligent welding technologies have seen increasingly widespread application across industrial fields. As a typical form of complex spatial curves, intersecting weld seams are widely used in the joining of pipelines, trusses, and other structural components. This paper proposes an extraction and real-time tracking method for intersecting weld seams based on a line laser vision sensor. First, a large–depth-of-field line laser vision sensor is employed to scan the workpiece. By combining the RANSAC algorithm with an adaptive genetic particle swarm optimization algorithm (GA-APSO), the weld seam curve is extracted with high accuracy. The extracted seam is then reconstructed using a NURBS curve, with parameter interpolation applied to ensure uniform robot welding motion. During the welding process, the sensor continuously scans the seam, and a proposed bidirectional sliding-window point extraction method enables fast and reliable identification of weld points under arc light and spatter interference. Together with a local curve correction algorithm, the welding trajectory is adjusted in real time, significantly improving weld precision. Experimental results show that the maximum deviation between the welding trajectory and the true seam is 0.83 mm, demonstrating strong potential for practical engineering applications.
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.