|
胡为(1979—),男,辽宁沈阳人,教授,博士,主要研究方向为工业过程自动检测及控制,E-mail:hwspeedcn@163.com。 |
收稿日期: 2024-12-30
修回日期: 2025-01-08
录用日期: 2025-01-10
网络出版日期: 2025-12-25
基金资助
国家自然科学基金(52174366)
辽宁省教育厅科学基金(JYTMS20230277)
The weld seam feature tracking algorithm based on correlation filtering in FSW
Received date: 2024-12-30
Revised date: 2025-01-08
Accepted date: 2025-01-10
Online published: 2025-12-25
为提升搅拌摩擦焊(friction stir welding, FSW)在焊缝遮挡等干扰下的视觉跟踪精度,提出了一种基于人工特征的高效卷积算子(efficient convolution operators with hand-crafted features, ECO-HC)的焊缝特征跟踪算法。该算法采用传统图像处理技术进行初始焊缝特征点的检测,同时在ECO-HC算法的基础上设计了由相似性计算和峰值旁瓣比组成的双重置信度评估机制,增强算法对异常干扰的敏感度,并提出了一种基于曲线拟合的轨迹预测方法,实现对丢失目标的重定位。利用不同厚度的铝合金焊件进行实验,结果表明,焊缝跟踪系统的平均绝对误差能够控制在0.051 mm之内,完全满足焊缝跟踪的精度要求,也证明了所提算法的有效性。
胡为 , 李变童 , 姬书得 , 王元胜 . 基于相关滤波的FSW焊缝特征跟踪算法[J]. 沈阳航空航天大学学报, 2025 , 42(6) : 55 -62 . DOI: 10.3969/j.issn.2095-1248.2025.06.007
To improve visual tracking precision for friction stir welding under weld seam occlusion and other interference, a weld seam feature tracking algorithm based on the ECO-HC was proposed. A traditional image processing technology was employed to detect the initial weld seam feature point, while enhancing the sensitivity of the algorithm to abnormal disturbances by introducing a dual confidence assessment mechanism comprising similarity calculation and peak to sidelobe ratio on the basis of the ECO-HC algorithm. Additionally, a trajectory prediction method based on curve fitting was proposed to achieve the relocalization of lost target. Experiments were conducted on aluminum alloy weldments of varying thicknesses. The experimental results show that the mean absolute error of the weld seam tracking system proposed can be maintained within 0.051 mm, which fully meets the precision requirement for weld seam tracking and demonstrates the effectiveness of the algorithm proposed.
| [1] |
栾国红,关桥.高效、固相焊接新技术:搅拌摩擦焊[J].电焊机,2005,35(9):8-13.
|
| [2] |
马领航,李波,赵彦广,等.火箭贮箱焊接缺陷修复技术研究现状[J].电焊机,2023,53(3):31-45.
|
| [3] |
刘东豪.2219铝合金厚板FSW焊缝成形成性规律与工艺改进[D].长沙:中南大学,2023.
|
| [4] |
王子德.机器人搅拌摩擦焊系统集成及焊缝自动跟踪研究[D].哈尔滨:哈尔滨工业大学,2021.
|
| [6] |
朱承科.基于视觉引导的焊接机器人焊缝纠偏技术的研究[J].机械管理开发,2024,39(1):292-294.
|
| [7] |
|
| [8] |
冯冬冬.基于激光视觉的搅拌摩擦焊焊缝跟踪系统研究[D].济南:山东大学,2016.
|
| [9] |
申俊琦,刘晨帆,胡绳荪,等.基于改进型U-net神经网络的焊缝图像处理[J].天津大学学报(自然科学与工程技术版),2023,56(4):436-442.
|
| [10] |
杜健准,高向东,黎扬进,等.基于改进TLD算法的激光视觉传感型焊缝跟踪[J].激光技术,2021,45(3):292-297.
|
| [11] |
刘宜鑫.基于相关滤波的焊缝跟踪算法研究[D].成都:电子科技大学,2022.
|
| [12] |
|
| [13] |
刘刚阳,胡博,王宇庆.基于改进ECO-HC的目标跟踪方法[J].液晶与显示,2023,38(8):1118-1127.
|
| [14] |
|
| [15] |
陈涛.强噪声下的激光视觉焊缝跟踪系统研究[D].广州:华南理工大学,2020.
|
| [16] |
|
| [17] |
|
| [18] |
胡俊,朱庆保.基于动态预测目标轨迹和围捕点的多机器人围捕算法[J].电子学报,2011,39(11):2480-2485.
|
/
| 〈 |
|
〉 |