摘要
针对TIG焊接过程中强弧光、烟尘、极端热辐射等复杂工况,以及液态金属动态流动引起的熔池区域反射特性不稳定对熔池视觉特征提取造成干扰的问题,本研究提出一种改进型熔池测量方法,包括基于注意力机制与多尺度特征融合的轻量级网络熔池分割方法和基于分割结果的闭运算、连通区域标记和最小外接矩形图像处理方法.结果表明,改进后的网络在自建熔池分割数据集上取得性能提升,平均交并比(MIoU)达95.44%,平均像素精度(mPA)为98.27%,单帧推理耗时仅为11.30 ms,且有效提取所分割熔池的长度、宽度和面积.
There is interference caused by complex working conditions such as strong arc light,smoke and dust,and extreme thermal radiation during the TIG welding,and interference for visual feature extraction of the molten pool due to the reflection characteristic instability of the molten pool region caused by the dynamic flow of liquid metal.In view of this,this study proposes an improvement method for molten pool measurement,which includes a lightweight network molten pool segmentation method based on the attention mechanism and multi-scale feature fusion,and an image processing method of closing operation,connected region labeling,and the minimum bounding rectangle based on the segmentation results.The results show that the improved network has enhanced performance on the self-built molten pool segmentation datasets.The mean intersection over union(MIoU)reaches 95.44%,the mean pixel accuracy(mPA)is 98.27%,and the inference time for a single frame is only 11.30 ms.Additionally,the length,width,and area of the segmented molten pool are effectively extracted.
作者
林雨浩
黎振龙
赵运强
邹鹏
奥列格·格纽申科
亚历山大·沃伊捷克
LIN Yu-Hao;LI Zhen-Long;ZHAO Yun-Qiang;ZOU Peng;Oleg GANUSHCHAK;Oleksandr VOITENKO(Guangdong Advanced Design and Manufacturing Engineering Technology Research Center for Motorcycles,Wuyi University,Jiangmen 529020,China;Guangdong Provincial Key Laboratory of Material Joining and Advanced Manufacturing,China-Ukraine Institute of Welding,Guangdong Academy of Sciences,Guangzhou 510650,China;E.O.Paton Electric Welding Institute,National Academy of Sciences of Ukraine,Kyiv 03150,Ukraine)
出处
《计算机系统应用》
2026年第1期246-254,共9页
Computer Systems & Applications
基金
国家重点研发计划(2023YFE0201500)
广东省重点人才计划(2023TQ07C702)
阳江市科技计划(RCZX2024006)
广东省科学院青年人才专项杰出青年项目(2024GDASQNRC-0103)。
