首页|基于改进ViT的熔池识别与焊接偏差在线检测方法

基于改进ViT的熔池识别与焊接偏差在线检测方法

扫码查看
原文链接
  • 万方数据
  • 维普
焊接偏差的精确检测是实现焊接机器人焊缝轨迹自动跟踪及智能化焊接的前提。提出了一种基于改进视觉转换器(Vision Transformer，ViT)的熔池识别与焊接偏差在线检测方法。首先，采用轻量级ViT模型Segformer作为基线模型，在其掩码分割前嵌入置换注意力(Shuffle Attention，SA)机制，以更好地捕获特征信息在空间和通道这2个维度中的依赖关系，从而提高模型的分割精度;其次，在多层感知机(Multilayer Perceptron，MLP)中加入上下文广播(Context Broadcasting，CB)模块，在保证模型低参数量的前提下提高泛化能力;最后，基于模型分割结果，提出一种焊接偏差计算方法来定量描述偏差检测精度。实验结果表明，相较于基线模型，所提出模型的平均交并比和平均像素准确率分别提高了 2。67％和2。12％，且对于不同预设焊枪偏移情况均具有良好的泛化性，焊接偏差精度控制在±0。021 mm之内，为实现精密焊接焊缝跟踪提供基础。
Improved ViT-based method for molten pool recognition and online detection of welding deviation
Accurate detection of welding deviations is a prerequisite for automatic seam tracking and intelligent welding by welding robots.An improved ViT-based method for molten pool recognition and online detection of welding deviation was proposed.Firstly,the lightweight ViT model Segformer was used as the baseline model.The Shuffle Attention(SA)was embedded before mask seg-mentation to better capture the dependencies of feature information in both spatial and channel dimensions.Thus,the model's seg-mentation accuracy was enhanced.Secondly,a Context Broadcasting(CB)module was added to the Multilayer Perceptron(MLP)to improve the generalization capability while ensuring low parameters of model.Finally,based on the model segmentation results,a welding deviation calculation method was proposed to quantitatively describe the deviation detection accuracy.The ex-perimental results show that,compared with the baseline model,the mean intersection over union and mean pixel accuracy of pro-posed model were increased by 2.67％and 2.12％,respectively,and it has good generalization for different preset torch offsets.The welding deviation accuracy was controlled between±0.021 mm,which provided a basis for seam tracking in precision welding.

welding deviationseam trackingmolten pool recognitionVision Transformer(ViT)attention mechanism

蒋宇轩、林凯、王瑶祺、张岳、洪宇翔

展开 >

中国计量大学机电工程学院,杭州 310018

中国计量大学浙江省智能制造质量大数据溯源与应用重点实验室,杭州 310018

焊接偏差 焊缝跟踪 熔池识别 视觉转换器 注意力机制

国家自然科学基金项目浙江省自然科学基金项目浙江省教育厅科研资助项目浙江省教育厅科研资助项目浙江省属高校基本科研业务费专项资金资助项目

51605251LY22E050009Y202249427Y2021478382023YW41

2024

10.16731/j.cnki.1671-3133.2024.10.017

现代制造工程
北京机械工程学会 北京市机械工业局技术开发研究所

现代制造工程

CSTPCD北大核心
影响因子：0.374
ISSN：1671-3133
年,卷(期)：2024.(10)
  • 1