图像自动增强与注意力机制深度学习的MIG焊缝跟踪系统

MIG weld seam tracking system based on image automatic enhancement and attention mechanism deep learning

针对常规MIG焊难以根据组对偏差及热积累变形实时调整焊接位置的难题,提出并建立了被动视觉MIG焊缝跟踪试验系统,通过图像空间域滤波及自动增强算法,采用添加注意力机制的YOLO v7深度学习模型,在感兴区内对坡口的对中位置、电弧位置进行实时提取与分析;并采用模糊控制算法对预设偏差时的MIG焊过程进行实时控制.结果表明,采用图像自动增强算法完成了对图像的预处理,边缘位置的像素灰度值由40增大到110左右,显著提高了边缘位置信息提取的精度;基于YOLO v7网络结构添加注意力机制模块,提升目标检测效率,整体平均精度值mAP指标达到99.27%;预设偏差试验表明,对中偏差检测像素误差在8个像素以内,对中偏差距离控制在±0.5 mm之间.

Aiming at the problem that conventional MIG welding is difficult to adjust the welding position in real time according to the group deviation and thermal accumulation deformation,a weld seam tracking method based on passive vision is proposed.Through the image spatial domain filtering and automatic enhancement algorithm,the YOLO v7 deep learning model with attention mechanism is used to extract and analyze the groove alignment position and arc position in the region of interest in real time.The fuzzy control algorithm is used to control the MIG welding process in real time when the preset deviation occurs.The results show that,the image automatic enhancement algorithm is used to complete the preprocessing of the image,and the pixel gray value of the edge position is increased from 40 to about 110,which significantly improves the accuracy of the edge position information extraction;Based on the YOLO v7 network structure,the attention mechanism module is added to improve the efficiency of target detection,and the mAP index is as high as 99.27%.The preset deviation test shows that the pixel error of the alignment deviation detection is within 8 pixels,and the alignment deviation distance is controlled between±0.5 mm.