摘要
机器人焊接因零件形状不规则和焊接工艺复杂不可避免带来各种焊缝缺陷.针对二维主成分分析应用于焊缝表面缺陷检测时面临计算复杂度高、分类准确率低及无法进行增量学习等问题,提出了一种基于均值更新的增量二维主成分分析(mean updated incremental two-dimensional principal component analysis,MUI2DPCA)算法,并将MUI2DPCA和前馈神经网络(feedforward neural network,FNN)相结合进行焊缝表面缺陷在线检测.首先,对相机捕获的视频帧图像进行预处理得到焊缝局部块图像.然后,利用MUI2DPCA在线提取局部块图像的模式特征.MUI2DPCA对图像的特征主成分进行增量迭代估计,降低计算复杂度,并且能够增量更新当前的样本均值,减少无关特征变化对主成分收敛性的影响.最后,利用FNN建立提取的模式特征与焊缝类别之间的联系,实时返回焊缝表面缺陷的检测信息.试验结果表明,该检测方法平均分类准确率为95.40%,平均处理速度可达29帧/s,能够满足焊缝在线检测的实时性要求.
Robot welding inevitably brings various weld defects due to the irregularity of part shape and the complexity of welding process. When applying two-dimensional principal component analysis to the detection of weld surface defects, it often faces problems such as high computational complexity,low classification accuracy and inability to incrementally learn. To resolve these problems, a mean updated incremental two-dimensional principal component analysis(MUI2 DPCA)algorithm is proposed. MUI2 DPCA and feedforward neural network(FNN) are combined to detect weld surface defects online. Firstly, the local block images are obtained by preprocessing the video frame images captured by the camera.Then, the pattern features of weld block images are extracted online by MUI2 DPCA. The algorithm performs incremental iterative estimation on principal components of block images,significantly reduces the computational complexity, and incrementally updates the current sample mean to reduce the influence of irrelevant feature changes on the convergences of principal components. Finally, FNN is used to establish the relationship between pattern features and weld categories, and the weld defect detection information is obtained in real time.The test results show that the average classification accuracy of the detection method is 95.40%, and the average processing speed reaches 29 frames per second, and it can meet the realtime requirements of weld detection.
作者
周兆逸
张亚南
王肖锋
刘军
ZHOU Zhaoyi;ZHANG Yanan;WANG Xiaofeng;LIU Jun(Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control,Tianjin University of Technology,Tianjin,300384,China;National Demonstration Center for Experimental Mechanical and Electrical Engineering Education,Tianjin University of Technology,Tianjin,300384,China)
出处
《焊接学报》
EI
CAS
CSCD
北大核心
2021年第11期70-76,I0005,共8页
Transactions of The China Welding Institution
基金
国家重点研发计划项目(2017YFB1303304)
国家自然科学基金青年项目(52005370)
天津市科技计划智能制造重大专项(17ZXZNGX00110)
天津市大学生创新创业训练计划项目(202010060033)。
关键词
焊缝表面缺陷检测
二维主成分分析
特征提取
均值更新
前馈神经网络
weld surface defect detection
two-dimensional principal component analysis
feature extraction
mean updated
feedforward neural network
