| 摘要: |
| 提出一种将点焊过程动态电极位移信号转化为二值图像的方法.基于图像特征分析,从焊点样本电极位移二值图像中提取出15个隐含特征.针对一系列对应不同焊接质量焊点样本电极位移二值图像特征,利用主成分分析消除图像特征间的互相关性,建立了基于最小风险贝叶斯图像识别技术的焊点质量分类器.分类器有效性测试结果表明,电极位移信号二值图像尽可能多的保留了焊点质量信息,特征提取算法简单、高效、易于实现;同时在小数据样本情况下,贝叶斯图像识别技术能够快速、准确地评判焊点质量,有较好的应用前景. |
| 关键词: 电阻点焊 质量评估 贝叶斯统计分析 图像识别 |
| DOI： |
| 分类号: |
| 基金项目: |
|
| Quality assessment for resistance spot welding based on Bayesian image recognition technology |
|
ZHANG Hongjie1,2, ZHANG Jianye1,2, SUI Xiuwu1,2
|
|
1.School of Mechanical Engineering, Tianjin Polytechnic University, Tianjin 300387, China;2.Tianjin Key Laboratory of Modern Mechatronics Equipment Technology, Tianjin Polytechnic University, Tianjin 300387, China
|
| Abstract: |
| A method for converting electrode displacement signal to binary image in resistance spot welding process is proposed. Based on image characteristic analysis,fifteen image features are extracted from the binary image of electrode displacement waveform. The principal component analysis is used to remove the cross correlation among image features,and a series of weld specimens with different welding quality are selected to develop a quality classifier. The test results based on Bayesian image recognition technology of minimum risk show that it is feasible and reliable to utilize the binary image of electrode displacement signal to evaluate the weld quality and the image conserves the information of the weld quality. The algorithm for image feature extraction is simple,efficient and easy to use. At the mean time,the Bayesian image recognition technique with small samples can realize the welding quality assessment rapidly and accurately, and the method has a broad application prospect. |
| Key words: resistance spot welding quality assessment Bayesian statistic analysis image recognition |
