摘要
提出了一种基于支持向量机的激光焊接质量监测方法.在监测系统中,首先利用光、声传感器获取焊接过程产生的各种信号,然后利用Gabor变换提取出特征向量,最后利用支持向量机对数据进行融合以判断焊缝是否达到质量要求.实验结果验证该方法的分类正确率可达93%.
A laser welding quality monitoring method is proposed, based on support vector machine. At first optical and sound sensors were used to acquire the various signals in the process of laser welding, then Gabor transformation was applied to extract the feature vector, and finally support vector machine was used for data fusion to judge whether the quality requirements of welding seams are meet. The eexperiments results show that the accuracy of this classification method is up to 93 %.
出处
《华中科技大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2007年第7期62-63,共2页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
关键词
支持向量机
激光焊接
特征提取
质量监测
support vector machine
laser welding
feature extraction
quality monitoring
