Real-time monitoring of high-power disk laser welding based on support vector machine

摘要

Highlights?SVM classifiers were generated to automatically evaluate the welding quality of high-power disk laser welding.?Using the appropriate feature selection method, the performance of the classifier can be improved significantly.?The plume and spatters images captured by high-speed camera can be used to create classifiers for real-time monitoring.AbstractIn this paper, an efficient quality monitoring system for monitoring high-power disk laser welding in real time was developed. Fifteen features of laser-induced metal vapor plume and spatters were extracted and support vector machine was adopted to establish a classifier to evaluate the welding quality. Feature selection method was employed to choose suitable features. The experiment results demonstrated that this method had satisfactory performance and could be applied to real-time monitoring application.]]>