Automated Inspection of Micro Laser Spot Weld Quality Using Optical Sensing and Neural Network Techniques

Abstract – This paper presents an approach to the automated inspection of laser spot welding processes using optical sensing and neural network techniques. An optical sensor is used to derive signals covering a spectrum ranging from visible to infrared bands. A set of features extracted from the signals is fed into a neural network to classify the quality of welds. A series of experiments was carried out using a pulsed Nd:YAG laser and a common SMD (surface mounted devices) as a test component. The results obtained show that this approach can be used to inspect the laser welding quality for the microelectronics industry