Intelligent Pseudo Solder Detection in PCB Using Laser-Pulsed Thermography and Neural Network

Abstract

Solder joints of printed circuit board provide the electrical and mechanical connections between electronic component and substrate. A pseudo solder inside the solder joint can reduce its electrical conductivity and often leads to crack initiation and propagation in service. The pseudo solder is a threat to the normal operation of the whole electronic equipment, especially in aerospace crafts. The pseudo solder inside the solder joint is hard to be detected with traditional electrometric method or automated optical inspection. In this paper, a laser pulse stimulated infrared thermography technique is presented to detect and identify the pseudo solder in solder joints. Characteristic parameters of the solder joints were extracted using pulsed phase thermography, temperature change rate, apparent thermal effusivity and higher-order statistics. Two neural network (NN) models based on the input patterns of data were constructed to classify the solder joints. The inputs were composed of seven characteristic parameters obtained or excess temperature evolutions. The NN was trained with the method of batch gradient descent or stochastic gradient descent. The application of principal component analysis (PCA) in data preprocessing and feature extraction was explored. Finally, the optimal scheme for pseudo solder detection with higher recognition rate was discovered. The optimal scheme is that, using PCA to extract the features from the excess temperature evolutions, and then using the stochastic gradient descent to train the neural network. The recognition rate of the sound and pseudo states can reach 95%, while the accuracy of the defective degree classification is approximately 76%.