Prediction of warp distortion in circuit board using machine learning

Abstract

A convolutional neural network, which reproduce a function by data, was used to predict the amount of warp distortion of a four-layer circuit board in a reflow soldering process. The data used for training are material properties such as Young's modulus, board thickness, and residual copper content as input data, and the predicted warp distortion data is the amount of warpage of the circuit board obtained from the measurement. Since a number of distortion data to be predicted was insufficient to be used for training, a newly proposed data augmentation method used to increase a number of data. The augmentation method is evaluated through the result of the predictions and discussed.