Prediction of drilling-induced damage in unidirectional glass-fibre-reinforced plastic laminates using an artificial neural network

Drilling-induced damage is a serious problem in laminated composite materials. The research efforts worldwide have been focused on minimization of this damage. A number of methodologies have been adopted for this purpose. The present research effort is aimed towards developing a predictive tool for calculating the likely damage before actual drilling commences, and thereby reducing its severity. The artificial neural network topology has been adopted as a predictive tool. The spindle speed, feed rate, drill diameter, and drill point geometry have been used as the input parameters. The drilling-induced damage was the output. The experimental data for drilling of unidirectional glass-fibre-reinforced plastic composite laminates were used for training and testing the model. The results of the predictive model have been found to be in good agreement with the test data.