Neural network approach for estimating the residual tensile strength after drilling in uni-directional glass fiber reinforced plastic laminates

The drilling of fiber reinforced plastics (FRP) often results in damage around the drilled hole. The drilling induced damage often serves to impair the long-term performance of the composite products with drilled holes. The present research investigation focuses on developing a predictive model for the residual tensile strength of uni-directional glass fiber reinforced plastic (UD-GFRP) laminates with drilled hole which has not been developed worldwide till now. Artificial neural network (ANN) predictive approach has been used. The drill point geometry, the feed rate and the spindle speed have been used as the input variables and the residual tensile strength as the output. The results of the predictive model are in close agreement with the training and the testing data.