An artificial neural network (ANN) approach to model Tire-Pavement interaction noise (TPIN) based on tire noise separation

•Order tracking analysis separates total tire noise into a periodic and non-periodic component.•This is the first ANN developed to predict the tread pattern related noise.•This is the first ANN developed to predict the non-tread pattern related noise.•A custom output layer transfer function was implemented for TPIN prediction.•The model predicts TPIN for different pavements, tires, and vehicle speeds.