PREDICTION OF TRIBOLOGICAL BEHAVIOR OF ALUMINIUM MATRIX HYBRID COMPOSITES USING ARTIFICIAL NEURAL NETWORKS

Abstract

Prediction of tribological characteristics of hybrid composites with A356 matrix using artificial neural networks (ANN) was performed in this paper. During experiment next parameters were varied: sliding speed, load, sliding distance and wt.% of reinforcement. The obtained experimental results were used to form the artificial neural network in which were varied number of neurons in the hidden layer, number of layers, the activation function and the function of training. Training of the neural network was performed for the wear rate, and optimal regression coefficient was equal to 0.994, for the network4-15-10-1. Using neural networks to predict the wear rate greatly reduces the time and cost of experiment.