12. An ANN Approach for Predicting the Wear Behavior of Nano SiC-Reinforced A356 MMNCs Synthesized by Ultrasonic-Assisted Cavitation

Artificial neural networks (ANN) are a science that attempts to mimic the system of human mind in tackling issues. Many researchers have been conveyed for modeling and forecast of wear properties of metal matrix composites (MMCs) by ANN method. But this technique is not yet used for metal matrix nanocomposites (MMNCs) so far. ANN is an incredible asset to foresee properties of MMNCs, if it is properly trained. In the current work, a back propagation neural network model for assessing wear characteristics of MMNCs is proposed, in which aluminum (A356) reinforced with different weight percentages (wt.% of 0.1, 0.2, 0.3, 0.4 and 0.5) of nano-silicon carbide (SiC) MMNCs is fabricated with ultrasonic-assisted cavitation. Taken the tested results of wear characteristics using pin on disk apparatus at different loads of 30 and 40 N, which are utilized to develop and test the model. Compared to pure aluminum alloy, the wear resistance of MMNCs is increased (Donthamsetty S, Babu PS, in Int. J. Autom. Mech. Eng. 14(4):4589–4602, [1]) and able to predicting the wear within minimal error by using ANN.