Using ANN and OA techniques to determine the specific wear rate effectors of A356 Al-Si/Al2O3 MMC

Abstract In the present work, it’s required to obtained wear rate effectors’ values of A356 Al-Si/Al 2 O 3 composite (Al wt%, applied load, hardness, and sliding distance) obtain a certain specific rate. So, behavior cast heat-treated metal matrix composites (MMC) were investigated as function its effectors. Five weight fractions Al particles used produce specimens using stir casting. Two different hardness are for each fraction (casted specimens). Sliding tests done under three loads (20, 30, 40 N), four distances (310, 620, 930 1240 m) at constant speed (1 m/min). Experimental results indicated that is generally reversed proportional percentage. The impact percentage was eliminated with grown load. Increasing load decreases rate, up 20% . However, 25% increases small graduation. Moreover, heat treatment process improves casted MMC. Both Artificial neural network (ANN) multiple regression techniques predict orthogonal array technique (OA) in selecting data set train ANN 2nd degree equation. gives more realistic prediction then end, an algorithm designed tested determine other effectors MMC according uncertainty ANN. obtaining provides very good choices rate’s value, error less than 1%.