Neural network analysis of tensile strength of austempered ductile iron

The neural technique was applied to the analysis of the ultimate tensile strength and additionally the yield strength of austempered ductile iron (ADI). Austempered ductile iron is an excellent material and it possesses attractive properties as high strength, ductility and toughness. This paper begins with an introduction to neural networks and demonstrates the ability of the method to investigate new phenomena in cases where the information cannot be accessed experimentally. The model allows the strength properties to be estimated as a function of heat treatment parameters and the chemical composition. A 'committee' model was used to increase the accuracy of the predictions. The model was validated by comparison its predictions with data of tensile tests experiments on austempered samples of ductile cast iron. The model successfully reproduces experimentally determined ultimate tensile strength and it can be exploited in the predictions of both ultimate and yield strength and in the design of chemical composition of cast irons and their heat treatments.