An Artificial Neural Network Model For Prediction Of The Properties Of Aluminum Bronze

Material research has used a large of experiments to determine the chemical composition and manufacture processes of a material, which lead to consume manpower, substance sources and time. Because of non-theoretic experience and rules, it is impossible for material design to deviate entirely from experience in due course. On these conditions, theoretic material design and prediction using computer are attended. They are very useful which can provide references for production of alloy.In this paper, SEM and Optical microscope and Image tool are used to analyze the microstructure of Aluminum Bronze. Constitution parameters are fixed under the definite technology processor. Finally, A mechanical property predicting model is set up for marine propeller aluminum bronze by back-propagation (BP) artificial neural network in MATLAB toolbox. The calculation results show that the tensile strength and yield strength of the alloy predicted by the model are approximate to real ones and the relative errors are about ?%, the error of the elongation is 2.3%, by the multi-dimension linear regression model, the relative error are from ?5% to ?15% respectively. Comparing the results, it can be found that the neural network overmatches the multi-dimension linear regression. So that, the model can be used in the production of the marine propeller aluminum bronze.