Investigation of Manufacturing Parameters on the Mechanical Properties of Powder Metallurgy Magnesium Matrix Nanocomposite by Artificial Neural Networks

In present study, Artificial Neural Network (ANN) approach to prediction of the ODS Magnesium matrix composite mechanical properties obtained was used. Several composition of Mg- Al2O3 composites with four different amount of Al2O3 reinforcement with four different size of nanometer to micrometer were produced in different sintering times. The specimens were characterized using metallographic observation, microhardness and strength (UTS) measurements. Then, for modeling and prediction of mentioned conditions, a multi layer perceptron back propagation feed forward neural network was constructed to evaluate and compare the experimental calculated data to predicted values. In neural network training modules, different composition, sintering time and reinforcement size were used as input (3 inputs), hardness and Ultimate Tensile Strength(UTS) were used as output. Then, the neural network was trained using the prepared training set. At the end of training process the test data were used to check the system’s accuracy. As a result, the comparison of neural network output results with the results from experiments and empirical relationship has shown good agreement with average error of 2.5%. When you are citing the document, use the following link http://essuir.sumdu.edu.ua/handle/123456789/3511