Application Of Artificial Neural Network In Material Design

Material design aims to manufacture material with certain properties based on accumulated experience and scientific theory. 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 is to be applied to. By means of computer technology, material design can break away from experiment and make use of fewer experiments to obtain ideal materials. With the development of expert system and artificial neural network, effective method is provided with computer aided material design.Artificial neural network(ANN) is non-linear technology developed since 1980. The ANN model is determined by topology structure, activation function and learning method. The model possesses with good fault tolerance, self-adaptability and non-linear mapping, especially it is suitable to resolve complex causal problems. In many fields material design is applied and developed.Structure design and calculation methods of back-propagation (bp) network are investigated in this paper. This research utilizes appended momentum and changes step methods in order to accelerate learning speed and avoid acute vibration. Based on experimental data, the bp model is built, which reflects the relationship between the mechanical properties, phase transformation points of material and its composition, micro-structure. Hardenability curves, alloy composition, austenite temperature, martensite start temperature and yield strength are predicted by means of artificial neural network technology. It is advantageous to predict material design with artificial neural network.