Design Of Man-Machine Interface And The Application Of Neural Network Expert System In Material Design

Material design aims to develop new material with certain properties based on accumulated experience and scientific theory. The main objects are to fix on the relation among composition, process parameters and performance of materials. As far as the development of currently material science, there are not enough inherent rules on the material, but a vast amount of experimental data about composition, process parameters and their performances. Researcher has used a large of experiments to determine the optimum performance and regularity composition of a material, which lead to consume manpower, substance sources and time. To obtain highly active, economic and predictive, it is inevitable to use the way of calculation.Expert system and artificial neural network are active branches of artificial intelligence. Artificial neural network is a mathematics method which simulates human's brain and own ability self-learning. The model possesses with good fault tolerance, self-adaptability and non-linear mapping, especially it is suitable to resolve complex causal problems. Expert system has the favorable function of data management and provides the expert with the friendly multimedia interface.Combining neural network and expert system, an expert system based on artificial neural network is built in this paper. The man-machine interactive interface is designed with Visual C++. The data preprocessing and dummy pattern program is compiled in order to perfect the predictive program. By means of adjusting learning rate and momentum we have improved the standard BP. So a three layer BP structure system is made up to predict the Jominy curves of Constructional Steel. In this paper we also discuss the effect of the different number of trainingsamples and dummy pattern on artificial neural network prediction accuracy and generalization ability.