KDPAG expert system applied to materials design and manufacture

A multi-dimensional space, spanned by dimensionless numbers describing the equilibrium states or the macroscopic chemical kinetics of complicated chemical reaction systems, I las been used fbr data processing and for the modeling of the processes needed to prepare industrial materials. It was found that there are four types of topological relationships between the optimization zone and the operation zone in multi-dimensional spaces. Pattern recognition, artificial neural networks (ANN) and genetic algorithms (GA) are used to build models and search for an optimization strategy. An integrated expert system called knowledge base, data base, pattern recognition, artificial neural network, genetic algorithm (KDPAG), consisting of a knowledge base, a database, and pattern-recognition, ANN, and GA modules has been built. Applications of this system give good results, as has been observed in several factories for the importance of the production of alloy steel, synthetic rubber, ceramic materials production and materials design of composite materials, high T-c superconductors, and ceramic semiconductors. (C) 1998 Elsevier Science Ltd. All rights reserved.