INFORMATION-PREDICTING SYSTEMS FOR THE DESIGN OF NEW MATERIALS

In this paper we discuss the main principles for the cybernetic predic tion of inorganic substances which would have predefined properties. T hese predictive techniques are based on machine learning strategies. T he efficiency of the proposed approach is illustrated by comparing the results of predicting the properties of new substances with experimen tal data. Examples showing the application of these techniques to the prediction of those materials used in the electronics industry are des cribed. Also discussed are the components and the organization of the computer-aided information-predicting system developed by the Institut e of Metallurgy of the Russian Academy of Sciences. A detailed descrip tion of the databank for the properties of the ternary inorganic phase s is provided, as well as an explanation of the main difference betwee n the information-predicting system and the expert systems.