Abstract: A material design system includes an expert terminal capable of using a model learning interface for performing machine learning of a model that inputs and outputs a correspondence between a design condition and a material property value of the material to be designed, and a plurality of general-purpose terminals configured to use a material design interface for estimating the material property value based on the design condition or estimating the design condition based on the material property value, by using a learned model that is created by the expert terminal and is for the material to be designed.

Abstract: Technical knowledge which is difficult for the expert to express in words or numerical form is predicted and reproduced. A technical knowledge prediction apparatus according to one embodiment of the present invention includes a problem setting unit configured to automatically create and set a problem which includes a control factor of a manufacturing step, and a variable of the control factor, an answer acquiring unit configured to acquire an answer with respect to the problem and indicating a decision of the manufacturing step, a query acquiring unit configured to acquire a query, and a prediction output unit configured to predict and output an answer corresponding to the query acquired by the query acquiring unit, based on a corresponding relationship between the problem and the answer.

Abstract: A prediction device for predicting a thermodynamic equilibrium state of a target material, includes a processor, and a memory storing program instructions that cause the processor to generate training data including inputs related to predetermined design conditions and outputs related to the thermodynamic equilibrium state that may occur based on the predetermined design conditions, for a model that outputs target variables related to the thermodynamic equilibrium state based on input explanatory variables related to design conditions of the target material, perform machine learning using the training data so that an input-output relation of the model approaches an input-output relation of the training data, set explanatory variables used to predict the thermodynamic equilibrium state of the target material, and output predictive target variables, being predicted results of the thermodynamic equilibrium state, from the model, based on the explanatory variables input into the model on which the machine learnin

Abstract: A material design device derives the optimal solution for a design condition satisfying a desired material property. A design condition setting unit for setting a specified range of a design condition of a material to be designed. A comprehensive prediction point generation unit generates a plurality of comprehensive prediction points within the specified range set by the design condition setting unit. A design condition-material property table stores data sets in which each point of the comprehensive prediction points is associated with a material property value calculated by inputting the comprehensive prediction points generated by the comprehensive prediction point generation unit, to a learned model. A required property setting unit sets a specified range of a required property of the material. A design condition extraction unit extracts, from the design condition-material property table, a data set satisfying the required property set by the required property setting unit.

Abstract: Efficiency of a material search is improved. An apparatus according to one embodiment of the present invention includes a composition obtaining unit configured to obtain a candidate composition, a thermodynamic calculation unit configured to perform thermodynamic calculation on the candidate composition, a manufacturing determining unit configured to determine whether the candidate composition is a manufacturable material based on a correspondence relation between a result of the thermodynamic calculation performed on a predetermined composition and manufacturability indicating whether a material having the predetermined composition is manufacturable, and an output unit configured to output a composition that is determined to be the manufacturable material.