Method and apparatus for designing multi-component material, optimization analyzer and storage medium using learning process

A rubber compound which is formed in composition having the compositional ratio of multi-component materials designed by a design method of a multi-component material comprising the steps of:

• (a) determining a conversion system using learning in which a non-linear correspondence between compositional ratios of multi-component materials composed of a plurality of components as inputs and mechanical behaviors of the multi-component materials as outputs is established;
• (b) determining an objective function expressing said mechanical behaviors and setting a constraint condition constraining the allowable range of at least one of said mechanical behaviors and said compositional ratios of the multi-component materials;
• and
• (c) determining a compositional ratio of the multi-component materials which gives an optimal solution of an objective function by using said objective function and said constraint condition on the basis of the conversion system determined in said step (a) to design the multi-component materials on the basis of the compositional ratio which gives the optimal solution of the objective function.

An optimization analyzing apparatus comprising;

• conversion system calculating means using learning for determining a non-linear corresponding relation between compositional ratios of multi-component materials composed of a plurality of components as inputs and mechanical behaviors of the multi-component materials as outputs;
• input means for inputting an objective function and constraint condition as optimization items by determining the objective function expressing the mechanical behaviors and determining the constraint condition which constrains an allowable range of at least one of the mechanical behaviors and the compositional ratios of the multi-component materials;
• and
• optimization calculation means for determining a compositional ratio of the multi-component materials which gives an optimal solution of the objective function by using the optimization item inputted by the input means on the basis of said conversion system calculation means.

A computer-readable storage medium having a stored optimization analyzing program for designing a multi-component material by a computer in which the optimization analyzing program is programmed, said stored optimization analyzing program performing the steps of:

• using learning, determining a non-linear corresponding relation between compositional ratios of multi-component materials as inputs and mechanical behaviors of the multi-component materials as outputs;
• determining an objective function expressing the mechanical behaviors;
• determining a constraint condition constraining an allowable range of at least one of the mechanical behaviors and the compositional ratios of the multi-component materials;
• and
• obtaining the compositional ratio of the multi-component materials which gives an optimal solution of the objective function, based on the determined corresponding relation, the objective function and the constraint condition to design a multi-component material on the basis of the compositional ratio of the multi-component materials which gives the optimal solution of the objective function.