Molded body region inspection program, molded body region inspection method, molded body region inspection device, and recording medium

An inspecting method for a molded body region, comprising:

• generating a mechanical property inference model for inferring unknown mechanical property information of a fiber-reinforced second molded body region using non-destructive inspection information of the second molded body region as input by performing machine learning of known mechanical property information and known non-destructive inspection information of a fiber-reinforced first molded body region;
• acquiring the non-destructive inspection information of the second molded body region;
• inputting the acquired non-destructive inspection information into the mechanical property inference model;
• acquiring mechanical property information of the second molded body region from the mechanical property inference model;
• and performing output based on the mechanical property information,
• wherein the first molded body region and the second molded body region are each obtained by molding a plate-shaped composite material with a mold,
• the first molded body region and the second molded body region are obtained by molding the composite material such that a charge ratio is 10% or more and 500% or less, respectively,
• wherein the charge ratio is a value obtained by calculating (S1/S2)×100, wherein
• S1 is a projected area of the composite material, and
• S2 is a projected area of a portion corresponding to the first molded body region and the second molded body region in a mold cavity of the mold,
• wherein the non-destructive inspection information is vibration characteristic information or acoustic characteristic information, and a sampling frequency at the time of acquiring the non-destructive inspection information is more than 0 Hz.

An inspection device for inspecting a molded body region, the device comprising a processor configured to access a model storage unit that stores a mechanical property inferring model generated by machine learning based on mechanical property information and non-destructive inspection information of a fiber-reinforced first molded body region,

• wherein the mechanical property inference model infers unknown mechanical property information of a fiber-reinforced second molded body region by inputting non-destructive inspection information of the second molded body region,
• wherein the first molded body region and the second molded body region are each obtained by molding a plate-shaped composite material with a mold,
• the first molded body region and the second molded body region are obtained by molding the composite material such that a charge ratio is 10% or more and 500% or less, respectively,
• wherein the charge ratio is a value obtained by calculating (S1/S2)×100, wherein
• S1 is a projected area of the composite material, and
• S2 is a projected area of a portion corresponding to the first molded body region and the second molded body region in a mold cavity of the mold,
• the processor is configured to:
• acquire the non-destructive inspection information of the second molded body region;
• input the non-destructive inspection information to the mechanical property inference model;
• acquire mechanical property information of the second molded body region from the mechanical property inference model;
• and
• output the mechanical property information based on the mechanical property information,
• wherein the non-destructive inspection information is vibration characteristic information or acoustic characteristic information, and a sampling frequency at the time of acquiring the non-destructive inspection information is more than 0 Hz.

A non-transitory computer readable medium storing a program for inspecting a molded body region, the inspection program causing a processor to execute the steps of:

• generating a mechanical property inference model for inferring unknown mechanical property information of a fiber-reinforced second molded body region using non-destructive inspection information of the second molded body region as input by performing machine learning of known mechanical property information and known non-destructive inspection information of a fiber-reinforced first molded body region;
• acquiring the temperature distribution information of the second molded body region;
• inputting the acquired temperature distribution information to the mechanical property inference model;
• acquiring mechanical property information of the second molded body region from the mechanical property inference model;
• and
• outputting the mechanical property information based on the mechanical property information,
• wherein the first molded body region and the second molded body region are each obtained by molding a plate-shaped composite material with a mold,
• wherein the first molded body region and the second molded body region are obtained by molding the composite material such that a charge ratio is 10% or more and 500% or less, respectively,
• wherein the charge ratio is a value obtained by calculating (S1/S2)×100, wherein
• S1 is a projected area of the composite material, and
• S2 is a projected area of a portion corresponding to the first molded body region and the second molded body region in a mold cavity of the mold.