Abstract: A quality prediction model generation method for a metal material manufactured through one or more processes includes: a first collection step of collecting a manufacturing condition of each of the processes for each of predetermined areas of the metal material; a second collection step of evaluating and collecting quality of the metal material manufactured through each process for each of the predetermined areas; a storage step of storing the manufacturing condition of each process and the quality of the metal material manufactured under the manufacturing condition in association with each other for each of the predetermined areas; and a model generation step of generating a quality prediction model that predicts quality of the metal material for each of the predetermined areas based on the stored manufacturing condition for each of the predetermined areas in each process.

Abstract: An analysis system 10 includes: an operational data acquisition unit 11 that acquires operational data including an operational state of a production line 20; a product information acquisition unit 13 that acquires a state of a product manufactured in the production line and outputs the state of the product as product information; a production state analyzer 12 that obtains a predetermined physical quantity of the product on a basis of the operational data acquired by the operational data acquisition unit 11 and outputs the predetermined physical quantity as information on the physical quantity; and a correlation analyzer 14 that performs analysis of a correlation between the information on the physical quantity and the product information.

Abstract: A prediction model constructing apparatus includes a operational result database, similarity calculating means, and prediction model constructing means. The operational result database relates manufacturing conditions of a product manufactured in the past to result information on the manufacturing, and stores a plurality pieces of information obtained by relating the manufacturing conditions to the result information. The similarity calculating means calculates a similarity composed of a plurality of comparison results by comparing the manufacturing conditions stored in the operational result database with a manufacturing condition of a prediction target. The prediction model constructing means determines a parameter of a prediction model corresponding to the manufacturing condition of the prediction target.

Abstract: A prediction model constructing apparatus includes a operational result database, similarity calculating means, and prediction model constructing means. The operational result database relates manufacturing conditions of a product manufactured in the past to result information on the manufacturing, and stores a plurality pieces of information obtained by relating the manufacturing conditions to the result information. The similarity calculating means calculates a similarity composed of a plurality of comparison results by comparing the manufacturing conditions stored in the operational result database with a manufacturing condition of a prediction target. The prediction model constructing means determines a parameter of a prediction model corresponding to the manufacturing condition of the prediction target.