Quality prediction model generation method, quality prediction model, quality prediction method, metal material manufacturing method, quality prediction model generation device, and quality prediction device

Abstract

This quality prediction model generation method is a quality prediction model generation method for a metal material manufactured through one or a plurality of steps, and includes: a first collection step for collecting manufacturing conditions for each step for each predetermined range of the metal material; a second collection step for evaluating and collecting, for each of the prescribed ranges, the quality of the metal material manufactured through each step; a storage step in which, for each prescribed range, the manufacturing conditions for each step and the quality of the metal material manufactured under the manufacturing conditions are stored in association with each other; and a model generation step for generating a quality prediction model for predicting the quality of the metal material in each prescribed range on the basis of the stored manufacturing conditions in each prescribed range in each step.

Description

technical field [0001] The present invention relates to a quality prediction model generation method, a quality prediction model, a quality prediction method, a metal material manufacturing method, a quality prediction model generation device, and a quality prediction device. Background technique [0002] As a method of predicting the quality of an arbitrary requirement condition, for example, there is known a method of calculating the distance between a plurality of past observation conditions stored in the performance database and the desired requirement condition, and calculating the observation condition based on the calculated distance. The weight of data (actual performance data) is a method of using the calculated weight to create a function that fits around the required condition and using the created function to predict the quality of the required condition (see, for example, Patent Documents 1 to 8). [0003] Patent Document 1: Japanese Patent Laid-Open No. 2004-35...

AI Technical Summary

Problems solved by technology

However, in the prior art, the actual performance values ​​of the manufacturing conditions collected in such a detailed manner have not been effectively used, so the improvement of the prediction accuracy of the quality of metal materials is limited.

Images