LEARNING MODEL GENERATION METHOD, DATABASE CONSTRUCTION METHOD, MILL SETUP SETTING METHOD, MANUFACTURING METHOD OF ROLLED MATERIAL, MANUFACTURING METHOD OF PROCESSING OBJECT, AND LEARNING MODEL GENERATION DEVICE

To provide a learning model generation method and a learning model generation device that can generate a learning model which outputs setting values of a production facility satisfying desired operation indices.SOLUTION: A learning model generation method includes: a first learning step for learning a learning model of variables in which operation conditions are used as input and predicted values of the variables are used as output, by using operation performance data on a production facility containing operation conditions of the production facility, actual values of variables that are operation indices of the production facility, and actual values of setting values of the production facility; a selection step for calculating predicted values of the variables by inputting the operation conditions contained in the operation performance data into the learning model of the variables, and selecting operation performance data corresponding to a processing object on the basis of a comparison between the predicted values and the actual values of the variables; and a second learning step for learning a learning model of the setting values using operation conditions as input and predicted values of the setting values as output, by using the selected operation performance data.SELECTED DRAWING: Figure 2 【課題】所望の操業指標を満足する生産設備の設定値を出力する学習モデルを生成可能な学習モデル生成方法及び学習モデル生成装置を提供すること。【解決手段】本発明に係る学習モデル生成方法は、生産設備の操業条件、生産設備の操業指標となる変数の実績値、及び生産設備の設定値の実績値を含む生産設備の操業実績データを用いて、操業条件を入力、変数の予測値を出力とする変数の学習モデルを学習する第１学習ステップと、変数の学習モデルに操業実績データに含まれる操業条件を入力することにより変数の予測値を算出し、変数の予測値と実績値との比較に基づいて処理対象に対応する操業実績データを選択する選択ステップと、選択された操業実績データを用いて、操業条件を入力、設定値の予測値を出力とする設定値の学習モデルを学習する第２学習ステップと、を含む。【選択図】図２