LEARNING MODEL GENERATION METHOD, LEARNING MODEL GENERATION DEVICE, BLAST FURNACE MOLTEN IRON TEMPERATURE CONTROL METHOD, BLAST FURNACE MOLTEN IRON TEMPERATURE CONTROL GUIDANCE METHOD, AND MOLTEN IRON MANUFACTURING METHOD

• Main Authors: HASHIMOTO YOSHIYA, KAISE TATSUYA
• Format: Patent
• Language: English; Japanese
• Published: 15.02.2021
• Subjects: CHEMISTRY; CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MANUFACTURE OF IRON OR STEEL; METALLURGY; METALLURGY OF IRON; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING

To provide a learning model generation method and a learning model generation device that can generate a learning model capable of accurately controlling a state of a process or a device.SOLUTION: A learning model generation method includes: a step of machine learning of behavioral models in which an operator determines an operation amount for a process or device (S2) by using, as input data, image data obtained by imaging historical data of one or more observation amounts that indicate the operating status of the process or the operating status of the device, and by using, as output data, the operation amount of the process or device determined by the operator based on the historical data; and a step of outputting the machine learned behavioral models (S3).SELECTED DRAWING: Figure 2 【課題】プロセス又は機器の状態を精度よく制御可能な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。【解決手段】プロセスの操業状態又は機器の運転状態を示す１つ以上の観測量の履歴データを画像化した画像データを入力データ、履歴データに基づいてオペレータが決定したプロセス又は機器の操作量を出力データとして、オペレータがプロセス又は機器の操作量を決定する行動モデルを機械学習し（Ｓ２）、機械学習された行動モデルを出力するステップ（Ｓ３）を含むことを特徴とする。【選択図】図２