TRAINING DEVICE, PLANT, MODEL GENERATING METHOD, INFERENCE DEVICE, INFERRING METHOD, AND PLANT CONTROL METHOD

• Main Authors: HINO HIROYUKI, YOSHIMURA YU, YONEDA MASARU, NAKABACHI KAIZABURO, HIRAI TAICHIRO, KANUMA MITSUSEI, UEHARA KAZUKI
• Format: Patent
• Language: English; Japanese
• Published: 03.03.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONTROL OR REGULATING SYSTEMS IN GENERAL; CONTROLLING; COUNTING; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS ORELEMENTS; PHYSICS; REGULATING

To realize a model with high generalization performance that infers information about observed values of a controlled object.SOLUTION: A training device comprises at least one memory and at least one processor. The at least one processor is configured executable to train a model on observed values of a controlled object under constraints according to a relation between changes in the values of time-series data that are input data and changes in the values of time-series data that are correct data.SELECTED DRAWING: Figure 4 【課題】制御対象の観測値に関する情報を推論する汎化性能の高いモデルを実現する。【解決手段】訓練装置は、少なくとも１つのメモリと、少なくとも１つのプロセッサと、を備え、前記少なくとも１つのプロセッサは、入力データである時系列データの値の変化と正解データである時系列データの値の変化との関係に応じた制約のもとで、制御対象の観測値に関するモデルを訓練すること、を実行可能に構成される。【選択図】図４