Heating furnace abnormality cause identification method, heating furnace abnormality cause identification device, machine learning method, and heating furnace abnormality cause identification model

摘要

PROBLEM TO BE SOLVED: To provide a heating furnace abnormality cause identification method capable of identifying an abnormality cause including an abnormality cause which has not occurred in the past, a heating furnace abnormality cause identification device, a machine learning method, and a heating furnace abnormality cause identification model. To do. SOLUTION: The method for identifying the cause of an abnormality in a heating furnace is a model in which a step of acquiring operation data of the heating furnace, operation data of the heating furnace is used as an input variable, and the cause of the abnormality of the heating furnace is used as an output variable. For the cause of the abnormality, there is no actual operation data corresponding to the cause of, or the actual operation data of more than the specified number is not obtained, the simulated operation data created based on the actual operation data at the normal time is used. The abnormality cause identification model includes a step of identifying the cause of the abnormality by inputting the acquired operation data to the machine-learned abnormality cause identification model, and the abnormality cause identification model uses an unadopted operation data detection sensor. Machine learning is performed using the data obtained by adding the newly acquired operation data to the simulated operation data by adopting it. [Selection diagram] Fig. 4