Abnormality diagnosis model construction method, abnormality diagnosis method, abnormality diagnosis model construction device and abnormality diagnosis device

摘要

PROBLEM TO BE SOLVED: To investigate the cause of an abnormality at an early stage by detecting an abnormal state from a large amount of measured values acquired in a manufacturing process and classifying and selecting a large number of candidates for the cause of the abnormality which do not have a one-to-one correspondence. To provide a method for constructing an abnormality diagnosis model, an abnormality diagnosis method, an abnormality diagnosis model construction device, and an abnormality diagnosis device. SOLUTION: The method for constructing an abnormality diagnosis model is a method for constructing an abnormality diagnosis model for a process of sequentially processing a metal material in a plurality of facilities, and the plurality of facilities are at the same time in a predetermined measurement cycle. Using the measured values, the first model creation step to create the first abnormality diagnosis model that learned the relationship between the measured values at the same time and the abnormality, and the measured values measured for multiple facilities. Creates a second abnormality diagnosis model that learns the relationship between the measurement value at the same position and the abnormality using the measurement value for each position of the metal material edited for each position of the metal material. Modeling steps and include. [Selection diagram] Fig. 1