Model generation device, abnormality occurrence prediction device, abnormality occurrence prediction model generation method and abnormality occurrence prediction method

摘要

PROBLEM TO BE SOLVED: To provide an abnormality occurrence prediction device or the like for suitably predicting the occurrence of an abnormality in a processed product. An abnormality occurrence prediction device including a control unit for generating an abnormality occurrence prediction model for predicting the occurrence of an abnormality in a processed product, wherein the control unit includes a data acquisition step S11 for acquiring operation data of a processing facility. The acquired operation data is divided into predetermined time intervals, and a pattern acquisition step S13 for generating a plurality of time series patterns and a plurality of acquired time series patterns are clustered and classified into a plurality of clusters, and each of them is classified into a plurality of clusters. Based on the clustering step S15 for deriving the cluster center of gravity of the cluster and the distance from the cluster center of time of the time series pattern belonging to a predetermined cluster, it is determined whether the time series pattern is normal or abnormal, and the determination result is time. A determination step S16 for labeling the series pattern and a model generation step S17 for generating an abnormality occurrence prediction model based on the determination result determined in the determination step S16 are executed. [Selection diagram] Fig. 2