Construction method of abnormality diagnosis model, abnormality diagnosis method, construction device of abnormality diagnosis model, and abnormality diagnosis device

An abnormality diagnosis device for diagnosing an abnormality of a steel manufacturing process, the device comprising:

• a first regression model creation means for creating a first regression model that sets a regression coefficient regarding an explanatory variable with a small influence on a response variable to zero by using all operational data in normal times collected in advance;
• an explanatory variable candidate determination means for dividing the operational data into a plurality of segments determined in advance and determines an explanatory variable candidate for each of the segments within a range of the explanatory variable used in the first regression model, wherein the plurality of segments include a product variety, a product size, an operating condition, and an operating pattern;
• a second regression model creation means for creating a second regression model that sets a regression coefficient regarding an explanatory variable candidate with a small influence on a response variable to zero by using the operational data included in the segment;
• an input unit for receiving the operational data including sensor data from a facility performing the steel manufacturing process via an information and control system network;
• an abnormality diagnosis means for calculating an abnormality index by using a second regression model according to a segment of the received operational data to be diagnosed;
• an abnormality determination means for determining whether or not there is an abnormality based on the abnormality index;
• and
• a display unit for displaying the determination result to provide guidance to an operator for stable operation, wherein
• maintenance is performed based on the determination result for the stable operation.