Abnormality diagnosis device and abnormality diagnosis method

An abnormality diagnosis method comprising:

• detecting whether each of observed values acquired from equipment is normal or abnormal;
• upon detecting an abnormal observed value among the observed values, calculating an abnormality degree that is an evaluation value obtained by discretizing the abnormal observed value into a plurality of levels based on a difference from a constraint set for the abnormal observed value;
• storing a cause correspondence table in which a cause of an abnormal mode of the equipment identified in fault tree analysis is associated with each of patterns of observed values, wherein
• the patterns are each defined by a combination of abnormal observed values respectively having abnormality degrees of specific levels;
• based on the abnormality degree that has been calculated, estimating a cause of an abnormality in the equipment using the cause correspondence table, by identifying which of the patterns corresponds to the observed values acquired from the equipment;
• and
• transmitting a notification of a fact that the abnormal mode has occurred and the cause of the abnormality in the equipment.

A non-transitory computer-readable recording medium that stores a program for causing a computer of an abnormality diagnosis device to execute:

• detecting whether each of observed values acquired from equipment is normal or abnormal;
• upon detecting an abnormal observed value among the observed values, calculating an abnormality degree that is an evaluation value obtained by discretizing the abnormal observed value into a plurality of levels based on a difference from a constraint set for the abnormal observed value;
• storing a cause correspondence table in which a cause of an abnormal mode of the equipment identified in fault tree analysis is associated with each of patterns of observed values, wherein
• the patterns are each defined by a combination of abnormal observed values respectively having abnormality degrees of specific levels;
• based on the abnormality degree that has been calculated, estimating a cause of an abnormality in the equipment using the cause correspondence table, by identifying which of the patterns corresponds to the observed values acquired from the equipment;
• and
• transmitting a notification of a fact that the abnormal mode has occurred and the cause of the abnormality in the equipment.