Diagnostic device, diagnostic method, and program

A diagnostic method for diagnosing a sign and a cause of abnormality of a plant, comprising:

• receiving from the plant, operation data indicating an operation state of the plant;
• storing first information including a first abnormal event which occurred in the past in the plant, at least one first attribution event that is a cause of the first abnormal event, and a first occurrence probability that is an occurrence probability of the first attribution event, in which a causal relationship between the first abnormal event and the first attribution event is indicated by a tree structure, and second information including a second abnormal event which is supposed to occur in the plant but has not occurred yet, at least one second attribution event that is a cause of the second abnormal event, and a second occurrence probability that is an occurrence probability of the second attribution event, in which a causal relationship between the second abnormal event and the second attribution event is indicated by a tree structure;
• diagnosing an abnormality by detecting the sign of the abnormality in the plant, based on the operation data;
• and
• estimating the cause of the sign of the abnormality based on the first information and the second information when the sign of the abnormality is detected and diagnosed as the abnormality by the diagnosing,
• wherein estimating the cause of the sign of the abnormality includes weighing the first occurrence probability more heavily than the second occurrence probability to estimate the cause of the sign of the abnormality.

A non-transitory computer-readable storage medium on which an executable program for diagnosing a sign and a cause of abnormality of a plant is stored, the program causing a computer to execute:

• receiving from the plant, operation data indicating an operation state of the plant;
• storing first information including a first abnormal event which occurred in the past in the plant, at least one first attribution event that is a cause of the first abnormal event, and a first occurrence probability that is an occurrence probability of the first attribution event, in which a causal relationship between the first abnormal event and the first attribution event is indicated by a tree structure, and second information including a second abnormal event which is supposed to occur in the plant but has not occurred yet, at least one second attribution event that is a cause of the second abnormal event, and a second occurrence probability that is an occurrence probability of the second attribution event, in which a causal relationship between the second abnormal event and the second attribution event is indicated by a tree structure;
• diagnosing an abnormality by detecting the sign of the abnormality in the plant, based on the operation data;
• and
• estimating the cause of the sign of the abnormality based on the first information and the second information when the sign of the abnormality is detected and diagnosed as the abnormality,
• wherein estimating the cause of the sign of the abnormality includes weighing the first occurrence probability more heavily than the second occurrence probability to estimate the cause of the sign of the abnormality.