Diagnosis device and diagnosis method for plant

1. A diagnosis device for diagnosing a plant based on an operating state of the plant, comprising:

a memory configured to store a program; and

a processor configured to execute the program and control the diagnosis device to:

acquire a plurality of monitoring data which are measurement values of a parameter related to the operating state of the plant, the plurality of monitoring data being measured at different times;

generate a diagnosis target pattern that is a plot pattern where each of the plurality of monitoring data is plotted against plant output data of the plant; and

diagnose the plant by comparing the plot pattern of the diagnosis target pattern with a plot pattern of the plant in a normal state, each of the plot patterns being an overall shape of plots.

2. The diagnosis device according to claim 1 ,

wherein the processor is further configured to execute the program and control the diagnosis device to diagnose the plant as abnormal if it is determined that the diagnosis target pattern has a predetermined abnormal characteristic plot pattern that is a specific plot pattern by which abnormality of the plant is identifiable.

3. The diagnosis device according to claim 2 ,

wherein the processor is further configured to execute the program and control the diagnosis device to determine that the diagnosis target pattern has the abnormal characteristic plot pattern if the diagnosis target pattern has a plot pattern with at least a predetermined degree of similarity to the abnormal characteristic plot pattern.

4. The diagnosis device according to claim 1 , wherein the processor is further configured to execute the program and control the diagnosis device to classify each of the plurality of monitoring data according to a predetermined operating pattern of the plant,

and to generate the diagnosis target pattern for each operating pattern.

5. The diagnosis device according to claim 4 , wherein the processor is further configured to execute the program and control the diagnosis device to diagnose the plant based on comparison between each of the plurality of monitoring data and a threshold.

6. The diagnosis device according to claim 5 , wherein the processor is further configured to execute the program and control the diagnosis device to store the diagnosis target pattern generated for each operating pattern if the plant is not diagnosed as abnormal by pattern diagnosis but is diagnosed as abnormal by threshold diagnosis.

7. The diagnosis device according to claim 4 ,

wherein the plant includes a plurality of devices, and

wherein the operating pattern is set based on an operating state of a target device including at least one of the plurality of devices.

8. The diagnosis device according to claim 1 ,

wherein the plant is a power generation plant including a generator.

9. A diagnosis method for diagnosing a plant based on an operating state of the plant, comprising:

a monitoring data acquisition step of acquiring a plurality of monitoring data which are measurement values of a parameter related to the operating state of the plant, the plurality of monitoring data being measured at different times;

a diagnosis target pattern generation step of generating a diagnosis target pattern that is a plot pattern obtained by plotting each of the plurality of monitoring data against plant output data of the plant; and

a pattern diagnosis step of diagnosing the plant by comparing the plot pattern of the diagnosis target pattern with a plot pattern of the plant in a normal state, each of the plot patterns being an overall shape of plots.

10. The diagnosis method according to claim 9 ,

wherein the pattern diagnosis step includes an abnormality diagnosis step of diagnosing the plant as abnormal if it is determined that the diagnosis target pattern has a predetermined abnormal characteristic plot pattern that is a specific plot pattern by which abnormality of the plant is identifiable.

11. The diagnosis method according to claim 10 ,

wherein the abnormality diagnosis step includes determining that the diagnosis target pattern has the abnormal characteristic plot pattern if the diagnosis target pattern has a plot pattern with at least a predetermined degree of similarity to the abnormal characteristic plot pattern.

12. The diagnosis method according to claim 9 , further comprising a monitoring data classification step of classifying each of the plurality of monitoring data according to a predetermined operating pattern of the plant,

wherein the diagnosis target pattern generation step includes generating the diagnosis target pattern for each operating pattern.

13. The diagnosis method according to claim 12 , further comprising a threshold diagnosis step of diagnosing the plant based on comparison between each of the plurality of monitoring data and a threshold.

14. The diagnosis method according to claim 13 , further comprising a diagnosis target pattern storage step of storing the diagnosis target pattern generated for each operating pattern if the plant is not diagnosed as abnormal in the pattern diagnosis step but is diagnosed as abnormal in the threshold diagnosis step.

15. The diagnosis method according to claim 12 ,

wherein the plant includes a plurality of devices, and

wherein the operating pattern is set based on an operating state of a target device including at least one of the plurality of devices.

16. The diagnosis method according to claim 9 ,

wherein the plant is a power generation plant including a generator.