Monitoring device, method for monitoring target device, and program

1. A monitoring device, comprising:

a processor; a memory; and a program in the memory for causing the processor to function as:

an acquisition unit configured to acquire measurement values being measurement values of a target device, the measurement values including at least a temperature and a flow rate of an input fluid to be input to the target device, and a temperature and a flow rate of an output fluid to be output from the target device;

a correction unit configured to acquire correction measurement values by substituting the measurement values to a plurality of thermal equilibrium calculations, calculating combinations of errors for the measurement values, which satisfy the plurality of thermal equilibrium calculations respectively, calculating a total of the errors or a total of squares of the errors for each combination, and selecting the combination so as to obtain the smallest total; and

a distance calculation unit configured to calculate a Mahalanobis distance with a factor of the correction measurement values.

2. The monitoring device according to claim 1 , the program in the memory for causing the processor to further function as:

an atmospheric condition acquisition unit configured to acquire an atmospheric condition including at least one of an atmospheric pressure, an atmospheric temperature, and an atmospheric humidity; and

a normalization unit configured to normalize the correction measurement values to values under a normal atmospheric condition by using the atmospheric condition that is acquired,

wherein the distance calculation unit calculates the Mahalanobis distance based on the normalized correction measurement values.

3. The monitoring device according to claim 1 , the program in the memory for causing the processor to further function as:

a likelihood calculation unit configured to calculate an occurrence likelihood for each of a plurality of phenomena that are liable to occur to the target device based on the correction measurement values when the Mahalanobis distance is equal to or greater than a predetermined value;

a table storage unit configured to store a table in which the plurality of phenomena and occurrence causes of abnormalities of the target device are associated to each other; and

an estimation unit configured to estimate the occurrence causes based on the occurrence likelihood and the table.

4. The monitoring device according to claim 1 , the program in the memory for causing the processor to further function as:

a linearity determination unit configured to determine whether a measurement value indicating a temperature among the measurement values acquired by the acquisition unit falls within a range from a minimum value to a maximum value of a measurement value indicating a temperature, which forms a unit space of the Mahalanobis distance,

wherein the distance calculation unit is prevented from calculating the Mahalanobis distance based on the correction measurement values when the linearity determination unit determined that the measurement value is out of the range from the minimum value to the maximum value of the measurement value indicating the temperature in the unit space.

5. The monitoring device according to claim 1 ,

wherein the acquisition unit acquires the measurement values at a time point after a start-up, which is a time point after elapse of a predetermined start-up period starting from an operation start time point of the target device, and

the distance calculation unit calculates the Mahalanobis distance based on the correction measurement values acquired by the correction unit with the unit space formed by using measurement values at a time point during the predetermined start-up period.

6. A method for monitoring a target device, comprising following steps of:

acquiring measurement values being measurement values of a target device, the measurement values including at least a temperature and a flow rate of an input fluid to be input to the target device, and a temperature and a flow rate of an output fluid to be output from the target device;

acquiring correction measurement values by substituting the measurement values to a plurality of thermal equilibrium calculations, calculating combinations of errors for the measurement values, which satisfy the plurality of thermal equilibrium calculations respectively, calculating a total of the errors or a total of squares of the errors for each combination, and selecting the combination so as to obtain the smallest total; and

calculating a Mahalanobis distance with a factor of the correction measurement values.

7. The method for monitoring a target device according to claim 6 , further comprising following steps of:

acquiring an atmospheric condition including at least one of an atmospheric pressure and an atmospheric humidity; and

normalizing the correction measurement values to values under a normal atmospheric condition by using the atmospheric condition that is acquired,

wherein the Mahalanobis distance is calculated based on the normalized correction measurement values.

8. A non-transitory computer-readable storage medium storing a program, which causes a computer to execute the processing of:

acquiring measurement values being measurement values of a target device, the measurement values including at least a temperature and a flow rate of an input fluid to be input to the target device, and a temperature and a flow rate of an output fluid to be output from the target device;

acquiring correction measurement values by substituting the measurement values to a plurality of thermal equilibrium calculations, calculating combinations of errors for the measurement values, which satisfy the plurality of thermal equilibrium calculations respectively, calculating a total of the errors or a total of squares of the errors for each combination, and selecting the combination so as to obtain the smallest; and

calculating a Mahalanobis distance with a factor of the correction measurement values.