Data-driven unsupervised algorithm for analyzing sensor data to detect abnormal valve operation

A system, comprising:

• a processor;
• and
• a memory containing a program which when executed by the processor performs an operation comprising:
• identifying from a plurality of maintenance messages (MMSGs) a threshold value indicating abnormal operations of a shut-off valve;
• capturing, during a first predefined time period after the shut-off valve is opened, a first plurality of sensor readings related to the shut-off valve;
• capturing, during a second predefined time period after the shut-off valve is closed, a second plurality of sensor readings related to the shut-off valve;
• identifying a first maximum value from the first plurality of sensor readings and a second maximum value from the second plurality of sensor readings;
• and
• in response to determining that a difference between the first maximum value and the second maximum value satisfies the threshold value, generating an alert indicating that the shut-off valve is operating abnormally.

A computer readable storage device including instructions that when executed by a processor enables the processor to perform an operation comprising:

• identifying from a plurality of maintenance messages (MMSGs) a threshold value indicating abnormal operations of a shut-off valve;
• capturing, during a first predefined time period after the shut-off valve is opened, a first plurality of sensor readings related to the shut-off valve;
• capturing, during a second predefined time period after the shut-off valve is closed, a second plurality of sensor readings related to the shut-off valve;
• identifying a first maximum value from the first plurality of sensor readings and a second maximum value from the second plurality of sensor readings;
• and
• in response to determining that a difference between the first maximum value and the second maximum value satisfies the threshold value, generating an alert indicating that the shut-off valve is operating abnormally.