Bivariate optimization technique for tuning sprt parameters to facilitate prognostic surveillance of sensor data from power plants

A non-transitory, computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for performing prognostic surveillance operations based on sensor signals from a power plant and associated transmission grid, the method comprising:

• obtaining signals comprising time-series data obtained from sensors in the power plant and associated transmission grid during operation of the power plant and associated transmission grid;
• using an inferential model trained on previously received signals from the power plant and associated transmission grid to generate estimated values for the signals based on correlations between the signals;
• performing a pairwise differencing operation between actual values and the estimated values for the signals to produce residuals;
• performing a sequential probability ratio test (SPRT) on the residuals to detect incipient anomalies that arise during operation of the power plant and associated transmission grid;
• while performing the SPRT, dynamically updating SPRT parameters to compensate for non-Gaussian artifacts that arise in the sensor data due to changing operating conditions in the power plant and associated transmission grid;
• and
• when an incipient anomaly is detected, generating a notification regarding the anomaly.

A system that performs prognostic surveillance operations based on sensor signals from a power plant and associated transmission grid, comprising:

• at least one processor and at least one associated memory;
• and
• an anomaly-detection mechanism that executes on the at least one processor, wherein during operation, the anomaly-detection mechanism:
• obtains signals comprising time-series data obtained from sensors in the power plant and associated transmission grid during operation of the power plant and associated transmission grid;
• uses an inferential model trained on previously received signals from the power plant and associated transmission grid to generate estimated values for the signals based on correlations between the signals;
• performs a pairwise differencing operation between actual values and the estimated values for the signals to produce residuals;
• performs a sequential probability ratio test (SPRT) on the residuals to detect incipient anomalies that arise during operation of the power plant and associated transmission grid;
• wherein while performing the SPRT, the anomaly-detection mechanism dynamically updates SPRT parameters to compensate for non-Gaussian artifacts that arise in the sensor data due to changing operating conditions in the power plant and associated transmission grid;
• and
• wherein when an incipient anomaly is detected, the anomaly-detection mechanism generates a notification regarding the anomaly.