Abstract: A method of monitoring for combustion anomalies in a gas turbomachine includes sensing an exhaust gas temperature at each of a plurality of temperature sensors arranged in an exhaust system of the gas turbomachine, comparing the exhaust gas temperature at each of the plurality of temperature sensors with a mean exhaust gas temperature, determining whether the exhaust gas temperature at one or more of the plurality of temperature sensors deviates from the mean exhaust temperature by a predetermined threshold value, and identifying an instantaneous combustion anomaly at one or more of the temperature sensors sensing a temperature deviating from the mean exhaust temperature by more than the predetermined threshold value.

Abstract: A system for detecting an at-fault combustor includes a sensor that is configured to sense combustion dynamics pressure data from the combustor and a computing device that is in electronic communication with the sensor and configured to receive the combustion dynamics pressure data from the sensor. The computing device is programmed to convert the combustion dynamics pressure data into a frequency spectrum, segment the frequency spectrum into a plurality of frequency intervals, extract a feature from the frequency spectrum, generate feature values for the feature within a corresponding frequency interval over a period of time, and to store the feature values to generate a historical database. The computing device is further programmed to execute a machine learning algorithm using the historical database of the feature values to train the computing device to recognize feature behavior that is indicative of an at-fault combustor.

Abstract: A method of monitoring for combustion anomalies in a gas turbomachine includes sensing an exhaust gas temperature at each of a plurality of temperature sensors arranged in an exhaust system of the gas turbomachine, comparing the exhaust gas temperature at each of the plurality of temperature sensors with a mean exhaust gas temperature, determining whether the exhaust gas temperature at one or more of the plurality of temperature sensors deviates from the mean exhaust temperature by a predetermined threshold value, and identifying an instantaneous combustion anomaly at one or more of the temperature sensors sensing a temperature deviating from the mean exhaust temperature by more than the predetermined threshold value.

Abstract: A system for assessing combustor health during operation of the combustor includes a combustor, a sensor configured to sense combustion dynamics pressure data from the combustor, and a computing device that is in communication with the sensor and configured to receive the combustion dynamics pressure data from the sensor. The computing device is programed to extract a feature from the combustion dynamics pressure data and generate feature values for the feature over a period of time. The computing device is also programmed to generate a cumulative form of the feature that is based on the feature values over a time series and to compare the cumulative form to a historical cumulative form.

Abstract: A system for detecting an at-fault combustor includes a sensor that is configured to sense combustion dynamics pressure data from the combustor and a computing device that is in electronic communication with the sensor and configured to receive the combustion dynamics pressure data from the sensor. The computing device is programmed to convert the combustion dynamics pressure data into a frequency spectrum, segment the frequency spectrum into a plurality of frequency intervals, extract a feature from the frequency spectrum, generate feature values for the feature within a corresponding frequency interval over a period of time, and to store the feature values to generate a historical database. The computing device is further programmed to execute a machine learning algorithm using the historical database of the feature values to train the computing device to recognize feature behavior that is indicative of an at-fault combustor.