Abstract:
A method for monitoring the health of a compressor of a gas turbine is disclosed. The method includes receiving a plurality of turbine data points, wherein the plurality of turbine data points may include one or more operating parameters, at least one of a computer discharge temperature (CTD), and one or more performance parameters. The plurality of turbine data points may be categorized based on the one or more operating parameters. A statistical variability measure of at least one of the CTD and the one or more performance parameters may be computed for each of the plurality of bands. An alarm indicator may be computed based on the at least one statistical variability measure. The method may also include combining two or more of the operating parameters, the CTD and the performance parameters using sensor fusion techniques. The alarm indicator may be computed based on the combined parameters.
Abstract:
Detection of, among other things, seal leakage(s) and/or seal oil contamination for a gas cooled generator are provided. Detectors according to some embodiments of the invention provide mechanisms of early detection of cooling gas, e.g., hydrogen, leakage through leakage sources as well as low purity and high cooling gas consumption problems in a gas cooled generator.
Abstract:
A coolant flow reduction monitoring system for a rotary electric machine having stator coils within a plurality of slots of a stator thereof is provided. The stator coils are cooled by a coolant flowing in a plurality of passages provided in the stator coils. The system includes an outlet temperature sensor for measuring a coolant outlet temperature of the coolant in an outlet of at least one of the plurality of passages, a slot temperature sensor for measuring a temperature in at least one slot at a location along a length of each slot and outside of the stator coils, and an inlet temperature sensor for measuring a coolant inlet temperature of the coolant. A coolant flow reduction monitor generates an alarm indicating a coolant flow reduction based on the at least one coolant outlet temperature, the at least one slot temperature and the coolant inlet temperature.
Abstract:
A coolant flow reduction monitoring system for a rotary electric machine having stator coils within a plurality of slots of a stator thereof is provided. The stator coils are cooled by a coolant flowing in a plurality of passages provided in the stator coils. The system includes an outlet temperature sensor for measuring a coolant outlet temperature of the coolant in an outlet of at least one of the plurality of passages, a slot temperature sensor for measuring a temperature in at least one slot at a location along a length of each slot and outside of the stator coils, and an inlet temperature sensor for measuring a coolant inlet temperature of the coolant. A coolant flow reduction monitor generates an alarm indicating a coolant flow reduction based on the at least one coolant outlet temperature, the at least one slot temperature and the coolant inlet temperature.
Abstract:
A system for rotor blade health monitoring include time of arrival (TOA) sensors and a controller comprising a processor configured for obtaining TOA signals indicative of times of arrival of rotating rotor blades from the respective TOA sensors and for determining initial features from the TOA signals; and a feature level fuser configured for fusing the initial features received from the processor for use in evaluating health of the rotating rotor blades.
Abstract:
A system, method and computer program product for predicting collector flashover is disclosed. The method includes receiving a frame of measured data from a data acquisition system, fitting a statistical model to the measured data wherein the measured data includes a plurality of measured variables measured at multiple time instances. The statistical model and the measured data are used for estimating one or more parameters for the frame wherein the one or more parameters include at least one of field circuit impedance and field current noise. A flashover is predicted based, at least in part, upon the one or more estimated parameter for the frame.
Abstract:
A system, apparatus, and method (10) for detecting an electrical short condition in a dynamoelectric machine are described. The method includes determining an operating parameter of a dynamoelectric machine (14) responsive to at least one output signal of the dynamoelectric machine and providing a transfer function (16) for predicting a field current of dynamoelectric machine. The method also includes obtaining a value for a predicted field current (18) of the dynamoelectric machine from the transfer function and the operating parameter and identifying a shorted turn condition of the dynamoelectric machine responsive to a difference between the value of the predicted field current and a value of an actual field current of the dynamoelectric machine (24).
Abstract:
A system and method for diagnosis and prognosis of thermal sensitivity in a rotor of an electrical machine. A first system is provided for evaluating thermal sensitivity in a rotor of an electrical machine and includes: an input system for obtaining vibration data and field current from the rotor and for obtaining a set of operating parameter; a system for calculating a relationship between vibration and field current; an evaluation system for determining whether the relationship is significant; and a system for issuing a notification of thermal sensitivity in response to a determination of a significant relationship. A second system includes a system for calculating a series of relationships between vibration and field current over a period of time; an evaluation system for determining whether a change in the series of relationships over the period of time is significant; and a system for issuing a notification of thermal sensitivity in response to a determination of a significant change in the series of relationships.
Abstract:
A method for monitoring the health of a compressor of a gas turbine is disclosed. The method includes receiving a plurality of turbine data points, wherein the plurality of turbine data points may include one or more operating parameters, at least one of a computer discharge temperature (CTD), and one or more performance parameters. The plurality of turbine data points may be categorized based on the one or more operating parameters. A statistical variability measure of at least one of the CTD and the one or more performance parameters may be computed for each of the plurality of bands. An alarm indicator may be computed based on the at least one statistical variability measure. The method may also include combining two or more of the operating parameters, the CTD and the performance parameters using sensor fusion techniques. The alarm indicator may be computed based on the combined parameters.
Abstract:
A system and method for diagnosis and prognosis of thermal sensitivity in a rotor of an electrical machine. A first system is provided for evaluating thermal sensitivity in a rotor of an electrical machine and includes: an input system for obtaining vibration data and field current from the rotor and for obtaining a set of operating parameter; a system for calculating a relationship between vibration and field current; an evaluation system for determining whether the relationship is significant; and a system for issuing a notification of thermal sensitivity in response to a determination of a significant relationship. A second system includes a system for calculating a series of relationships between vibration and field current over a period of time; an evaluation system for determining whether a change in the series of relationships over the period of time is significant; and a system for issuing a notification of thermal sensitivity in response to a determination of a significant change in the series of relationships.