초록 ▼

A method and system is provided for identifying in-range sensor faults in a gas turbine engine, by observing the tracked component qualities in an embedded model and recognizing anomalous patterns of quality changes corresponding to sensor errors. An embedded model of the engine is employed to estim

A method and system is provided for identifying in-range sensor faults in a gas turbine engine, by observing the tracked component qualities in an embedded model and recognizing anomalous patterns of quality changes corresponding to sensor errors. An embedded model of the engine is employed to estimate sensed parameters such as rotor speeds, temperatures and pressures, as well as other parameters that are computed based on input parameters. Each major rotating component of the engine, including the fan, compressor, combustor, turbines, ducts and nozzle is individually modeled. Sensor failures are detected by identifying anomalous patterns in component quality parameters. A library of anomalous patterns is provided for comparing quality parameters generated by a tracking filter with the library of anomalous patterns. If a pattern is matched, a sensor may be eliminated from the tracking filter and the estimated model parameter used to avoid corrupting the model quality parameters.

대표청구항 ▼

We claim: 1. A method for detecting in-range sensor failures in a gas turbine engine, the method comprising the steps of: providing a component level model of a plurality of engine components, the component level model generating a plurality of estimated operating parameters and quality parameters;

We claim: 1. A method for detecting in-range sensor failures in a gas turbine engine, the method comprising the steps of: providing a component level model of a plurality of engine components, the component level model generating a plurality of estimated operating parameters and quality parameters; sensing a plurality of operating parameters associated with the plurality of engine components; comparing the plurality of sensed operating parameters to the plurality of estimated operating parameters of the component level model; generating a set of engine component quality parameters based on the comparison of the plurality of sensed operating parameters to the plurality of estimated operating parameters; storing a library of anomalous patterns, each pattern in the library of anomalous patterns comprising a plurality of known quality parameters corresponding to the generated set of engine component quality parameters; and identifying a malfunctioning sensor in response to the generated set of engine component quality parameters matching at least one of the anomalous patterns. 2. The method as set forth in claim 1, also including substituting at least one of the estimated operating parameters of the component level model for at least one of the sensed operating parameters in response to identifying the malfunctioning sensor. 3. The method as set forth in claim 1, also including the step of updating the quality parameters of the component level model in response to comparing the plurality of sensed operating parameters to the plurality of estimated operating parameters. 4. The method of claim 1, wherein the plurality of engine components includes a fan, a compressor, a high-pressure turbine and a low-pressure turbine. 5. The method of claim 4, wherein the plurality of engine components also includes a booster. 6. The method of claim 4, wherein the quality parameters include a flow parameter and an efficiency parameter. 7. The method of claim 6, wherein at least one of the quality parameters is adjustable from a nominal value. 8. A control system for a gas turbine engine having a plurality of components, the control system comprising: a control module to transmit control commands to the engine; a plurality of component sensors to sense at least one operating parameter associated with each component of the plurality of components; a component level model to generate a plurality of estimated engine component parameters, the component level model comprising an individual model for each component of the plurality of components, each individual model having at least one estimated operating parameter and a plurality of quality parameters; a tracking filter to monitor changes in the sensed operating parameters with respect to the component level model estimated operating parameters, the tracking filter configured to generate an updated set of quality parameters based on the monitored changes; and a pattern recognition module including a data storage unit storing a library of anomalous patterns, each pattern in the library of anomalous patterns comprising a plurality of known quality parameters corresponding to the generated set of engine component quality parameters, the pattern recognition module also including logic configured to identify when the updated set of quality parameters matches at least one anomalous pattern of the library of anomalous patterns, and to determine a failed sensor in response to matching the set of updated quality parameters with at least one anomalous pattern of the library of anomalous patterns. 9. The system set forth in claim 8, wherein the tracking filter is configured to: receive at least one sensed operating parameter for each of the plurality of engine components; compare the received at least one sensed operating parameter with a corresponding estimated operating parameter from the component model; generate a set of quality parameters for a subset of the plurality of engine components; and output the computed set of quality parameters for processing by the pattern recognition module. 10. The system set forth in claim 8, wherein the quality parameters in each individual model are iteratively updated from the updated set of quality parameters. 11. The system set forth in claim 8 wherein the component level model is one of a physics-based model, a regression fit model or a neural network model. 12. The system set forth in claim 8 wherein the library of anomalous patterns are derived from historical data identifying anomalous patterns, or generated by at least one algorithm configured to determine an anomalous pattern. 13. The system set forth in claim 8 wherein the sensed operating parameters include rotor speed, temperature and pressure. 14. The system set forth in claim 8, also including a plurality of computed parameters based on a plurality of input parameters. 15. The system set forth in claim 14 wherein the computed operating parameters include stall margin, thrust and airflow. 16. The system set forth in claim 14 wherein the plurality of input parameters include environmental conditions, power setting and actuator position. 17. The system set forth in claim 8, wherein the control module includes a microprocessor, memory and I/O devices.