초록 ▼

A transient fault detection system and method is provided that facilitates improved fault detection performance in transient conditions. The transient fault detection system provides the ability to detect symptoms of fault in engine that occur in transient conditions. The transient fault detection

A transient fault detection system and method is provided that facilitates improved fault detection performance in transient conditions. The transient fault detection system provides the ability to detect symptoms of fault in engine that occur in transient conditions. The transient fault detection system includes a feature extractor that measures sensor data during transient conditions and extracts salient features from the measured sensor data. The extracted salient features are passed to a classifier that analyzes the extracted salient features to determine if a fault has occurred during the transient conditions. Detected faults can then be passed to a diagnostic system where they can be passed as appropriate to maintenance personnel.

대표청구항 ▼

The invention claimed is: 1. A transient fault detection system for detecting transient faults in a turbine engine, the transient fault detection system comprising: a) a feature extractor, the feature extractor receiving measured turbine sensor data from the turbine engine during a transient condit

The invention claimed is: 1. A transient fault detection system for detecting transient faults in a turbine engine, the transient fault detection system comprising: a) a feature extractor, the feature extractor receiving measured turbine sensor data from the turbine engine during a transient condition, the feature extractor performing a principal component analysis, the principal component analysis extracting salient features from the measured turbine sensor data by transforming the measured sensor data into a substantially smaller set of uncorrelated variables; and b) a classifier, the classifier receiving the extracted salient features and analyzing the extracted salient features to determine if a fault occurred during the transient condition, and wherein the classifier comprises a multilayer perceptron neural network classifier. 2. The system of claim 1 wherein the neural network classifier is trained using a leave-one out method. 3. The system of claim 1 wherein the neural network classifier is trained using sensor data including a plurality of known good transient condition data sets and a plurality of known bad transient condition data sets. 4. The system of claim 1 wherein the feature extractor extracts principal components selected to improve performance of the classifier. 5. The system of claim 1 wherein tile sensor data comprises engine speed. 6. The system of claim 1 wherein the sensor data comprises exhaust gas temperature. 7. The system of claim 1 wherein the transient condition comprises turbine engine startup. 8. An apparatus comprising: a) a processor; b) a memory coupled to the processor; c) a transient fault detection program residing in the memory and being executed by the processor, the transient fault detection program including: i) a feature extractor, the feature extractor receiving measured turbine sensor data from the turbine engine during a transient condition, the feature extractor performing a principal component analysis, the principal component analysis extracting salient features from the measured turbine sensor data, by transforming the measured sensor data into a substantially smaller set of uncorrelated variables; and ii) a classifier, the classifier receiving the extracted salient features and analyzing the extracted salient features to determine if a fault occurred during the transient condition, and wherein the classifier comprises a multilayer perceptron neural network classifier. 9. The apparatus of claim 8 wherein the neural network classifier is trained using a leave-one out method. 10. The apparatus of claim 8 wherein the neural network classifier is trained using sensor data including a plurality of known good transient condition data sets and a plurality of known bad transient condition data sets. 11. The apparatus of claim 8 wherein the feature extractor extracts principal components selected to improve performance of the classifier. 12. The apparatus of claim 8 wherein the sensor data comprises engine speed. 13. The apparatus of claim 8 wherein the sensor data comprises exhaust gas temperature. 14. The apparatus of claim 8 wherein the transient condition comprises turbine engine startup. 15. A program product comprising: a) a transient fault detection program, the transient fault detection program including: i) a feature extractor, the feature extractor receiving measured turbine sensor data from the turbine engine during a transient condition, the feature extractor performing a principal component analysis, the principal component analysis extracting salient features from the measured turbine sensor data, by transforming the measured sensor data into a substantially smaller set of uncorrelated variables; and ii) a classifier, the classifier receiving the extracted salient features and analyzing the extracted salient features to determine if a fault occurred during the transient condition, and wherein the classifier comprises a multilayer perceptron neural network classifier; and b) computer-readable signal bearing media bearing said program. 16. The program product of claim 15 wherein the computer-readable signal bearing media comprises recordable media. 17. The program product of claim 15 wherein the computer-readable signal bearing media comprises transmission media. 18. The program product of claim 15 wherein the neural network classifier is trained using a leave-one out method. 19. The program product of claim 15 wherein the neural network classifier is trained using sensor data including a plurality of known good transient condition data sets and a plurality of known bad transient condition data sets. 20. The program product of claim 15 wherein the feature extractor extracts principal components selected to improve performance of the classifier. 21. The program product of claim 15 wherein the sensor data comprises engine speed. 22. The program product of claim 15 wherein the sensor data comprises exhaust gas temperature. 23. The program product of claim 15 wherein the transient condition comprises turbine engine startup. 24. A method of detecting faults in transient conditions in a turbine engine, the method comprising the steps of: a) receiving measured turbine sensor data from the turbine engine during a transient condition; b) extracting salient features from the measured turbine sensor data by performing a principal component analysis on the measured sensor data, the principal component analysis transforming the measured sensor data into a substantially smaller set of uncorrelated variables; and c) classifying the extracted salient features with a multilayer perceptron neural network to determine if a fault occurred during the transient condition. 25. The method of claim 24 further comprising the step of training the neural network classifier using a plurality of known good transient condition data sets and a plurality of known bad transient condition data sets. 26. The method of claim 25 wherein the step of training the neural network classifier comprises training using a leave-one out method. 27. The method of claim 24 where the step of extracting salient features comprises extracting principal components selected to improve performance of the classifying step. 28. The method of claim 24 wherein the sensor data comprises engine speed. 29. The method of claim 24 wherein the sensor data comprises exhaust gas temperature. 30. The method of claim 24 wherein the transient condition comprises turbine engine startup.