Clustering system and method for blade erosion detection

• US 20050288901A1
• Filed: 06/28/2004
• Published: 12/29/2005
• Est. Priority Date: 06/28/2004
• Status: Active Grant

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Mylaraswamy, Dinkar, Nwadiogbu, Emmanuel O., Vhora, Mohamad Hanif Y.
• Granted Patent: US 7,254,491 B2
• Time in Patent Office: Days
• US Class Current: 702/185
• CPC Class Codes: F01D 17/085 to temperature
• CPC Class Codes: F01D 21/00 Shutting-down of machines or engines, e.g. in emergency; Regulating, controlling, or safety means not otherwise provided for
• CPC Class Codes: F05D 2260/80 Diagnostics
• CPC Class Codes: F05D 2270/11 to prolong engine life

Abstract

A system and method for detecting erosion in turbine engine blades is provided. The blade erosion detection system includes a sensor data processor and a cluster analysis mechanism. The sensor data processor receives engine sensor data, including exhaust gas temperature (EGT) data, and augments the sensor data to determine sensor data residual values and the rate of change of the sensor data residual values. The augmented sensor data is passed to the cluster analysis mechanism. The cluster analysis mechanism analyzes the augmented sensor data to determine the likelihood that compressor blade erosion has occurred. Specifically, the cluster analysis mechanism performs a 2-tuple cluster feature analysis using Gaussian density functions that provide approximations of normal and eroded blades in a turbine engine. The 2-tuple cluster feature analysis thus provides the probability that the sensor data indicates erosion has occurred in the turbine engine.

Claims

1. An erosion detection system for detecting erosion in blades in a turbine engine, the erosion detection system comprising:

a sensor data processor, the sensor data processor receiving engine sensor data from the turbine engine and generating sensor data residuals and sensor data residual slopes from the sensor data; and

a cluster analysis mechanism, the cluster analysis mechanism performing a cluster analysis on the sensor data residuals and sensor data residual slopes to determine a likelihood that erosion has occurred in the blades.

2. The system of claim 1 wherein the blades comprise compressor blades.

3. The system of claim 1 wherein the sensor data processor generates sensor data residuals by comparing the sensor data to expected sensor values provided from a turbine engine model.

4. The system of claim 1 wherein the sensor data processor generates sensor data residual slopes by performing a linear trend fit on a set of sensor data residuals.

5. The system of claim 1 wherein the sensor data comprises exhaust gas temperature data.

6. The system of claim 1 wherein the cluster analysis mechanism performs a cluster analysis on the sensor data residuals and sensor data residual slopes using a first Gaussian density function representing a good turbine blade cluster and a second Gaussian density function representing an eroded turbine blade cluster.

7. The system of claim 1 wherein the cluster analysis mechanism performs a cluster analysis using sensor data residuals and sensor data residual slopes by using the sensor data residuals and sensor data residual slopes as 2-tuples from non-eroded blades and 2-tuples from eroded blades that are approximated using Gaussian density functions.

8. The system of claim 7 wherein the Gaussian density functions are determined during an offline training phase using historical data.

9. The system of claim 8 wherein the Gaussian density functions are rotated appropriately to fit the historical data.

10. The system of claim 1 wherein the cluster analysis mechanism calculates the likelihood that the sensor data corresponds to an engine with non-eroded blades and corresponds to an engine with eroded blades.

11. The system of claim 10 wherein the cluster analysis mechanism further uses a Bayesian rule to determine the probability of eroded blades in the turbine engine.

12. A method of detecting erosion in blades in a turbine engine, the method comprising the steps of:

a) receiving sensor data from the turbine engine;

b) generating sensor data residuals and sensor data residual slopes from the received sensor data; and

c) determining a likelihood of erosion in the blades through a cluster analysis on the sensor data residuals and sensor data residual slopes.

13. The method of claim 12 wherein the blades comprise compressor blades.

14. The method of claim 12 wherein the step of generating sensor data residuals comprises comparing the sensor data to expected sensor values provided from a turbine engine model.

15. The method of claim 12 wherein the step of generating sensor data residuals and sensor data residual slopes comprises generating sensor data residual slopes by performing a linear trend fit on a set of sensor data residuals.

16. The method of claim 12 wherein the sensor data comprises exhaust gas temperature data.

17. The method of claim 12 wherein the step of determining a likelihood of erosion in the turbine blades through a cluster analysis on the sensor data residuals and sensor data residual slopes comprises performing a cluster analysis on the sensor data residuals and sensor data residual slopes using a first Gaussian density function representing a good turbine blade cluster and a second Gaussian density function representing a eroded turbine blade cluster.

18. The method of claim 12 wherein the step of determining a likelihood of erosion in the turbine blades through a cluster analysis on the sensor data residuals and sensor data residual slopes comprises using the sensor data residuals and sensor data residual slopes as 2-tuples from non-eroded blades and 2-tuples from eroded blades that are approximated using Gaussian density functions.

19. The method of claim 18 further comprising the step of determining the Gaussian density functions during an offline training phase using historical data.

20. The method of claim 19 wherein the Gaussian density functions are rotated appropriately to fit the historical data.

21. The method of claim 12 wherein the step of determining a likelihood of erosion in the turbine blades through a cluster analysis on the sensor data residuals and sensor data residual slopes comprises calculating a likelihood that the sensor data corresponds to an engine with non-eroded blades and corresponds to an engine with eroded blades.

22. The method of claim 21 wherein the step of calculating a likelihood that the sensor data corresponds to an engine with non-eroded blades and corresponds to an engine with eroded blades comprises using a Bayesian rule to determine the probability of eroded blades in the turbine engine.

23. A program product comprising:

a) an erosion detection for detecting erosion in blades in a turbine engine, the erosion detection program including;

a sensor data processor, the sensor data processor receiving engine sensor data from the turbine engine and generating sensor data residuals and sensor data residual slopes from the sensor data; and

a cluster analysis mechanism, the cluster analysis mechanism performing a cluster analysis on the sensor data residuals and sensor data residual slopes to determine a likelihood that erosion has occurred in the blades; and

b) signal bearing media bearing said erosion detection program.

24. The program product of claim 23 wherein the signal bearing media comprises recordable media.

25. The program product of claim 23 wherein the signal bearing media comprises transmission media.

26. The program product of claim 23 wherein the wherein the blades comprise compressor blades.

27. The program product of claim 23 wherein the sensor data processor generates sensor data residuals by comparing the sensor data to expected sensor values provided from a turbine engine model.

28. The program product of claim 23 wherein the sensor data processor generates sensor data residual slopes by performing a linear trend fit on a set of sensor data residuals.

29. The program product of claim 23 wherein the sensor data comprises exhaust gas temperature data.

30. The program product of claim 23 wherein the cluster analysis mechanism performs a cluster analysis on the sensor data residuals and sensor data residual slopes using a first Gaussian density function representing a good turbine blade cluster and a second Gaussian density function representing an eroded turbine blade cluster.

31. The program product of claim 30 wherein the Gaussian density functions are determined during an offline training phase using historical data.

32. The program product of claim 31 wherein the Gaussian density functions are rotated appropriately to fit the historical data.

33. The program product of claim 23 wherein the cluster analysis mechanism calculates the likelihood that the sensor data corresponds to an engine with non-eroded blades and corresponds to an engine with eroded blades.

34. The program product of claim 33 wherein the cluster analysis mechanism further uses a Bayesian rule to determine the probability of eroded blades in the turbine engine.