System and method for diagnosing faults utilizing baseline modeling techniques

• US 7,383,165 B2
• Filed: 12/30/2003
• Issued: 06/03/2008
• Est. Priority Date: 08/17/2001
• Status: Expired due to Term

• Current Assignee: General Electric Company
• Original Assignee: General Electric Company
• Inventors: Aragones, James Kenneth
• Primary Examiner(s): Rodriguez; Paul L
• Assistant Examiner(s): Thangavelu; Kandasamy
• Application Number:
  US10/707,656
• Publication Number:
  US 20040172228A1
• Time in Patent Office: 1,617 Days
• Field of Search: 703/8, 705/10, 705/8, 707/104.1, 701/100, 701/14, 701/111, 701/29, 700/272, 702/182, 702/185, 345/713, 750/10, 750/8
• US Class Current: 703/8
• CPC Class Codes: G05B 17/02 electric
• CPC Class Codes: Y10S 707/99945 Object-oriented database structure processing
• CPC Class Codes: Y10S 707/99948 Application of database or data structure, e.g. distributed, multimedia, or image

Abstract

System, method and computer product for baseline modeling a product or process. A service database contains process data. A preprocessor processes the data into a predetermined format. A baseline modeling component builds a baseline model from the preprocessed data, wherein the baseline model relates process performance variables as a function of process operating conditions.

Claims

1. A system for building an engine baseline model for fuel-powered engines, comprising:

a computer comprising;

one or more processors;

a memory configured to store a program of instructions;

an engine service database containing engine data for fuel-powered engines;

a data segmenting component that segments the engine data into a plurality of groups, and each group clusters a portion of the engine data based on similarities in data of engine operating parameters, based on each specific engine, and based on time periods of data acquisition; and

an engine baseline modeling component that builds an engine baseline model for each of the plurality of groups using regression analysis, wherein the regression analysis relates engine performance variables as functions of the engine operating parameters as related by the engine baseline model for a group; and

a display configured to display the engine performance variables as functions of the engine operating parameters as related by the engine baseline model for a group.

2. The system of claim 1, wherein the data segmenting component segments the engine data into the plurality of groups throughout a pre-selected moving time window.

3. The system of claim 1, wherein the data segmenting component segments the engine data into the plurality of groups throughout discrete time ranges.

4. The system of claim 1, wherein the engine baseline modeling component generates a set of estimated regression parameters for each of the plurality of groups based upon the regression analysis, wherein each set of estimated regression parameters are representative of the baseline model for that group.

5. The system of claim 4, wherein the engine baseline modeling component calculates a time series for each estimated regression parameter, and wherein the engine baseline modeling component further calculates a trend for each estimated regression parameter over time.

6. The system of claim 4, further comprising:

means for identifying fluctuations in trends for each estimated regression parameter representative of engine faults;

means for evaluating trends having identified fluctuations; and

means for identifying parameters estimating trends relating to baseline trend shifts.

7. The system of claim 1, further comprising a preprocessor that comprises a data acquisition component that extracts engine data from the engine service database.

8. The system of claim 7, wherein the preprocessor maps engine data to an uncorrelated data set using a principal component analysis technique.

9. The system of claim 8, wherein the engine baseline modeling component comprises a heuristics component that generates rules for cleaning the preprocessed data.

10. The system of claim 1, wherein the engine baseline modeling component comprises a metric component that validates the engine baseline model.

11. The system of claim 1, further comprising a model diagnostics component that evaluates performance of the engine baseline model.

12. The system of claim 1, wherein the engine service database comprises historical service information.

13. The system of claim 1, wherein the plurality of groups comprise a plurality of different engine performance variables.

14. The system of claim 1, wherein the each group represents a cluster of similar data of engine operating parameters comprising altitude, air speed, air temperature, fuel specific heat value, air humidity, control settings, or a combination thereof.

15. A computer implemented method for building an engine baseline model for fuel-powered engines, comprising:

storing engine data in an engine service database for fuel-powered engines;

processing the engine data into a predetermined format in a preprocessor, wherein the processing includes segmenting the engine data into a plurality of groups based upon similarities in data of engine operating parameters, based on each specific engine and further based upon specific time periods during which each data was measured;

building an engine baseline model for each of the plurality of groups using regression analysis, wherein the regression analysis relates engine performance variables as functions of the engine operating parameters;

using the engine baseline model to monitor engine status, predict future engine behavior, diagnose engine faults, identify when engine performance is out of specification or identify engine quality, or a combination thereof.

16. The method of claim 15, further comprising segmenting the engine data into the plurality of groups throughout a pre-selected moving time window.

17. The method of claim 15, further comprising segmenting the engine data into the plurality of groups throughout discrete time ranges.

18. The method of claim 15, further comprising generating a set of estimated regression parameters for each of the plurality of groups based upon the regression analysis, wherein each set of estimated regression parameters are representative of the baseline model for that group.

19. The method of claim 18, further comprising:

calculating a time series for each estimated regression parameter; and

calculating a trend for each estimated regression parameter over time.

20. The method of claim 18, further comprising:

identifying fluctuations in trends for each estimated regression parameter representative of engine faults;

evaluating trends having identified fluctuations; and

identifying parameters estimating trends relating to baseline trend shifts.

21. The method of claim 15, wherein the processing step further comprising extracting engine data from the engine service database.

22. The method of claim 21, further comprising mapping engine data to an uncorrelated data set using a principal component analysis technique.

23. The method of claim 22, further comprising generating rules for cleaning the preprocessed data.

24. The method of claim 15, further comprising validating the engine baseline model.

25. The method of claim 15, further comprising evaluating performance of the engine baseline model.

26. The method of claim 15, wherein the engine service database comprises engine repair history.

27. The method of claim 15, wherein the plurality of groups are representative of different clusters of similar data of engine operating parameters comprising altitude, air speed, air temperature, fuel specific heat value, air humidity, control settings, or a combination thereof.

28. A computer-readable storage medium incorporating computer instructions which when executed on a computer perform a process for building an engine baseline model for fuel-powered engines, comprising:

instructions for storing engine data in an engine service database for fuel-powered engines;

instructions for processing the engine data into a predetermined format in a preprocessor, wherein the instructions for processing include instructions for segmenting the engine data into a plurality of groups based upon similarities in data of engine operating parameters, and further based upon specific time periods during which each data was measured;

instructions for building an engine baseline model for each of the plurality of groups using regression analysis, wherein the regression analysis relates engine performance variables as functions of the engine operating parameters;

instructions for using the engine baseline model to monitor engine status, predict future engine behavior, diagnose engine faults, identify when engine performance is out of specification or identify engine quality, or a combination thereof.

29. The computer-readable storage medium of claim 28, further comprising instructions for segmenting the engine data into the plurality of groups throughout a pres-selected moving time window.

30. The computer-readable storage medium of claim 28, further comprising instructions for segmenting the engine data into the plurality of groups throughout discrete time ranges.

31. The computer-readable storage medium of claim 28, further comprising instructions for generating a set of estimated regression parameters for each of the plurality of groups based upon the regression analysis, wherein each set of estimated regression parameters are representative of the baseline model for that group.

32. The computer-readable storage medium of claim 31, further comprising:

instructions for calculating a time series for each estimated regression parameter; and

instructions for calculating a trend for each estimated regression parameter over time.

33. The computer-readable storage medium of claim 31, further comprising:

instructions for identifying fluctuations in trends for each estimated regression parameter representative of engine faults;

instructions for evaluating trends having identified fluctuations; and

instructions for identifying parameters estimating trends relating to baseline trend shifts.

34. The computer-readable storage medium of claim 28, wherein the instructions for processing in the preprocessor further comprise instructions for extracting engine data from the engine service database.

35. The computer-readable storage medium of claim 34, further comprising instructions for mapping engine data to an uncorrelated data set using a principal component analysis technique.

36. The computer-readable storage medium of claim 35, further comprising instructions for generating rules for cleaning the preprocessed data.

37. The computer-readable storage medium of claim 28, further comprising instructions for validating the engine baseline model.

38. The computer-readable storage medium of claim 28, further comprising instructions for evaluating performance of the engine baseline model.

39. The computer-readable storage medium of claim 28, wherein the plurality of groups are representative of different clusters of similar data of engine operating parameters comprising altitude, air speed, air temperature, fuel specific heat value, air humidity, control settings, or a combination thereof.

40. A computer implemented method for building an engine baseline model for combustion-based engines, comprising:

storing engine data in an engine service database for combustion-based engines;

clustering the engine data into a plurality of groups each based on similarities in data of engine operating parameters, based on each specific engine, and based on time periods of data acquisition;

building an engine baseline model for each of the plurality of groups using regression analysis, wherein the regression analysis relates engine performance variables as functions of the engine operating parameters; and

displaying the engine performance variables as functions of the engine operating parameters as related by the engine baseline model for a group.

41. A computer-readable storage medium incorporating computer instructions, which when executed on a computer perform a process for building an engine baseline model for combustion-based engines, comprising:

instructions for storing engine data in an engine service database for combustion-based engines;

instructions for segmenting the engine data into a plurality of groups representative of different clusters of similar data of engine operating parameters comprising altitude, air speed, air temperature, fuel specific heat value, air humidity, control settings or a combination thereof;

instructions for building an engine baseline model for each of the plurality of groups using regression analysis, wherein the regression analysis relates engine performance variables as functions of engine operating parameters; and

instructions for displaying the engine performance variables as functions of the engine operating parameters as related by the engine baseline model for a group.