SYSTEMS AND METHODS FOR ENGINE DIAGNOSIS USING WAVELET TRANSFORMATIONS

• US 20090326754A1
• Filed: 06/30/2008
• Published: 12/31/2009
• Est. Priority Date: 06/30/2008
• Status: Abandoned Application

• Current Assignee: Honeywell International Inc.
• Original Assignee: Honeywell International Inc.
• Inventors: Mylaraswany, Dinkar, Shetty, Pradeep, Ryali, Srikanth
• Application Number:
  US12/165,267
• Publication Number:
  US 20090326754A1
• Time in Patent Office: Days
• US Class Current: 701/29
• CPC Class Codes: G05B 23/0221 Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
• CPC Class Codes: G05B 23/0281 Quantitative, e.g. mathematical distance; Clustering; Neural networks; Statistical analysis

Abstract

A method for performing diagnosis on an engine includes the steps of obtaining data for a plurality of variables pertaining to the engine, transforming the data with respect to each of the plurality of variables using a wavelet transformation, to thereby generate initial coefficients for each of the plurality of variables, and aggregating the initial coefficients for each of the plurality of variables, to thereby generate an aggregate set of coefficients for the plurality of variables.

Claims

1. A method for performing diagnosis on an engine of a vehicle, the method comprising the steps of:

obtaining data for a plurality of variables pertaining to the engine;

transforming the data with respect to each of the plurality of variables using a wavelet transformation, to thereby generate initial coefficients for each of the plurality of variables; and

aggregating the initial coefficients for each of the plurality of variables, to thereby generate an aggregate set of coefficients for the plurality of variables.

2. The method of claim 1, further comprising the step of:

generating a revised set of coefficients for the plurality of variables, based on the aggregate set of coefficients and one or more optimization criteria.3. The method of claim 2, wherein the step of generating the revised set of coefficients comprises the step of;

generating the revised set of coefficients for the plurality of variables based on the aggregate set of coefficients and a mean squared error for the data.

3. The method of claim 2, wherein the step of generating the revised set of coefficients comprises the step of:

generating the revised set of coefficients for the plurality of variables based on the aggregate set of coefficients and a weighted average of a normalized mean squared error for the data.

4. The method of claim 3, wherein the step of generating the revised set of coefficients comprises the step of:

generating the revised set of coefficients for the plurality of variables based on the aggregate set of coefficients, the weighted average of the normalized mean squared error for the data, and a measure representing at least in part a number of values in the data.

5. The method of claim 2, further comprising the step of:

comparing the revised set of coefficients with a fault vector space and a no-fault vector space to determine whether there is a fault in the engine.

6. The method of claim 2, further comprising the step of:

determining boundaries of the fault vector space and the no-fault vector space using a set of actual fault data and using a bootstrap technique.

7. The method of claim 5, further comprising the step of

performing hypothesis testing to determine whether a given set of revised coefficients belongs to the fault or no-fault vector space.

8. The method of claim 1, wherein the steps of transforming the data and aggregating the initial coefficients are operable under limited training data sets and is further operable to provide optimal representation of the data without losing any necessary information.

9. A program product comprising:

an engine diagnostic program configured to at least facilitate;

obtaining data for a plurality of variables pertaining to the engine;

transforming the data with respect to each of the plurality of variables using a wavelet transformation, to thereby generate initial coefficients for each of the plurality of variables; and

aggregating the initial coefficients for each of the plurality of variables, to thereby generate an aggregate set of coefficients for the plurality of variables; and

a computer-readable signal bearing media bearing the engine diagnostic program.

10. The program product of claim 9, wherein the engine diagnostic program is further configured to at least facilitate generating a revised set of coefficients for the plurality of variables, based on the aggregate set of coefficients and one or more optimization criteria.

11. The program product of claim 10, wherein the engine diagnostic program is further configured to at least facilitate generating the revised set of coefficients for the plurality of variables based on the aggregate set of coefficients and a mean squared error for the data.

12. The program product of claim 10, wherein the engine diagnostic program is further configured to at least facilitate generating the revised set of coefficients for the plurality of variables based on the aggregate set of coefficients a weighted average of a normalized mean squared error for the data, and a measure representing at least in part a number of values in the data.

13. The program product of claim 10, wherein the engine diagnostic program is further configured to at least facilitate comparing the revised set of coefficients with a fault vector space and a no-fault vector space to determine whether there is a fault in the engine.

14. The program product of claim 10, wherein the engine diagnostic program is further configured to at least facilitate determining whether there is a fault in the engine based at least in part on the revised set of coefficients and using a bootstrap technique.

15. An engine diagnostic system comprising:

a memory configured to at least facilitate storing data for a plurality of variables pertaining to the engine; and

a processor coupled to the memory and configured to at least facilitate;

transforming the data with respect to each of the plurality of variables using a wavelet transformation, to thereby generate initial coefficients for each of the plurality of variables; and

aggregating the initial coefficients for each of the plurality of variables, to thereby generate an aggregate set of coefficients for the plurality of variables.

16. The engine diagnostic system of claim 15, wherein the processor is further configured to at least facilitate generating a revised set of coefficients for the plurality of variables, based on the aggregate set of coefficients and one or more optimization criteria.

17. The engine diagnostic system of claim 16, wherein the processor is further configured to at least facilitate generating the revised set of coefficients for the plurality of variables based on the aggregate set of coefficients, a weighted average of a normalized mean squared error for the data, and a measure representing at least in part a number of values in the data.

18. The engine diagnostic system of claim 16, wherein the processor is further configured to at least facilitate comparing the revised set of coefficients with a fault vector space and a no-fault vector space to determine whether there is a fault in the engine.

19. The engine diagnostic system of claim 16, wherein the processor is further configured to at least facilitate determining whether there is a fault in the engine based at least in part on the revised set of coefficients and using a bootstrap technique.

20. The engine diagnostic system of claim 19, wherein the processor is configured to at least facilitate transforming the data and aggregating the initial coefficients while addressing time correlation and correlation across variables in the data.