Surveillance system and method having an adaptive sequential probability fault detection test

• US 7,082,379 B1
• Filed: 12/31/2004
• Issued: 07/25/2006
• Est. Priority Date: 03/08/2002
• Status: Expired due to Term

• Current Assignee: Intellectual Assets LLC
• Original Assignee: Intellectual Assets LLC
• Inventors: Bickford, Randall L., Herzog, James P.
• Primary Examiner(s): Nghiem, Michael
• Assistant Examiner(s): Taylor, Victor J.
• Application Number:
  US11/027,998
• Time in Patent Office: 571 Days
• Field of Search: 702/178, 702/181, 702/185, 700/30, 700/29
• US Class Current: 702/178
• CPC Class Codes: G05B 23/0254 based on a quantitative model, e.g. mathematical relationships between inputs and outputs; functions: observer, Kalman filter, residual calculation, Neural Networks
• CPC Class Codes: G06F 18/24155 Bayesian classification

Abstract

System and method providing surveillance of an asset such as a process and/or apparatus by providing training and surveillance procedures that numerically fit a probability density function to an observed residual error signal distribution that is correlative to normal asset operation and then utilizes the fitted probability density function in a dynamic statistical hypothesis test for providing improved asset surveillance.

Claims

1. A method for performing surveillance of an asset, the steps including:

acquiring residual data correlative to expected asset operation;

fitting a mathematical model to the acquired residual data and storing the mathematical model in a memory means;

collecting a current set of observed signal data values from the asset;

using the mathematical model in a sequential hypotheses test to determine if the current set of observed signal data indicates unexpected operation of the asset that is indicative of a fault condition;

outputting a signal correlative to a detected fault condition for providing asset surveillance.

2. The method of claim 1 wherein the step of acquiring residual data includes a step of acquiring residual data correlative to at least one mode of asset operation.

3. The method of claim 2 wherein the step of acquiring residual data correlative to at least one mode of asset operation includes a step of acquiring past observations of signal data values from the asset and obtaining deviations between the past observations of signal data values and expected signal values obtained by using a model of expected asset operation.

4. The method of claim 1 wherein the step of fitting the mathematical model to the acquired residual data and storing the mathematical model in the memory means includes a step of fitting at least one mathematical function correlative to a frequency distribution to the acquired residual data.

5. The method of claim 4 wherein the step of fitting at least one mathematical function correlative to a frequency distribution to the acquired residual data includes a step of fitting at least one function defining a frequency curve to the acquired residual data.

6. The method of claim 4 wherein the step of fitting at least one mathematical function correlative to a frequency distribution to the acquired residual data includes a step of fitting at least one function defining a frequency histogram to the acquired residual data.

7. The method of claim 4 wherein the step of fitting at least one mathematical function correlative to a frequency distribution to the acquired residual data includes a step of fitting at least one function defining a frequency polygon to the acquired residual data.

8. The method of claim 1 wherein the step of using the mathematical model in the sequential hypotheses test to determine if the current set of observed signal data indicates unexpected operation of the asset that is indicative of a fault condition further includes the step of performing at least one of a group of sequential hypothesis tests comprised of a positive mean test, a negative mean test, a nominal variance test, and a inverse variance test all as a function of the mathematical model.

9. The method of claim 8 wherein the step of performing at least one of the group of sequential hypothesis tests comprised of the positive mean test, the negative mean test, the nominal variance test, and the inverse variance test all as a function of the mathematical model includes a step of processing the at least one of the group of sequential hypothesis tests and comparing an outcome of each processed test to upper and lower threshold limits for determining unexpected operation of the asset that is indicative of a fault condition.

10. The method of claim 1 further including a step of determining if an outputted signal correlative to a detected fault condition necessitates a control action.

11. The method of claim 1 further including a step of determining if an outputted signal correlative to a detected fault condition necessitates an alarm action.

12. The method of claim 2 where the step of acquiring residual data correlative to at least the one mode of asset operation includes a step of transforming the residual data values to remove noise from the residual data values.

13. The method of claim 12 wherein the step of transforming the residual data values to remove noise from the residual data values includes a step of transforming the residual data values to remove correlated noise from the residual data values.

14. The method of claim 12 wherein the step of transforming the residual data values to remove noise from the residual data values includes a step of transforming the residual data values to remove uncorrelated noise from the residual data values.

15. The method of claim 1 wherein the asset is a rocket engine.

16. The method of claim 1 wherein the asset is a rocket engine turbo pump.

17. The method of claim 1 wherein the step of acquiring residual data correlative to expected asset operation includes a step of acquiring observed signal data values from an accelerometer.

18. The method of claim 1 wherein the step of using the mathematical model in the sequential hypotheses test further includes a step of determining if a determined unexpected operation of the asset that is indicative of a fault condition is a degraded signal.

19. The method of claim 1 wherein the step of using the mathematical model in the sequential hypotheses test further includes a step of determining if a determined unexpected operation of the asset that is indicative of a fault condition is a degraded sensor.

20. The method of claim 1 wherein the step of using the mathematical model in the sequential hypotheses test further includes a step of determining if a determined unexpected operation of the asset that is indicative of a fault condition is a degraded component.

21. The method of claim 1 where the step of using the mathematical model in the sequential hypotheses test further includes a step of determining if a determined unexpected operation of the asset that is indicative of a fault condition is an operating anomaly.

22. The method of claim 1 where the step of fitting the mathematical model to the acquired residual data and storing the mathematical model in the memory means includes a step of selecting the parameters in the mathematical model that provide a best fit to a frequency distribution of the acquired residual data.

23. The method of claim 22 where the step of selecting the parameters in the mathematical model that provide the best fit to the frequency distribution of the acquired residual data includes a step of performing a optimization procedure to minimize the error between the mathematical model and the frequency distribution of the acquired residual data.

24. The method of claim 23 wherein the optimization procedure used to minimize the error between the mathematical model and the frequency distribution of the acquired residual data is a simplex optimization procedure.

25. A method for performing surveillance and control of an asset, the steps including:

acquiring residual data correlative to expected asset operation;

fitting a mathematical model to the acquired residual data and storing the mathematical model in a memory means;

collecting a current set of observed signal data values from the asset;

using the mathematical model in a sequential hypotheses test to determine if the current set of observed signal data indicates an unexpected operation of the asset that is indicative of a fault condition; and

determining if a determined unexpected operation of the asset necessitates a control action.

26. The method of claim 25 further including a step of performing a control action when a control action is determined to be necessitated by the determining step.

27. The method of claim 25 further including a step of determining if a determined unexpected operation of the asset necessitates an alarm action.

28. The method of claim 27 further including a step of sounding an alarm when an alarm action is determined to be necessitated by the determining step.

29. A system for performing surveillance of an asset, said system comprising in combination:

means for acquiring residual data correlative to expected asset operation;

means for fitting a mathematical model to said acquired residual data and storing said mathematical model in a memory means;

means for collecting a current set of observed signal data values from the asset;

means for using said mathematical model in a sequential hypotheses test to determine if said current set of observed signal data indicates unexpected operation of the asset that is indicative of a fault condition;

a communication means for communicating detected fault conditions to a remote location for providing asset surveillance.

30. The combination of claim 29 further including means for determining if an outputted signal correlative to a detected fault condition necessitates a control action.

31. The combination of claim 29 further including means for determining if an outputted signal correlative to a detected fault condition necessitates an alarm action.

32. The combination of claim 29 wherein said means for fitting said mathematical model to said acquired residual data and storing said mathematical model in said memory means includes means for selecting parameters in said mathematical model that provide a best fit to a frequency distribution of said acquired residual data.

33. The combination of claim 29 wherein said means for using said mathematical model in said sequential hypotheses test to determine if said current set of observed signal data indicates unexpected operation of the asset that is indicative of a fault condition further includes means for performing at least one of a group of sequential hypothesis tests comprised of a positive mean test, a negative mean test, a nominal variance test, and a inverse variance test all as a function of said mathematical model.

34. The combination of claim 33 wherein said means for performing at least one of said group of sequential hypothesis tests comprised of said positive mean test, said negative mean test, said nominal variance test, and said inverse variance test all as a function of said mathematical model includes means for processing at least one of said group of sequential hypothesis tests and comparing an outcome of each processed test to upper and lower threshold limits for determining unexpected operation of the asset that is indicative of a fault condition.