Asset surveillance system: apparatus and method

• US 7,158,917 B1
• Filed: 03/05/2005
• Issued: 01/02/2007
• 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.
• Primary Examiner(s): Barlow; John
• Assistant Examiner(s): Taylor; Victor J.
• Application Number:
  US11/073,161
• Time in Patent Office: 668 Days
• Field of Search: 702179-183, 700/30
• US Class Current: 702/181
• 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 for providing surveillance of an asset comprised of numerically fitting at least one mathematical model to obtained residual data correlative to asset operation; storing at least one mathematical model in a memory; obtaining a current set of signal data from the asset; retrieving at least one mathematical model from the memory, using the retrieved mathematical model in a sequential hypothesis test for determining if the current set of signal data is indicative of a fault condition; determining an asset fault cause correlative to a determined indication of a fault condition; providing an indication correlative to a determined fault cause, and an action when warranted. The residual data can be mode partitioned, a current mode of operation can be determined from the asset, and at least one mathematical model can be retrieved from the memory as a function of the determined mode of operation.

Claims

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

obtaining residual data correlative to asset operation;

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

obtaining a current set of observed signal data from the asset;

using the mathematical model in a sequential hypothesis test for determining if the current set of observed signal data is indicative of an asset fault condition;

determining an asset fault cause correlative to a determined indication of an asset fault condition; and

providing an indication correlative to a determined asset fault cause for providing asset surveillance.

2. The method of claim 1 wherein the step of determining an asset fault cause includes a step of determining a most probable asset fault cause from a plurality of possible asset fault causes.

3. The method of claim 2 wherein the step of determining the most probable asset fault cause from the plurality of possible asset fault causes includes a step of utilizing a Bayesian belief network to determine the probability of at least one possible asset fault cause.

4. The method of claim 1 further including a step of providing a response to a provided indication correlative to a determined asset fault cause.

5. The method of claim 4 wherein the step of providing the response includes a step of providing a control action.

6. The method of claim 4 wherein the step of providing the response includes a step of providing an alarm action.

7. The method of claim 1 wherein the step of obtaining residual data correlative to asset operation includes a step of transforming the residual data to remove noise from the residual data.

8. The method of claim 1 wherein the step of obtaining residual data correlative to asset operation includes a step of obtaining residual data correlative to at least two modes of asset operation.

9. The method of claim 8 further including a step of dividing the obtained residual data into a plurality of residual data subsets each having at least one mode of asset operation associated thereto.

10. The method of claim 9 further including a step of fitting at least one mathematical model to at least one of the plurality of residual data subsets for defining at least the one mathematical model stored in the memory means.

12. The method of claim 1 further including a step of obtaining residual data correlative to at least two modes of asset operation.

13. The method of claim 12 further including a step of dividing the obtained residual data into a plurality of residual data subsets each having at least one mode of asset operation associated thereto.

14. The method of claim 13 further including a step of fitting at least one mathematical model to at least one of the plurality of residual data subsets for defining at least the one mathematical model stored in the memory means.

15. The method of claim 14 wherein the fitting step includes a step of fitting at least one mathematical function correlative to a frequency distribution to at least one of the plurality of residual data subsets for defining at least the one mathematical model stored in the memory means.

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

obtaining a current set of observed signal data from the asset;

determining a mode of asset operation correlative to the current set of observed signal data obtained from the asset;

retrieving at least one mathematical model from a memory means as a function of the determined mode of asset operation for obtaining at least one retrieved mathematical model, and

using at least the one retrieved mathematical model in a sequential hypothesis test for determining if the current set of observed signal data is indicative of an asset fault condition for providing asset surveillance.

16. The method of claim 11 further including a step of determining an asset fault cause correlative to a finding of an asset fault condition.

17. The method of claim 16 wherein the step of determining an asset fault cause includes a step of determining a most probable asset fault cause from a plurality of possible asset fault causes.

18. The method of claim 17 further including a step of providing an indication correlative to a determined most probable asset fault cause.

19. The method of claim 18 further including a step of providing a response to a provided indication correlative to a determined most probable asset fault cause.

20. The method of claim 19 wherein the step of providing the response includes a step of providing a control action.

21. The method of claim 19 herein the step of providing the response includes a step of providing an alarm action.

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

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

means for performing a sequential hypothesis test for determining if the current set of observed signal data is indicative of an asset fault condition;

means for determining an asset fault cause correlative to a determined indication of an asset fault condition; and

means for providing an indication correlative to a determined asset fault cause for providing asset surveillance.

23. The combination of claim 22 further including means for obtaining residual data correlative to at least two modes of asset operation and means for dividing the acquired residual data into a plurality of residual data subsets each having at least one mode of asset operation associated thereto.

24. The combination of claim 23 further including means for fitting at least one mathematical model to at least one of the plurality of residual data subsets and storing at least the one mathematical model in a memory means.

25. The combination of claim 24 further including means for determining a mode of asset operation correlative to the current set of observed signal data obtained from the asset, means for retrieving at least one mathematical model from said memory means as a function of the determined mode of asset operation for obtaining at least one retrieved mathematical model, and means for using at least the one retrieved mathematical model in performing the sequential hypothesis test for determining if the current set of observed signal data is indicative of an asset fault condition.

26. The combination of claim 22 wherein said determining means includes means for determining a most probable asset fault cause correlative to a determined indication of an asset fault condition from a plurality of possible asset fault causes.

27. The combination of claim 26 further including means for providing an indication correlative to a determined most probable asset fault cause.

28. The combination of claim 27 further including means for providing a response to an indication correlative to a determined most probable asset fault cause.

29. The combination of claim 28 wherein said means for providing a response includes means for providing a control action to an indication correlative to a determined most probable asset fault cause.

30. The combination of claim 28 wherein said means for providing a response includes means for providing an alarm action to an indication correlative to a determined most probable asset fault cause.

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

obtaining a current set of observed signal data from the asset;

performing a sequential hypothesis test for determining if the current set of observed signal data is indicative of an asset fault condition;

determining an asset fault cause correlative to a determined indication of an asset fault condition; and

providing an indication correlative to a determined asset fault cause for providing asset surveillance.

32. A computer readable medium having a program recorded thereon in which the program causes, in use, a computer running the program to execute a procedure according to the method of claim 31.