Asset surveillance system and method comprising self-calibrating fault detection

1. A computer-implemented method for self calibrating at least one fault detector monitoring an asset, comprising the steps of:

calibrating at least one fault detector with statistics associated with expected asset behavior;

acquiring observed data values from an asset;

screening the observed data values based upon at least one defined criterion for obtaining screened data values;

updating the statistics associated with expected asset behavior as a function of the screened data values for defining updated statistics; and

recalibrating the at least one fault detector with the updated statistics.

2. The computer-implemented method of claim 1 wherein the at least one defined criterion comprises an indication of a degrading asset condition.

3. The computer-implemented method of claim 1 wherein the updating step comprises a step of utilizing a sequential discounting expectation maximization method.

4. The computer-implemented method of claim 1 further comprising a step of iteratively repeating the acquiring step, the screening step, the updating step, and the recalibrating step for repeatedly recalibrating the at least one fault detector.

5. The computer-implemented method of claim 1 further comprising a step of using the at least one fault detector for determining an indication of an asset fault condition.

6. The computer-implemented method of claim 5 further comprising a step of effecting an alarm action as a function of a determined indication of an asset fault condition.

7. The computer-implemented method of claim 5 further comprising a step of effecting a control action as a function of a determined indication of an asset fault condition.

8. The computer-implemented method of claim 5 further comprising a step of determining an asset fault cause correlative to a determined indication of an asset fault condition.

9. A non-transitory computer readable medium containing computer instructions stored therein for causing a computer processor to perform a self calibrating method, said method comprising:

calibrating at least one fault detector with statistics associated with expected asset behavior;

acquiring observed data values from an asset;

screening the observed data values based upon at least one defined criterion for obtaining screened data values;

updating the statistics associated with expected asset behavior as a function of the screened data values for defining updated statistics; and

recalibrating the at least one fault detector with the updated statistics.

10. The non-transitory computer-readable medium of claim 9 wherein the at least one defined criterion comprises an indication of a degrading asset condition.

11. The non-transitory computer-readable medium of claim 9 wherein the updating step comprises a step of utilizing a sequential discounting expectation maximization method.

12. The non-transitory computer-readable medium of claim 9 wherein the method further comprises a step of iteratively repeating the acquiring step, the screening step, the updating step, and the recalibrating step for repeatedly recalibrating the at least one fault detector.

13. The non-transitory computer-readable medium of claim 9 wherein the method further comprises a step of using the at least one fault detector for determining an indication of an asset fault condition.

14. The non-transitory computer-readable medium of claim 13 wherein the method further comprises a step of effecting an alarm action as a function of a determined indication of an asset fault condition.

15. The non-transitory computer-readable medium of claim 13 wherein the method further comprises a step of effecting a control action as a function of a determined indication of an asset fault condition.

16. The non-transitory computer-readable medium of claim 13 wherein the method further comprises a step of determining an asset fault cause correlative to a determined indication of an asset fault condition.

17. An asset surveillance system comprising self-calibrating fault detection, said system comprising:

at least one fault detector calibrated with statistics associated with expected asset behavior;

means for acquiring observed data values from an asset;

means for screening said observed data values based upon at least one defined criterion for obtaining screened data values;

means for updating said statistics associated with expected asset behavior as a function of said screened data values for defining updated statistics; and

means for recalibrating said at least one fault detector with said updated statistics.

18. The system of claim 17 wherein said at least one defined criterion comprises an indication of a degrading asset condition.

19. The system of claim 17 wherein said means for updating comprises means for utilizing a sequential discounting expectation maximization method.

20. The system of claim 17 further comprising means for iteratively recalibrating said at least one fault detector.

21. The system of claim 17 further comprising means for using said at least one fault detector for determining an indication of an asset fault condition.

22. The system of claim 21 further comprising means for effecting an alarm action as a function of a determined indication of an asset fault condition.

23. The system of claim 21 further comprising means for effecting a control action as a function of a determined indication of an asset fault condition.

24. The system of claim 21 further comprising means for determining an asset fault cause correlative to a determined indication of an asset fault condition.