Method and apparatus to predict the remaining service life of an operating system

• US 7,457,785 B1
• Filed: 08/25/2000
• Issued: 11/25/2008
• Est. Priority Date: 08/25/2000
• Status: Expired due to Fees

• Current Assignee: Battelle Memorial Institute
• Original Assignee: Battelle Memorial Institute
• Inventors: Skorpik, James R., Kangas, Lars J., Wilson, Bary W., Maynard, Melody A., Greitzer, Frank L., Terrones, Kristine M., Ferryman, Thomas A., Pawlowski, Ronald A.
• Primary Examiner(s): Holmes; Michael B
• Application Number:
  US10/362,717
• Time in Patent Office: 3,014 Days
• Field of Search: None
• US Class Current: 706/12
• CPC Class Codes: G01D 1/18 with arrangements for signalling that a predetermined value of an unspecified parameter has been exceeded G01D1/14 takes precedence
• CPC Class Codes: G05B 2219/32234 Maintenance planning
• CPC Class Codes: G05B 2219/37252 Life of tool, service life, decay, wear estimation
• CPC Class Codes: G05B 23/0283 Predictive maintenance, e.g. involving the monitoring of a system and, based on the monitoring results, taking decisions on the maintenance schedule of the monitored system; Estimating remaining useful life [RUL] preventive maintenance, i.e. planning maintenance according to the available resources without monitoring the system G06Q10/06
• CPC Class Codes: G07C 3/00 Registering or indicating the condition or the working of machines or other apparatus, other than vehicles

Abstract

A method and computer-based apparatus for monitoring the degradation of, predicting the remaining service life of, and/or planning maintenance for, an operating system are disclosed. Diagnostic information on degradation of the operating system is obtained through measurement of one or more performance characteristics by one or more sensors onboard and/or proximate the operating system. Though not required, it is preferred that the sensor data are validated to improve the accuracy and reliability of the service life predictions. The condition or degree of degradation of the operating system is presented to a user by way of one or more calculated, numeric degradation figures of merit that are trended against one or more independent variables using one or more mathematical techniques. Furthermore, more than one trendline and uncertainty interval may be generated for a given degradation figure of merit/independent variable data set. The trendline(s) and uncertainty interval(s) are subsequently compared to one or more degradation figure of merit thresholds to predict the remaining service life of the operating system. The present invention enables multiple mathematical approaches in determining which trendline(s) to use to provide the best estimate of the remaining service life.

Claims

1. A computer-implemented method for predicting the remaining service life of an operating system, comprising the steps of:

obtaining data from at least one sensor that measures at least one performance characteristic of said system during operation;

calculating at least one degradation figure of merit using data from said at least one sensor;

trending said at least one degradation figure of merit against at least one independent variable relative to at least one degradation figure of merit threshold, thereby generating multiple trendlines;

weighting said multiple trendlines by setting weights for said multiple trendlines;

combining said multiple trendlines into a single trendline based on said weights; and

responsive to said trending, said weighting, and said combining, estimating the remaining service life of said system.

2. The method of claim 1, further comprising the step of validating said data prior to calculating said at least one degradation figure of merit.

3. The method of claim 1, wherein calculating said at least one degradation figure of merit employs a diagnostic technique selected from algorithm, artificial intelligence, pattern recognition, and combinations thereof.

4. The method of claim 1, wherein said system is mechanical.

5. The method of claim 4, wherein said system is an internal combustion engine.

6. The method of claim 4, wherein said system is a turbine engine.

7. The method of claim 1, wherein said system is a fuel cell.

8. The method of claim 1, wherein said trending is performed using at least one mathematical technique, the selection thereof dependent upon the degree of change in the degradation figure of merit with said independent variable.

9. The method of claim 8, wherein said at least one mathematical technique is selected from regression analysis, Bayesian analysis, time series analysis, linear analysis, non-linear analysis, and Kalman Filtering.

10. The method of claim 1, wherein said trending comprises

(a) generating said multiple trendlines using a plurality of window sizes for a given independent variable;

(b) assessing performance of said multiple trendlines; and

(c) selecting a regression trendline.

11. The method of claim 10, further comprising the steps of:

selecting another independent variable before step (c) and repeating steps (a) and (b).

12. The method of claim 1, wherein said at least one sensor comprises at least two sensors that measure at least two different performance characteristics.

13. A computer-implemented method for planning maintenance for an operating system, comprising the steps of:

obtaining data from at least one sensor that measures at least one performance characteristic of said system during operation;

calculating at least one degradation figure of merit using data from said at least one sensor;

trending said at least one degradation figure of merit against at least one independent variable using a plurality of window sizes for said at least one independent variable to produce a plurality of regression trendlines;

assessing performance of said plurality of regression trendlines;

responsive to said assessing, assigning weights to said plurality of regression trendlines;

selecting a regression trendline based on said weights; and

communicating at least one of the plurality of regression trendlines to a person to inform the person of any degradation and associated maintenance needs in the future.

14. The method of claim 13, further comprising the steps of trending said at least one degradation figure of merit against at least one degradation figure of merit threshold and further communicating said at least one degradation figure of merit threshold to the person.

15. The method of claim 13, wherein said communicating is performed by telemetry.

16. A computer-implemented method for monitoring the degradation of an operating system and communicating the degradation to a user, comprising the steps of:

obtaining data from at least one onboard sensor that measures at least one performance characteristic of said system during operation;

calculating a plurality of degradation figures of merit using data from said at least one sensor; and

generating a plurality of regression trendlines using respective degradation figures of merit;

assessing performance of said plurality of regression trendlines;

responsive to said assessing, selecting a regression trendline; and

displaying said selected regression trendline to the user of said operating system.

17. The method of claim 16, wherein calculating said at least one degradation figure of merit employs a diagnostic technique selected from algorithm, artificial intelligence, pattern recognition, and combinations thereof.

18. The method of claim 16, further comprising the step of displaying at least one degradation figure of merit threshold to the user.

19. The method of claim 16, further comprising the step of validating said data prior to calculating said at least one degradation figure of merit.

20. An apparatus for monitoring the degradation of an operating system and communicating the degradation to a user, comprising:

at least one onboard sensor that measures at least one performance characteristic of said system during operation;

a computer for receiving said sensor data;

a first instruction set within said computer for calculating at least one degradation figure of merit using said sensor data;

a second instruction set within said computer for trending said at least one degradation figure of merit against at least one independent variable relative to at least one degradation figure of merit threshold to generate at least one trendline and to estimate the remaining service life of said system; and

a display for communicating said at least one degradation figure of merit as a function of at least one independent variable to the user of said operating system.

21. The apparatus of claim 20, wherein said display further communicates at least one degradation figure of merit threshold to the user.

22. The apparatus of claim 20, wherein said system is mechanical.

23. The apparatus of claim 22, wherein said system is an internal combustion engine.

24. The apparatus of claim 22, wherein said system is a turbine engine.

25. The apparatus of claim 20, wherein said system is a fuel cell.

33. The apparatus of claim 20, further comprising a third instruction set within said computer for assessing performance of said trending and for selecting a trendline from said at least one trendline based on said assessing.

26. An apparatus for predicting the remaining service life of an operating system, comprising:

at least one sensor that measures at least one performance characteristic of said system during operation;

a computer for receiving said sensor data;

a first instruction set within said computer for calculating at least one degradation figure of merit using said sensor data;

a second instruction set within said computer for trending said at least one degradation figure of merit against at least one independent variable relative to at least one degradation figure of merit threshold to generate at least one trendline and to estimate the remaining service life of said system;

a third instruction set within said computer for validating said sensor data; and

a fourth instruction set within said computer for assessing performance of said trending and for selecting a trendline from said at least one trendline based on said assessing.

27. The apparatus of claim 26, wherein said third instruction set for validating said sensor data includes instructions for comparing said sensor data to predicted sensor values based on a tolerance parameter.

28. The apparatus of claim 26, wherein said first instruction set employs a diagnostic technique selected from algorithm, artificial intelligence, pattern recognition, and combinations thereof.

29. The apparatus of claim 26, wherein said second instruction set employs at least one mathematical technique, the selection thereof dependent upon the degree of change in the degradation figure of merit with its independent variable.

30. The apparatus of claim 26, wherein said at least one sensor comprises at least two sensors that measure at least two different performance characteristics.

34. The apparatus of claim 26, wherein said fourth instruction set comprises instructions for setting weights for said at least one trendline based on said assessing.

35. The apparatus of claim 26, further comprising:

a display for communicating said at least one degradation figure of merit as a function of said at least one independent variable to a user of said operating system.

31. A computer-implemented method for planning maintenance for an operating system, comprising the steps of:

obtaining data from at least one sensor that measures at least one performance characteristic of said system during operation;

calculating at least one degradation figure of merit using data from said at least one sensor;

trending said at least one degradation figure of merit against at least one independent variable to produce a plurality of trendlines;

setting weights for said plurality of trendlines and combining two or more of said plurality of trendlines into a single trendline based on said weights; and

communicating said single trendline.

32. A computer-implemented method for monitoring the degradation of an operating system and communicating the degradation to a user, comprising the steps of:

obtaining data from at least one onboard sensor that measures at least one performance characteristic of said system during operation;

calculating at least one degradation figure of merit using data from said at least one sensor, wherein said degradation figure of merit is calculated for various states of said operating system;

trending said degradation figure of merit against at least one independent variable for respective states of said operating system to produce a plurality of trendlines;

setting weights for said plurality of trendlines;

combining two or more of said plurality of trendlines into a single trendline based on said weights; and

displaying said at least one degradation figure of merit as a function of at least one independent variable, or displaying said single trendline.