SYSTEM AND METHOD FOR HEALTH ASSESSMENT OF DOWNHOLE TOOLS

• US 20090299654A1
• Filed: 04/23/2009
• Published: 12/03/2009
• Est. Priority Date: 04/24/2008
• Status: Active Grant

• Current Assignee: Baker Hughes Incorporated (Baker Hughes Company), University of Tennessee Research Foundation (University of Tennessee)
• Original Assignee: Baker Hughes Incorporated (Baker Hughes Company)
• Inventors: Hines, J. Wesley, Garvey, Dustin
• Granted Patent: US 8,204,697 B2
• Time in Patent Office: Days
• US Class Current: 702/34
• CPC Class Codes: E21B 47/00 Survey of boreholes or wells monitoring pressure or flow of drilling fluid E21B21/08
• CPC Class Codes: G01V 1/40 specially adapted for well-logging

Abstract

A system for assessing the health of a mechanism includes a processor for receiving observation data from at least one sensor, the processor including: a detector receptive to the observation data and capable of identifying whether the mechanism is operating in a normal or degraded mode; a diagnoser to identify a type of fault from at least one symptom pattern; and a prognoser capable of calculating a remaining useful life (RUL) of the mechanism, wherein the prognoser includes a population prognoser for calculating the RUL based on a duration of use of the mechanism, a cause prognoser for calculating the RUL based on causal data, and an effect prognoser for calculating the RUL based on effect data generated from the fault. A method and computer program product for assessing the health of a downhole tool is also disclosed.

Claims

1. A system for assessing the health of a mechanism, the system comprising:

at least one sensor associated with the mechanism for generating observation data;

a memory in operable communication with the at least one sensor, the memory including a database for storing observation data generated by the sensor; and

a processor in operable communication with the memory, for receiving the observation data, the processor including;

a detector receptive to the observation data and capable of identifying whether the mechanism is operating in a normal or degraded mode, the degraded mode being indicative of a fault in the mechanism;

a diagnoser responsive to the observation data to identify a type of fault from at least one symptom pattern; and

a prognoser in operable communication with the at least one sensor, the detector and the diagnoser, the prognoser capable of calculating a remaining useful life (RUL) of the mechanism based on information from at least one of the sensor, the detector and the diagnoser, wherein the prognoser includes a population prognoser for calculating the RUL based on a duration of use of the mechanism, a cause prognoser for calculating the RUL based on causal data, and an effect prognoser for calculating the RUL based on effect data generated from the fault.

2. The system of claim 1, further comprising a predictor in operable communication with the detector, the predictor configured to receive one or more exemplar observations and comparing the observation data to the one or more exemplar observations to generate one or more estimated observations.

3. The system of claim 2, wherein the processor is configured to generate one or more residual observations based on a comparison of the observation data and the one or more estimated observations, and the detector is configured to generate one or more exemplar residual observations and identify the degraded mode based on a comparison between the one or more residual observations and the one or more exemplar residual observations.

4. The system of claim 3, wherein the diagnoser is configured to identify the degraded mode responsive to the one or more residual observations exceeding a selected threshold.

5. The system of claim 1, wherein the processor is configured to generate the symptom pattern for observation data identified as representing the degraded mode, and the diagnoser is configured to generate one or more exemplar symptom patterns and identify a type of the fault based on a comparison between the symptom pattern and the one or more exemplar symptom patterns.

6. The system of claim 1, wherein the processor is configured to generate a degradation path and an associated lifetime for observation data identified as representing the degraded mode, and the prognoser is configured to estimate the RUL based on a comparison of the degradation path and one or more exemplar degradation paths.

7. The system of claim 6, wherein the prognoser is configured to estimate the RUL by identifying a closest exemplar degradation path associated with the type of fault at a time of the fault, calculating a time-to-failure of the closest exemplar degradation path, and subtracting the time of the fault from the time-to-failure.

8. The system of claim 1, wherein the detector, the diagnoser and the prognoser form a data-driven model.

9. The system of claim 8, wherein the data-driven model is a nonparametric fuzzy inference system (NFIS).

10. A method for assessing the health of a mechanism, the method comprising:

receiving observation data generated by at least one sensor associated with the mechanism;

identifying whether the mechanism is operating in a normal or degraded mode, the degraded mode being indicative of a fault in the mechanism; and

responsive to an identification of the degraded mode, identifying a type of fault from at least one symptom pattern, and calculating a remaining useful life (RUL) of the mechanism based on a comparison of the observation data with exemplar degradation data associated with the type of fault, wherein calculating the RUL is based on;

a duration of use of the mechanism, causal data, and effect data generated from the fault.

11. The method of claim 10, further comprising receiving one or more exemplar observations and comparing the observation data to the one or more exemplar observations to generate one or more estimated observations.

12. The method of claim 11, further comprising generating one or more residual observations based on a comparison of the observation data and the one or more estimated observations, generating one or more exemplar residual observations, and identifying the degraded mode based on a comparison between the one or more residual observations and the one or more exemplar residual observations.

13. The method of claim 12, wherein identifying the degraded mode is responsive to the one or more residual observations exceeding a selected threshold.

14. The method of claim 10, further comprising generating the symptom pattern for observation data identified as representing the degraded mode, generating one or more exemplar symptom patterns, and identifying a type of the fault based on a comparison between the symptom pattern and the one or more exemplar symptom patterns.

15. The method of claim 10, wherein the processor is configured to generate a degradation path and an associated lifetime for observation data identified as representing the degraded mode, and the prognoser is configured to estimate the remaining useful life based on a comparison of the degradation path and one or more exemplar degradation paths.

16. The method of claim 10, wherein estimating the RUL includes identifying a closest exemplar degradation path associated with the type of fault at a time of the fault, calculating a time-to-failure of the closest exemplar degradation path, and subtracting the time of the fault from the time-to-failure.

17. A computer program product stored on machine readable media for assessing the health of a mechanism by executing machine implemented instructions, the instructions for:

receiving observation data generated by at least one sensor associated with the mechanism;

identifying whether the mechanism is operating in a normal or degraded mode, the degraded mode being indicative of a fault in the mechanism; and

responsive to an identification of the degraded mode, identifying a type of fault from at least one symptom pattern, and calculating a remaining useful life (RUL) of the mechanism based on a comparison of the observation data with exemplar degradation data associated with the type of fault.

18. The computer program product of claim 17, wherein the instructions further include:

receiving one or more exemplar observations and comparing the observation data to the one or more exemplar observations to generate one or more estimated observations;

generating one or more residual observations based on a comparison of the observation data and the one or more estimated observations;

generating one or more exemplar residual observations; and

identifying the degraded mode based on a comparison between the one or more residual observations and the one or more exemplar residual observations.