System and method for prioritizing artificial lift system failure alerts

• US 9,157,308 B2
• Filed: 01/17/2012
• Issued: 10/13/2015
• Est. Priority Date: 12/29/2011
• Status: Active Grant

• Current Assignee: Chevron USA Incorporated (Chevron Corp.)
• Original Assignee: Chevron USA Incorporated (Chevron Corp.)
• Inventors: Balogun, Oluwafemi Opeyemi, Olabinjo, Olanrewaju, Seren, Fatma Burcu
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): Smith, Paulinho E
• Application Number:
  US13/351,318
• Publication Number:
  US 20130173505A1
• Time in Patent Office: 1,365 Days
• Field of Search: None
• US Class Current: 1/1
• CPC Class Codes: E21B 43/121 Lifting well fluids monitoring of down-hole pump systems E21B47/008
• CPC Class Codes: E21B 44/00 Automatic control systems specially adapted for drilling operations, i.e. self-operating systems which function to carry out or modify a drilling operation without intervention of a human operator, e.g. computer-controlled drilling systems; Systems specially adapted for monitoring a plurality of drilling variables or conditions
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

A system, method, and computer program product are disclosed for analysis of artificial lift systems. An Artificial Lift Analysis Solution (ALAS) is also provided to view and analyze artificial lift well data trends, prediction and detection event alerts, and to diagnose system conditions to facilitate production optimization. Production well information is provided for a plurality of the production wells each being associated with an artificial lift system. Artificial lift system failure alerts for the plurality of production wells are received and processed on a computer. A relevance measure for each of the artificial lift system failure alerts is determined responsive to the production well information. A summary of the artificial lift system failure alerts is displayed in an ordering based on the relevance measure.

Claims

1. A method for artificial lift system analysis, the method comprising:

(a) providing production well information measured at a surface for a plurality of production wells, wherein each of the production wells is associated with an artificial lift system;

(b) receiving and processing, on a computer, artificial lift system failure alerts for the plurality of production wells, wherein the artificial lift system failure alerts comprise predicted failure alerts and detected failure alerts, and wherein the predicted failure alerts are generated using a support vector machine method and the detected failure alerts are generated using a Bayesian Network method;

(c) determining a relevance measure for each of the artificial lift system failure alerts responsive to the production well information; and

(d) displaying a summary of the artificial lift system failure alerts in an ordering based on the relevance measure, wherein the relevance measure comprises an urgency of the artificial lift system failure alerts such that the detected failure alerts are ordered before the predicted failure alerts in the summary of the artificial lift system failure alerts.

2. The method of claim 1, wherein the relevance measure comprises a combination of average daily production and potential production volume loss for each of the plurality of production wells.

3. The method of claim 1, wherein the relevance measure comprises an artificial lift failure type.

4. The method of claim 1, wherein the relevance measure comprises a completion status such that the artificial lift system failure alerts are ordered according to whether the alert is associated with a new, under evaluation, in progress, or closed completion status.

5. The method of claim 1, further comprising:

(e) selecting one or more of the plurality of production wells; and

(f) generating a well history graph for the one or more of the plurality of production wells selected.

6. The method of claim 1, further comprising:

(e) selecting one or more of the plurality of production wells; and

(f) generating an alert history graph for the one or more of the plurality of production wells selected.

7. The method of claim 1, further comprising:

(e) selecting one or more of the plurality of production wells; and

(f) generating a comparison of production performance for the one or more of the plurality of production wells selected with one or more associated neighborhood wells.

8. The method of claim 1, further comprising:

(a) identifying an artificial lift system failure alert that is incorrect;

(b) correcting the artificial lift system failure alert; and

(c) training an artificial intelligence engine with the corrected artificial lift system failure alert.

9. The method of claim 1, further comprising:

(e) selecting one or more of the plurality of production wells that are associated with rod pump artificial lift systems; and

(f) generating a dynamometer card history for the one or more of the plurality of production wells selected.

10. The method of claim 1, wherein one or more of the plurality of production wells are associated with artificial lift systems that are not electric submersible pumps.

11. The method of claim 1, wherein one or more of the plurality of production wells are associated with rod pump artificial lift systems or plunger lift systems.

12. The method of claim 1,

wherein the detected failure alerts correspond to forecasted artificial lift system failures that can occur within fourteen days;

and

wherein the predicted failure alerts correspond to forecasted artificial lift system failures that can occur between fourteen days and one hundred days.

13. The method of claim 1, further comprising using an Artificial Neural Network to interpret a dynamometer card and determine at least one problem with an associated pump.

14. A system for artificial lift system analysis, the system comprising:

a database configured to store production well information measured at a surface for a plurality of production wells, wherein each of the production wells is associated with an artificial lift system;

a computer processor;

a computer program executable on the computer processor, wherein the computer program, when executed on the computer processor, cause the processor to implement a method, the method comprising;

(a) processing artificial lift system failure alerts for the plurality of production wells, the artificial lift system failure alerts comprise predicted failure alerts and detected failure alerts, and wherein the predicted failure alerts are generated using a support vector machine method and the detected failure alerts are generated using a Bayesian Network method;

(b) determining a relevance measure for each of the artificial lift system failure alerts responsive to the production well information; and

(c) ordering the artificial lift system failure alerts using the relevance measure, wherein the relevance measure comprises an urgency of the artificial lift system failure alerts such that the detected failure alerts are ordered before the predicted failure alerts; and

a display that communicates with the computer program to produce image data representations of the artificial lift system failure alerts ordered using the relevance measure.

15. The system of claim 14, wherein the relevance measure comprises a combination of average daily production and potential production volume loss for each of the plurality of production wells.

16. The system of claim 14, further comprising generating a well history graph for one or more of the plurality of production wells.

17. The system of claim 14, further comprising generating an alert history graph for one or more of the plurality of production wells.

18. The system of claim 14, further comprising generating a comparison of production performance for one or more of the plurality of production wells with one or more associated neighborhood wells.

19. The system of claim 14, further comprising correcting artificial lift system failure alerts to train an artificial intelligence engine.

20. The system of claim 14, further comprising generating a dynamometer card history for one or more of the plurality of production wells associated with rod pump artificial lift systems.

21. The system of claim 14, wherein one or more of the plurality of production wells are associated with artificial lift systems that are not electric submersible pumps.

22. The system of claim 14, wherein one or more of the plurality of production wells are associated with rod pump artificial lift systems or plunger lift systems.

23. The system of claim 14,

wherein the detected failure alerts correspond to forecasted artificial lift system failures that can occur within fourteen days;

and

wherein the predicted failure alerts correspond to forecasted artificial lift system failures that can occur between fourteen days and one hundred days.

24. The system of claim 14, wherein the relevance measure comprises an artificial lift failure type.

25. The system of claim 14, further comprising using an Artificial Neural Network to interpret a dynamometer card and determine at least one problem with an associated pump.

26. A non-transitory processor readable medium containing computer readable software instructions used for surveillance of artificial lift systems, the computer readable instructions comprising:

(a) processing production well information measured at a surface and artificial lift system failure alerts for a plurality of production wells, wherein each of the production wells is associated with an artificial lift system, wherein the artificial lift system failure alerts comprise predicted failure alerts and detected failure alerts, and wherein the predicted failure alerts are generated using a support vector machine method and the detected failure alerts are generated using a Bayesian Network method;

(b) determining a relevance measure for each of the artificial lift system failure alerts responsive to the production well information; and

(c) ordering the artificial lift system failure alerts using the relevance measure, wherein the relevance measure comprises an urgency of the artificial lift system failure alerts such that the detected failure alerts are ordered before the predicted failure alerts.