Systems and methods for an expert system for well control using Bayesian intelligence

• US 9,202,175 B2
• Filed: 03/14/2013
• Issued: 12/01/2015
• Est. Priority Date: 11/02/2012
• Status: Active Grant

• Current Assignee: Saudi Arabian Oil Company (Government of Saudi Arabia), Texas A&M University System
• Original Assignee: Saudi Arabian Oil Company (Government of Saudi Arabia), Texas A&M University System
• Inventors: Al-Yami, Abdullah Saleh Hussain, Schubert, Jerome
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): BROWN JR, NATHAN H
• Application Number:
  US13/827,794
• Publication Number:
  US 20140129506A1
• Time in Patent Office: 992 Days
• Field of Search: 706/52
• US Class Current: 1/1
• 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: E21B 47/117 Detecting leaks, e.g. from tubing, by pressure testing
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/048 Fuzzy inferencing
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

Systems and methods are provided for a well control expert system that provides well control recommendations for a drilling system. The well control expert system includes a well control Bayesian decision network (BDN) model that receives inputs and outputs recommendations based on Bayesian probability determinations. The well control BDN model includes a circulation section, a well control practices section, and a troubleshooting section.

Claims

1. A system, comprising:

one or more processors;

a non-transitory tangible computer-readable memory, the memory comprising;

a well control expert system executable by the one or more processors and configured to provide one or more well control recommendations based on one or more inputs, the well control expert system comprising a well control Bayesian decision network (BDN) model, the well control BDN model comprising;

a kick indicators uncertainty node configured to receive one or more kick indicators from the one or more inputs;

a kick verifications uncertainty node dependent on the kick indicators uncertainty node and configured to receive one or more kick verifications from the one or more inputs;

a kick details uncertainty node dependent on the kick verifications uncertainty node and configured to receive one or more kick details from the one or more inputs;

a circulations decision node configured to receive one or more circulations from the one or more inputs;

a circulations consequences node dependent on the kick details uncertainty node and the circulations decision node and configured to output the one or more well control recommendations based on one or more Bayesian probabilities calculated from one or more kick details and the one or more circulations; and

a well control practices consequences node dependent on (a) a well control scenarios uncertainty node, (b) a well control operations uncertainty node, and (c) a recommended practices decision node, the well control practices consequences node being configured to output the one or more well control recommendations based on one or more Bayesian probabilities calculated from;

one or more well control scenarios input to the well control uncertainty node,

one or more well control operations input to the well control operations uncertainty node, and

one or more recommended practices input to the recommended practices decision node.

2. The system of claim 1, further comprising a user interface configured to display the well control BDN model and receive user selections of the one or more inputs.

3. The system of claim 1, wherein the one or more kick indicators, the one or more kick verifications phases, and the one or more kick details are each associated with a respective plurality of probabilities.

4. The system of claim 1, wherein the well control BDN model comprises:

a troubleshooting solutions consequences node dependent on a well control problems uncertainty node and a troubleshooting solutions decision node, wherein the troubleshooting solutions consequences node is configured to output the one or more well control recommendations based on one or more Bayesian probabilities calculated from one or more well control problems input to the well control problems uncertainty node and one or more troubleshooting solutions input to the troubleshooting decisions node.

5. A method for a well control expert system having a well control Bayesian decision network (BDN) model, the method comprising:

receiving one or more inputs;

providing the one or more inputs to one or more nodes of a well control BDN model, the one or more nodes comprising;

a kick indicators uncertainty node;

a kick verifications uncertainty node dependent on the kick indicators uncertainty node;

a kick details uncertainty node dependent on the kick verifications uncertainty node; and

a circulations decision node;

determining one or more well control recommendations at a second consequences node of the well control BDN model, the determination comprising a calculation of one or more Bayesian probabilities based on the one or more inputs, the one or more inputs provided to;

(a) a well control scenarios uncertainty node, (b) a well control operations uncertainty node dependent on the well control scenarios uncertainty node, and (c) a recommended practices decisions node; and

providing the one or more well control recommendations to a user.

6. The method of claim 5, wherein providing the one or more well control recommendations to a user comprises displaying the one or more well control recommendations in a user interface element of a user interface configured to display the well control BDN model.

7. The method of claim 5, comprising determining the one or more well control recommendations at a third consequences node of the well control BDN model, the determination comprising a calculation of one or more Bayesian probabilities based on the one or more inputs, wherein the one or inputs are provided to a troubleshooting checklists uncertainty node, an actions and results uncertainty node dependent on the troubleshooting checklists uncertainty node, a well control problems uncertainty node dependent on the actions and results uncertainty node, and a troubleshooting solutions decision node.

8. A system, comprising:

one or more processors;

a non-transitory tangible computer-readable memory, the memory comprising;

a well control expert system executable by the one or more processors and configured to provide one or more well control recommendations based on one or more inputs, the well control expert system comprising a well control Bayesian decision network (BDN) model, the well control BDN model comprising;

a well control scenarios uncertainty node configured to receive one or more well control scenarios from the one or more inputs;

a well control operations uncertainty node dependent on the well control scenarios uncertainty node and configured to receive one or more well control operations from the one or more inputs;

a recommended practices decision node configured to receive one or more recommended practices from the one or more inputs;

a circulations consequences node dependent on a kick details uncertainty node and a circulations decision node and configured to output the one or more well control recommendations based on one or more Bayesian probabilities calculated from one or more kick details input to the kick details uncertainty node and one or more circulations input to the circulations decision node;

a troubleshooting solutions consequences node dependent on a well control problems uncertainty node and a troubleshooting solutions decision node, the troubleshooting solutions consequences node being configured to output the one or more well control recommendations based on one or more Bayesian probabilities calculated from one or more well control problems input to the well control problems uncertainty node and one or more troubleshooting solutions input to the troubleshooting decisions node; and

a well control practices consequences node dependent on (a) the well control scenarios uncertainty node, (b) the well control operations uncertainty node, and (c) the recommended practices decision node and configured to output the one or more well control recommendations based on one or more Bayesian probabilities calculated from;

the one or more well control scenarios,

the one or more well control operations, and

the one or more recommended practices.

9. The system of claim 8, comprising a user interface configured to display the well control BDN model and receive user selections of the one or more inputs.

10. The system of claim 8, wherein the one or more well control scenarios and the one or more well control operations are each associated with a respective plurality of probabilities.

11. A method for a well control expert system having a well control Bayesian decision network (BDN) model, the method comprising:

receiving one or more inputs;

providing the one or more inputs to one or more nodes of a well control BDN model, the one or more nodes comprising;

a well control scenarios uncertainty node;

a well control operations uncertainty node dependent on the well control scenarios uncertainty node;

a kick details uncertainty node dependent on the kick verifications uncertainty node; and

a recommended practices decision node;

determining one or more well control recommendations at a second consequences node of the well control BDN model, the determination comprising a calculation of one or more Bayesian probabilities based on the one or more inputs, the one or more inputs being provided to;

(a) a kick indicators uncertainty node, (b) a kick verifications uncertainty node dependent on the kick indicators uncertainty node, (c) a kick details uncertainty node dependent on the kick verifications uncertainty node, and (d) a circulations decision node; and

providing the one or more well control recommendations to a user.

12. The method of claim 11, wherein providing the one or more well control recommendations to a user comprises displaying the one or more well control recommendations in a user interface element of a user interface configured to display the well control BDN model.

13. The method of claim 11, comprising determining the one or more well control recommendations at a third consequences node of the well control BDN model, the determination comprising a calculation of one or more Bayesian probabilities based on the one or more inputs, wherein the one or inputs are provided to a troubleshooting checklists uncertainty node, an actions and results uncertainty node dependent on the troubleshooting checklists uncertainty node, a well control problems uncertainty node dependent on the actions and results uncertainty node, and a troubleshooting solutions decision node.

14. A system, comprising:

one or more processors;

a non-transitory tangible computer-readable memory, the memory comprising;

a well control expert system executable by the one or more processors and configured to provide one or more well control recommendations based on one or more inputs, the well control expert system comprising a well control Bayesian decision network (BDN) model, the well control BDN model comprising;

a troubleshooting checklists uncertainty node configured to receive one or more troubleshooting checklists from the one or more inputs;

an actions and results uncertainty node dependent on the troubleshooting checklists uncertainty node and configured to receive one or more actions and results from the one or more inputs;

a well control problems uncertainty node dependent on the actions and results uncertainty node and configured to receive one or more well control problems from the one or more inputs;

a troubleshooting solutions decision node configured to receive one or more troubleshooting solutions from the one or more inputs;

a troubleshooting solutions consequences node dependent on the well control problems uncertainty node and the troubleshooting solutions decision node and configured to output the one or more well control recommendations based on one or more Bayesian probabilities calculated from the one or more well control problems and the one or more troubleshooting solutions; and

a circulations consequences node dependent on (i) a kick details uncertainty node and (ii) a circulations decision node, and configured to output the one or more well control recommendations based on one or more Bayesian probabilities calculated from;

one or more kick details input to the kick details uncertainty node, and

one or more circulations input to the circulations decision node.

15. The system of claim 14, comprising a user interface configured to display the well control BDN model and receive user selections of the one or more inputs.

16. The system of claim 14, wherein the one or more troubleshooting checklists, the one or more actions and results, and the one or more well control problems are each associated with a respective plurality of probabilities.

17. The system of claim 14, wherein the well control BDN model comprises:

a well control practices consequences node dependent on a well control scenarios uncertainty node, a well control operations uncertainty node, and a recommended practices decision node, wherein the well control practices consequences node is configured to output the one or more well control recommendations based on one or more Bayesian probabilities calculated from one or more well control scenarios input to the well control uncertainty node, one or more well control operations input to the well control operations uncertainty node, and one or more recommended practices input to the recommended practices decision node.

18. A method for a well control expert system having a well control Bayesian decision network (BDN) model, the method comprising:

receiving one or more inputs;

providing the one or more inputs to one or more nodes of a well control BDN model, the one or more nodes comprising;

a troubleshooting checklists uncertainty node;

an actions and results uncertainty node dependent on the troubleshooting checklists uncertainty node;

a well control problems uncertainty node dependent on the actions and results uncertainty node; and

a troubleshooting solutions decision node;

determining one or more well control recommendations at a second consequences node of the well control BDN model, the determination comprising a calculation of one or more Bayesian probabilities based on the one or more inputs, the one or more inputs being provided to;

(a) a well control scenarios uncertainty node, (b) a well control operations uncertainty node dependent on the well control scenarios uncertainty node, and (c) a recommended practices decision node; and

providing the one or more well control recommendations to a user.

19. The method of claim 18, wherein providing the one or more well control recommendations to a user comprises displaying the one or more well control recommendations in a user interface element of a user interface configured to display the well control BDN model.

20. The method of claim 18, comprising determining the one or more well control recommendations at a third consequences node of the well control BDN model, the determination comprising a calculation of one or more Bayesian probabilities based on the one or more inputs, wherein the one or inputs are provided to a troubleshooting checklists uncertainty node, an actions and results uncertainty node dependent on the troubleshooting checklists uncertainty node, a well control problems uncertainty node dependent on the actions and results uncertainty node, and a troubleshooting solutions decision node.