Expert system for well completion using bayesian probabilities and a consequences node dependent on the zonal isolation types, reliability level, cost level, productivity level, the completion type, and the junction classification decision nodes

• US 9,366,130 B2
• Filed: 07/24/2015
• Issued: 06/14/2016
• 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): VINCENT, DAVID ROBERT
• Application Number:
  US14/808,930
• Publication Number:
  US 20150332161A1
• Time in Patent Office: 326 Days
• Field of Search: 706/12, 706/62, 706/45
• 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: G06N 5/045 Explanation of inference; Explainable artificial intelligence [XAI]; Interpretable artificial intelligence
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

Systems and methods are provided for expert systems for well completion using Bayesian decision networks to determine well completion recommendations. The well completion expert system includes a well completion Bayesian decision network (BDN) model that receives inputs and outputs recommendations based on Bayesian probability determinations. The well completion BDN model includes a treatment fluids section, a packer section, a junction classification section, a perforation section, a lateral completion section, and an open hole gravel packing section.

Claims

1. A system, comprising:

one or more processors;

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

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

a zonal isolation types uncertainty node configured to receive one or more zonal isolation types from the one or more inputs;

a reliability level uncertainty node configured to receive one or more reliability levels from the one or more inputs;

a cost level uncertainty node configured to receive one or more cost levels from the one or more inputs;

a productivity level uncertainty node configured to receive one or more productivity levels from the one or more inputs; and

a completion type decision node configured to receive one or more completion types from the one or more inputs;

a junction classification decision node configured to receive one or more junction classifications from the one or more inputs; and

a completion consequences node dependent on the zonal isolation types uncertainty node, the reliability level uncertainty node, the cost level uncertainty node, the productivity level uncertainty node, the completion type decision node, and the junction classifications decision node and configured to output one or more well completion recommendations based on one or more Bayesian probabilities calculated from the one or more zonal isolation types, the one or more reliability levels, the one or more cost levels, the one or more productivity levels, the one or more completion types, and the one or more junction classifications.

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

3. The system of claim 1, wherein the one or more zonal isolation types, the one or more reliability levels, the one or more cost levels, and the one or more productivity levels each associated with a respective plurality of probabilities.

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

a junction classification consequences node dependent on a multilateral junction design considerations uncertainty node and the junction classifications decision node, wherein the junction classification consequences node is configured to output the one or more well completion recommendations based on one or more Bayesian probabilities calculated from one or more multilateral junction design considerations input to the multilateral junction design considerations uncertainty node and the one or more junction classifications.

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

receiving, at one or more processors, one or more inputs;

providing, by one or more processors, the one or more inputs to one or more nodes of the well completion BDN model, the one or more nodes comprising;

a zonal isolation types uncertainty node;

a reliability level uncertainty node;

a cost level uncertainty node;

a productivity level uncertainty node;

a completion type decision node;

a junction classification decision node; and

a consequences node dependent on the zonal isolation types uncertainty node, the reliability level uncertainty node, the cost level uncertainty node, the productivity level uncertainty node, the completion type decision node, and the junction classification decision node;

determining, by one or more processors, one or more well completion recommendations at the consequences node of the well completion BDN model, the determination comprising a calculation of one or more Bayesian probabilities based on the one or more inputs; and

providing, by one or more processors, the one or more well completion recommendations to a user.

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

7. The computer-implemented method of claim 5, comprising determining the one or more well completion recommendations at a second consequences node of the well completion 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 multilateral junction design considerations uncertainty node and the junction classification decision node.