Bayesian Drilling Control with Dynamic Range Constraints

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current wellbore drilling technologies face challenges in efficiently adjusting drilling parameters like weight-on-bit (WOB) and drill bit rotational speed in real-time to optimize rate of penetration (ROP) due to variable formation conditions, leading to suboptimal drilling performance.

Innovation Solution

A system utilizing Bayesian optimization with a deep-learning neural network that continuously learns and applies range constraints to compute optimized values for WOB and drill bit rotational speed, enabling real-time, closed-loop control and automation of drilling operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If traditional drilling parameter adjustment methods are used, then drilling operations can proceed with simple control, but drilling performance becomes suboptimal due to inability to efficiently optimize parameters in real-time

Engineering Contradiction:

Improvedrilling performanceVSAvoidcontrol system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent implements real-time feedback loops where drilling parameters (WOB, rotational speed) are continuously monitored, and optimization results are fed back to adjust parameters dynamically. This closed-loop control enables the system to adapt to changing formation conditions and maintain optimal drilling performance.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system optimizes drilling by dynamically changing key parameters including weight-on-bit (WOB), drill bit rotational speed, and rate of penetration (ROP). These parameter adjustments are based on real-time formation condition analysis and Bayesian optimization results, allowing the system to transition from static to adaptive parameter control.

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If Bayesian optimization with continuous learning is implemented, then optimization accuracy and speed improve, but computing power and storage requirements increase

Engineering Contradiction:

Improveoptimization accuracyVSAvoidcomputing power consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system performs preliminary analysis of formation conditions and pre-computes optimization strategies before actual drilling operations. By anticipating required parameter adjustments and pre-processing optimization calculations, the system reduces real-time computing demands while maintaining high optimization accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent uses deep-learning neural networks to create computational models that replicate complex optimization relationships. Once trained, these network copies can rapidly predict optimal parameters without requiring intensive real-time computation of full Bayesian optimization, significantly reducing energy consumption while preserving accuracy.

Inventive Principle:

Principle #26Copying

3Productivity

If real-time closed-loop control is implemented, then drilling efficiency improves, but system complexity and processing time increase

Engineering Contradiction:

Improvedrilling efficiencyVSAvoidprocessing time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent replaces traditional mechanical and manual drilling control systems with automated computational systems. Bayesian optimization algorithms and deep-learning neural networks substitute for manual parameter adjustment, enabling real-time closed-loop control that improves drilling efficiency while reducing processing time through automated decision-making.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transitions from static drilling parameter control to dynamic real-time adjustment. Drilling parameters are continuously adapted based on real-time formation condition monitoring and optimization results, allowing the system to respond dynamically to changing conditions and maintain optimal efficiency throughout the drilling process.

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS11555394B2Controlling range constraints for real-time drilling

Publication Date: 2023.01.17 LANDMARK GRAPHICS CORP

AI summary

A system and method for controlling a drilling tool inside a wellbore makes use of Bayesian optimization with range constraints. A computing device samples observed values for controllable drilling parameters such as weight-on-bit (WOB) and drill bit rotational speed in RPM and evaluates a selected drilling parameter such a rate-of-penetration (ROP) for the observed values using an objective function. Range constraints can be continuously learned by the computing device as the range constraints change. A Bayesian optimization, subject to the range constraints and the observed values, can produce an optimized value for the controllable drilling parameter to achieve a predicted value for the selected drilling parameter. The system can then control the drilling tool using the optimized value to achieve the predicted value for the selected drilling parameter.