Adaptive Trajectory Control for Directional Drilling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional automated directional drilling systems face challenges in adapting to various trajectory control scenarios, leading to poor performance due to reliance on physics-based models with high uncertainty and limited real-time parameter estimation, resulting in aggressive behavior and excessive downlinks.

Innovation Solution

An adaptive trajectory control framework that generates tailored steering proposals using real-time data from well plans and drilling parameters, selecting suitable control engines to optimize build and turn rates, and inclination/azimuth hold setpoints, allowing for surface-based or downhole control of bottom hole assemblies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If physics-based models are used for trajectory control, then the system can operate with existing modeling approaches, but the control performance deteriorates due to high uncertainty and limited real-time parameter estimation

Engineering Contradiction:

Improvetrajectory control reliabilityVSAvoidparameter estimation accuracy

Core Design Contradiction:

ReliabilityVSLoss of information

Solution Approach 1:

The patent replaces physics-based mechanical models with data-driven machine learning models (neural networks) that learn trajectory patterns from historical drilling data, eliminating the need for uncertain physical parameter estimation while improving control reliability through pattern recognition

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system implements real-time feedback by continuously monitoring actual drilling parameters and comparing them with predicted values from the machine learning model, then adjusting steering commands to compensate for deviations and maintain accurate trajectory control

Inventive Principle:

Principle #23Feedback

2Device complexity

If conventional control methods are used, then the system structure remains simple, but the drilling behavior becomes aggressive and requires excessive downlinks

Engineering Contradiction:

Improvecontrol system complexityVSAvoiddrilling efficiency

Core Design Contradiction:

Device complexityVSProductivity

Solution Approach 1:

The machine learning model performs preliminary prediction of future trajectory positions and required steering actions, allowing the system to proactively adjust controls before deviations occur, thereby preventing aggressive drilling behavior and reducing the need for reactive downlinks

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adapts control parameters based on real-time drilling conditions by using the machine learning model to adjust steering commands continuously, enabling smooth and efficient trajectory following without excessive interventions

Inventive Principle:

Principle #15Dynamics

Data Source

PatentUS12129751B2Adaptive trajectory control for automated directional drilling

Publication Date: 2024.10.29 BAKER HUGHES OILFIELD OPERATIONS LLC

AI summary

Examples described herein provide a method for drilling a wellbore by a wellbore operation system into a subsurface of the earth. The wellbore operation system includes a bottom hole assembly. The method includes conveying the bottom hole assembly into the wellbore. The method further includes selecting a well plan for the wellbore. The method further includes measuring well data by at least one sensor in the wellbore operation system while the bottom hole assembly is in the wellbore. The method further includes generating, by a processing device, a steering proposal based at least in part on the well plan and the well data. The method further includes drilling, with the wellbore operation system, at least a portion of the wellbore based at least in part on the steering proposal.