Real-Time Drilling Control Using Simulated Annealing and Bayesian Search

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Drilling operations in wellbore systems face challenges in maintaining optimal drilling parameters such as rate of penetration (ROP) due to variable forces exerted by the subterranean formation, requiring real-time adjustments of controllable parameters like weight-on-bit (WOB) and drill bit rotational speed.

Innovation Solution

A system utilizing simulated annealing and Bayesian optimization to quickly and accurately project optimized controllable drilling parameters, enabling real-time, closed-loop control and automation by generating exploration points that maximize ROP, reducing computing power and storage requirements, and providing more accurate results faster.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of time

If traditional optimization methods are used to determine drilling parameters, then computing accuracy is achieved, but optimization time is excessive and computing resources are excessive

Engineering Contradiction:
Improveoptimization timeVSAvoidcomputing accuracy
Core Design Contradiction:
Loss of timeVSMeasurement precision

Solution Approach 1:

The system performs preliminary action by generating an initial set of exploration points using simulated annealing before executing Bayesian optimization. This pre-positioning of exploration points in high-probability regions accelerates the subsequent optimization process, reducing overall optimization time while maintaining accuracy through the two-stage approach.

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If traditional optimization methods are used to determine drilling parameters, then computing accuracy is achieved, but computing power requirements are excessive

Engineering Contradiction:
Improvecomputing accuracyVSAvoidcomputing power
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The optimization process is segmented into two distinct stages: simulated annealing for generating exploration points and Bayesian optimization for fine-tuning parameters. This segmentation allows each method to operate in its optimal performance zone, reducing overall computational power requirements while maintaining computing accuracy through coordinated execution of both stages.

Inventive Principle:
Principle #1Segmentation

3Productivity

If real-time adjustments of drilling parameters are implemented, then drilling efficiency is improved, but system complexity increases

Engineering Contradiction:
Improvedrilling efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The system implements real-time feedback by continuously monitoring drilling parameters and using the optimization results to adjust controllable parameters such as weight on bit and rotational speed. This closed-loop feedback mechanism improves drilling efficiency by adapting to changing formation conditions while managing system complexity through automated control algorithms.

Inventive Principle:
Principle #23Feedback

4Measurement precision

If more exploration points are generated for optimization, then accuracy is improved, but computing resources and storage requirements increase

Engineering Contradiction:
Improveoptimization accuracyVSAvoidcomputing resources
Core Design Contradiction:
Measurement precisionVSQuantity of substance

Solution Approach 1:

The system changes parameters by using simulated annealing to generate exploration points with optimized distributions rather than uniform random sampling. This parameter change in the exploration point generation strategy improves optimization accuracy by concentrating computational resources in high-probability regions, reducing the total number of points needed while maintaining or improving accuracy.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentUS11591895B2Simulated annealing accelerated optimization for real-time drilling
Publication Date: 2023.02.28 LANDMARK GRAPHICS CORP
  • US11591895B2 patent drawing
  • US11591895B2 patent drawing
  • US11591895B2 patent drawing

AI summary

A system and method for controlling a drilling tool inside a wellbore makes use of simulated annealing and Bayesian optimization to determine optimum controllable drilling parameters. In some aspects, a computing device generates sampled exploration points using simulated annealing and runs a Bayesian optimization using a loss function and the exploration points to optimize at least one controllable drilling parameter to achieve a predicted value for a selected drilling parameter. In some examples, the selected drilling parameter is rate-of-penetration (ROP) and in some examples, the controllable drilling parameters include such parameters as rotational speed (RPM) and weight-on-bit (WOB). In some examples, the computing device applies the controllable drilling parameter(s) to the drilling tool to achieve the predicted value for the selected drilling parameter and provide real-time, closed-loop control and automation in drilling.