Drilling Parameter Optimization via Neural Network Energy Transfer Modeling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods fail to accurately identify optimal drilling parameters to minimize energy transfer loss from the surface to the bottom hole assembly (BHA) during drilling operations, leading to suboptimal drilling performance due to the complexity of variables involved.

Innovation Solution

A two-step drilling parameter optimization process that uses historical data to generate mathematical approximations of energy transfer for each distinctive segment of the wellbore, allowing for real-time optimization of drilling parameters based on calculated energy transfer losses during drilling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual evaluation methods are used to identify drilling parameters, then expert experience and geological knowledge are utilized, but the accuracy and optimality of the parameters are insufficient due to the complexity of variables

Engineering Contradiction:

Improveaccuracy of drilling parameter identificationVSAvoidcomplexity of variables affecting energy transfer

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces manual expert evaluation with a machine learning-based computational system that automatically analyzes multiple variables and their interactions. The system uses historical drilling data, geological information, and real-time measurements to predict optimal drilling parameters, substituting human expert judgment with algorithmic processing that can handle complex multi-variable relationships more accurately.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces a machine learning model as an intermediary between the complex variables (geological data, drilling parameters, energy transfer measurements) and the decision-making process. This intermediary processes the complex relationships and outputs optimized drilling parameters, simplifying the overall system while improving accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If recommended drilling parameters are manually altered during drilling based on performance and driller experience, then drilling performance can be maximized, but the process is time consuming and tedious

Engineering Contradiction:

Improvedrilling performance maximizationVSAvoidtime for parameter alteration

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent implements a self-adjusting drilling system where the machine learning model continuously monitors drilling performance and automatically recommends parameter adjustments without requiring manual intervention. The system uses real-time feedback from sensors and measurements to autonomously optimize drilling parameters, eliminating the time-consuming manual adjustment process while maintaining or improving drilling performance.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent establishes a closed-loop feedback system where drilling performance data is continuously collected, analyzed by the machine learning model, and used to generate real-time parameter recommendations. This feedback mechanism enables dynamic adaptation to changing drilling conditions, maximizing productivity while minimizing the time lag associated with manual parameter adjustments.

Inventive Principle:

Principle #23Feedback

3Ease of manufacture

If conventional methods are used to generate drilling parameters, then the process is simpler, but the parameters are less than optimal due to inability to accurately identify relationships between variables and energy transfer loss

Engineering Contradiction:

Improvesimplicity of parameter generation processVSAvoidenergy transfer loss from surface to BHA

Core Design Contradiction:

Ease of manufactureVSLoss of energy

Solution Approach 1:

The patent replaces simple conventional parameter generation methods with an advanced machine learning system that accurately models the complex relationships between drilling parameters and energy transfer loss. The system processes historical data, geological information, and real-time measurements to predict optimal parameters that minimize energy loss, achieving both simplicity in operation and optimality in results.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent uses parameter changes in the machine learning model to adapt to different drilling conditions and accurately capture the relationships between variables and energy transfer loss. The system dynamically adjusts its predictions based on changing conditions, maintaining optimality while keeping the user interface simple and ease of use high.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11441411B2Optimal drilling parameter machine learning system and methods

Publication Date: 2022.09.13 NABORS DRILLING TECHNOLOGIES USA INC

AI summary

A method of optimizing drilling and drilling instructions for different segments of a wellbore that includes: calculating mathematical approximations of energy transfer loss between a top drive and a BHA using a neural network and a plurality of drilling records for segments of wellbores that are similar to the segments of the wellbore to be drilled; calculating drilling instructions based on each mathematical approximation; drilling the wellbore using the drilling instructions; monitoring the energy transfer loss; and optimizing the drilling instructions using one of the mathematical approximations to minimize the energy transfer loss. Optimizing the drilling instructions includes using Bayesian optimization techniques.