Wellbore Planning Using Protein Code Sequences

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Planning new wellbores in oil and gas exploration is complicated due to uncertainties in underground conditions, as formation characteristics at the planned wellbore are not known with certainty, and existing methods rely on inferred information from offset wellbores.

Innovation Solution

A method involving the use of protein code sequences based on drillability values, where surface drilling parameters are analyzed to infer downhole parameters, and a machine learning model is trained to identify optimal drilling parameters for a planned wellbore by correlating protein codes with rates of penetration, allowing for the optimization of drilling operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If drilling operations proceed without accurate formation information, then drilling can continue without interruptions, but drilling efficiency and rate of penetration are reduced due to suboptimal drilling parameters

Engineering Contradiction:

Improvedrilling efficiencyVSAvoidformation characteristics information

Core Design Contradiction:

ProductivityVSLoss of information

Solution Approach 1:

The patent replaces direct mechanical measurement of formation properties with a computational approach using machine learning models. The system uses protein code sequences (computational representations) to predict formation characteristics, substituting physical measurement systems with information processing systems that analyze drilling data patterns to infer formation properties.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces protein code sequences as an intermediary between observed drilling parameters and formation characteristics. These protein codes serve as a mediating representation that encodes formation properties in a standardized format, allowing the machine learning model to bridge the gap between drilling data and formation information without direct measurement.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If drilling parameters are optimized based on inferred formation information, then rate of penetration and drilling efficiency improve, but the accuracy of formation information may be insufficient leading to suboptimal parameter selection

Engineering Contradiction:

Improverate of penetrationVSAvoidformation information accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent implements a feedback mechanism where the machine learning model continuously learns from actual drilling outcomes. The system compares predicted formation characteristics with actual drilling responses, using this feedback to refine and improve the accuracy of formation information over time, thereby progressively optimizing drilling parameters for higher rate of penetration.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The patent performs preliminary analysis of drilling data to generate protein code sequences and predict formation characteristics before actual drilling operations begin. This preliminary action allows optimization of drilling parameters in advance, enabling more efficient drilling from the start rather than reacting to formation conditions as they are encountered.

Inventive Principle:

Principle #10Preliminary action

3Productivity

If machine learning models are used to identify optimal drilling parameters, then drilling operations can be optimized, but the complexity of the planning system increases

Engineering Contradiction:

Improvedrilling operation optimizationVSAvoidwellbore planning system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent extracts the complex decision-making logic from the overall wellbore planning system and encapsulates it within a dedicated machine learning model. By isolating the optimization function into a separate computational module, the rest of the planning system can remain relatively simple while still achieving optimized drilling operations through the specialized ML component.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20220397027A1Wellbore planning systems and methods

Publication Date: 2022.12.15 SCHLUMBERGER TECH CORP

AI summary

Planning a wellbore includes determining drillability values from surface drilling parameters for an offset wellbore. The drillability values are used to prepare a protein code sequence of protein codes assigned to a range of drillability values. The protein code sequence from the offset wellbore is used to develop a protein code sequence for a planned wellbore. A machine learning model analyzes the offset surface drilling parameters and protein code sequence, and provides target surface drilling parameters for the planned wellbore.