Automated Mud Motor Drilling Mode Identification via Machine Learning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for detecting mud motor drilling modes are manual and prone to errors due to reliance on visual inspections and rule-based systems, which can be affected by data quality and require continuous monitoring, lacking an automated and systematic approach.

Innovation Solution

A system and method that involves data cleaning, training models using historical data, and deploying them to automatically detect drilling modes in real-time, utilizing machine learning algorithms to process surface and downhole parameters, and updating models with new data for improved accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual visual inspection methods are used to detect drilling modes, then the system requires minimal equipment and low complexity, but the detection precision and reliability are poor due to human error and lack of systematic approach

Engineering Contradiction:

Improvedrilling mode detection precisionVSAvoiddetection system complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces manual visual inspection with an automated machine learning-based detection system. The system uses processors to analyze drilling parameters and automatically identify drilling modes, substituting human visual assessment with computational analysis to improve precision while accepting increased system complexity.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables automated self-detection of drilling modes without requiring continuous human monitoring. The machine learning model processes drilling data autonomously to identify modes, allowing the system to serve itself in terms of detection functionality while improving measurement precision.

Inventive Principle:

Principle #25Self-service

2Reliability

If rule-based systems are used for drilling mode detection, then the system structure is simple and easy to implement, but the reliability is poor due to data quality issues and inability to handle complex patterns

Engineering Contradiction:

Improvedrilling mode detection reliabilityVSAvoiddetection system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces rule-based detection systems with machine learning models that can learn complex patterns from historical data. This substitution improves reliability by enabling the system to handle non-linear relationships and data quality variations, while accepting the increased complexity of training and deploying ML models.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system transforms static rule-based parameters into dynamic learned parameters through machine learning training. The model learns optimal detection parameters from historical drilling data, allowing it to adapt to varying data quality and complex drilling patterns, thereby improving reliability.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If continuous manual monitoring is performed to detect drilling modes, then the detection can be performed in real-time, but the loss of time and operational efficiency are reduced due to continuous human involvement

Engineering Contradiction:

Improvedrilling operational efficiencyVSAvoidtime for mode detection

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The automated system maintains continuous detection capability without interruption or human intervention. The machine learning model continuously processes drilling parameters in real-time, ensuring uninterrupted mode detection while improving operational efficiency by freeing up human operators.

Inventive Principle:

Principle #20Continuity of useful action

4Measurement precision

If visual inspection methods are used by directional drillers, then the equipment requirement is minimal and system complexity is low, but the detection precision is poor due to lack of systematic approach and susceptibility to human error

Engineering Contradiction:

Improvedrilling mode detection precisionVSAvoiddetection automation level

Core Design Contradiction:

Measurement precisionVSExtent of automation

Solution Approach 1:

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces a machine learning model as an intermediary between raw drilling data and mode identification. This intermediary layer processes and interprets drilling parameters systematically, improving detection precision by removing human subjectivity while increasing the level of automation.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS20230175383A1System and method for automated identification of mud motor drilling mode

Publication Date: 2023.06.08 HALLIBURTON ENERGY SERVICES INC

AI summary

The disclosure provides for a method for identifying a mud motor drilling mode. The method comprises accessing historical run information stored in a memory of a controller and determining drilling measurements based on the historical run information. The method further comprises training at least one initial model with a machine learning method using the determined drilling measurements, wherein the at least one initial model comprises one or more inputs selected from a group consisting of revolutions per minute, tool-face, torque, flowrate, weight on bit, rate of penetration, differential pressure, a derivative thereof, and any combination thereof. The method further comprises utilizing the trained at least one initial model to determine the mud motor drilling mode for a mud motor.