Real-Time Formation Cuttings Analysis With Computer Vision During Drilling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Traditional manual monitoring of cuttings and cavings during drilling operations is infrequent and inefficient, leading to suboptimal drilling performance and safety risks due to the lack of real-time analysis.

Innovation Solution

A system utilizing a camera to stream video of cuttings on a shale shaker, combined with a learning machine for real-time image segmentation and analysis, enabling automated detection and volume estimation of cuttings, and generating trend lines to diagnose drilling issues.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual monitoring of cuttings is used, then personnel can visually inspect cuttings, but the monitoring frequency is low and real-time analysis is not achieved

Engineering Contradiction:

Improvecuttings analysis accuracyVSAvoidresponse time for wellbore instability detection

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical inspection process with an automated optical system. A camera captures images of cuttings on the shale shaker, and machine learning algorithms automatically analyze these images to identify wellbore instability conditions. This substitution eliminates the need for continuous manual observation while providing real-time automated analysis, thereby improving both measurement precision and reducing time loss.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent introduces an intermediary automated analysis system between the cuttings and the operator. The machine learning model acts as an intermediary that processes cutting images and generates alerts about wellbore instability conditions, enabling real-time detection without requiring direct continuous human observation of the cuttings.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If manual cuttings monitoring is performed, then personnel safety is maintained with fewer automated systems, but safety risks increase due to infrequent monitoring

Engineering Contradiction:

Improvewellbore stability monitoring reliabilityVSAvoidsafety incidents involving on-site personnel

Core Design Contradiction:

ReliabilityVSObject-affected harmful factors

Solution Approach 1:

The system enables self-service monitoring where the automated machine learning model continuously analyzes cuttings images without requiring human intervention. This self-service capability ensures continuous reliable monitoring of wellbore stability while eliminating the need for personnel to physically observe cuttings, thereby reducing safety risks associated with on-site personnel exposure to hazardous drilling environments.

Inventive Principle:

Principle #25Self-service

3Productivity

If automated machine learning analysis is implemented, then real-time cuttings analysis is achieved, but system complexity increases

Engineering Contradiction:

Improvedrilling operation efficiencyVSAvoidautomated cuttings analysis system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The patent implements a universal machine learning model that performs multiple functions: identifying different types of cuttings, detecting various wellbore instability conditions, and providing real-time alerts. This multi-functional approach consolidates what would otherwise require multiple separate systems into a single automated platform, managing system complexity while maximizing productivity benefits.

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Loss of time

If continuous real-time monitoring is implemented, then non-productive time is reduced, but operational costs increase due to automated systems

Engineering Contradiction:

Improvenon-productive drilling timeVSAvoidoperational cost for automated monitoring

Core Design Contradiction:

Loss of timeVSLoss of energy

Solution Approach 1:

The patent implements continuous automated monitoring that operates without interruption during drilling operations. The machine learning model continuously processes cutting images in real-time, ensuring that wellbore instability conditions are detected immediately when they occur. This continuity eliminates gaps in monitoring that would occur with manual inspection, reducing non-productive time caused by delayed detection of drilling problems.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS12437385B2Real-time formations cuttings analysis system using computer vision and machine learning approach during a drilling operation

Publication Date: 2025.10.07 HALLIBURTON ENERGY SERVICES INC

AI summary

In some embodiments, a method for controlling a learning machine used in a drilling operation to drill a well into a subsurface formation includes receiving, via a video stream, an image of debris including cuttings from the drilling operation. The method may further include generating a first mask on the image to identify the cuttings in the debris, generating, via instance segmentation, a second mask for each of the identified cuttings, determining, based on the second masks, one or more properties of each of the cuttings, and associating each of the identified cuttings to a depth interval of the subsurface formation based, at least in part, on the properties of each of the identified cuttings and at least one property of the drilling operation.