Automated Formation Cutting Analysis for Downhole Problem Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for analyzing formation cuttings during well drilling operations are manual, subjective, slow, and prone to errors, lacking effective means to acquire additional information to corroborate downhole problems, which can lead to well stability issues and other drilling challenges.
Innovation Solution
A system that uses cameras and sensors to capture real-time images and data of formation cuttings, employing machine-learning models to automatically detect downhole problems by analyzing properties such as shape, size, and material, and providing recommendations for corrective actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis methods are used to examine formation cuttings, then operational simplicity is maintained, but detection accuracy and reliability deteriorate due to subjectivity and human error
Solution Approach 1:
The patent replaces manual mechanical examination of formation cuttings with an automated optical imaging system coupled with machine learning algorithms. Cameras capture images of cuttings on the shaker belt, and AI models automatically analyze shape, size, and material properties, eliminating human subjectivity and error while maintaining operational simplicity.
Solution Approach 2:
The system creates digital copies (images) of physical formation cuttings using cameras positioned over the shaker belt. These digital representations are then analyzed by machine learning models, allowing repeated examination and analysis without physically handling or disturbing the original cuttings, thereby improving detection accuracy.
2Productivity
If manual examination of formation cuttings is performed, then equipment complexity is minimized, but productivity and detection speed deteriorate due to time-consuming manual processes
Solution Approach 1:
The patent replaces slow manual examination with automated optical imaging and machine learning analysis. Cameras continuously capture images of formation cuttings as they travel across the shaker belt, and algorithms instantly analyze properties such as shape, size, and material composition, providing real-time detection feedback that significantly accelerates productivity.
Solution Approach 2:
The system enables continuous automated analysis of formation cuttings as they continuously move across the shaker belt. Unlike intermittent manual examination, the automated system operates without interruption, maintaining constant monitoring and analysis, which maximizes detection speed and productivity throughout the drilling operation.
3Reliability
If additional sensors and cameras are deployed to gather more formation data, then measurement precision and reliability improve, but device complexity and cost increase
Solution Approach 1:
The patent employs a multi-functional integrated system where cameras serve multiple purposes: capturing images for shape analysis, size measurement, and material identification. The same optical system supports various machine learning models that analyze different cutting properties, reducing the need for separate specialized sensors and thereby limiting complexity growth despite enhanced reliability.
Solution Approach 2:
The system merges multiple data collection functions into a single integrated platform. Cameras positioned over the shaker belt simultaneously gather information about cutting shape, size, and material properties, which are then processed by unified machine learning algorithms. This consolidation improves detection reliability while preventing exponential growth in system complexity through functional integration.
Data Source
AI summary
A system is disclosed for detecting a problem associated with a drilling operation based on the properties of a formation cutting. The system can include a camera for generating an image of the formation cutting extracted from a subterranean formation. The system can include one or more sensors for detecting one or more characteristics of the subterranean formation or a well tool. The system can provide the image as input to a first model for determining one or more properties of the formation cutting based on the image. The system can provide the one or more properties and the one or more characteristics as input to a second model for detecting a downhole problem associated with the drilling operation. The system can transmit an alert indicating the downhole problem and optionally a recommended solution to a user.