Drilling Fluid Additive Imaging for Automated LCM Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The evaluation of solid drilling fluid additives, particularly lost circulation materials (LCM), is time-consuming and labor-intensive, requiring manual identification and characterization of particles in drilling fluid, necessitating improved automation methods.
Innovation Solution
A method involving digital image processing and machine learning algorithms, such as Mask R-CNN, to automatically classify and quantify LCM particles in drilling fluid by extracting color and texture features, enabling semi-automated or fully automated identification and classification of LCM types and concentrations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual identification and characterization of LCM particles is performed, then measurement precision can be maintained, but productivity is reduced and loss of time increases
Solution Approach 1:
The patent replaces manual mechanical particle identification with an automated digital image processing system. The system captures images of LCM particles and uses computer algorithms to automatically identify, classify, and quantify different particle types, substituting human visual inspection and manual analysis with automated optical detection and image processing.
Solution Approach 2:
The patent creates digital copies (images) of the LCM particles for analysis. Instead of directly manipulating or examining physical particles, the system captures optical images that serve as replicas, allowing for automated analysis without physically handling the particles, thereby increasing throughput while maintaining identification accuracy.
2Measurement precision
If manual isolation and characterization of LCM is performed, then measurement precision is maintained, but device complexity increases due to additional manual processing steps
Solution Approach 1:
The patent combines multiple manual operations (particle isolation, imaging, identification, classification, and quantification) into a single integrated automated system. The digital image processing system performs all these functions through computer algorithms, merging what were previously separate manual steps into one cohesive automated process, thereby reducing operational complexity.
Solution Approach 2:
The patent creates a multi-functional automated system that can identify, classify, and quantify multiple types of LCM particles (such as nut plugs, cellulose, mica, rubber) using a single image processing platform. This universal system handles diverse particle types without requiring separate specialized procedures for each particle type, reducing the complexity associated with managing multiple specialized tools and methods.
3Productivity
If automated image processing is implemented, then productivity is improved and loss of time is reduced, but device complexity increases
Solution Approach 1:
The patent implements a self-service automated system where the computer algorithm autonomously performs particle identification, classification, and quantification without requiring manual intervention at each step. The system processes images automatically, making decisions about particle types and concentrations based on programmed criteria, thereby achieving high productivity while the complexity is contained within the automated decision-making logic rather than requiring complex manual operational procedures.
Data Source
AI summary
A method for evaluating solid drilling fluid additives such as lost cuttings materials (LCM) includes acquiring a calibrated digital image of solid particles separated from drilling fluid circulating in a wellbore. The calibrated digital image is processed to identify individual ones of the solid particles depicted in the image. Color features and/or texture features are extracted from the identified solid particles depicted in the image. The extracted color and/or texture features are processed to identify LCM particles among the identified solid particles and to classify each of the identified LCM particles into one of a plurality of LCM classes and thereby obtain an LCM particle classification.