AI Microstructure Classification for Coal Maceral Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The existing visual analysis method for classifying coal Maceral microstructures is time-consuming and prone to variation among examiners due to its reliance on manual counting, making it difficult for unskilled workers to accurately distinguish and calculate the proportion of Maceral components.
Innovation Solution
A material analysis method utilizing artificial intelligence (AI) models, including preprocessing specimen images and classifying them into target microstructure patterns using noise removal and microstructure classification AI models, specifically employing ResNet and Inception-based deep learning networks, to automate the process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual visual analysis by examiners is used to classify coal Maceral microstructures, then analysis can be performed with simple equipment, but the analysis is time-consuming and prone to variation among examiners
Solution Approach 1:
The patent replaces the manual mechanical visual analysis system with an AI-based automated classification system. The AI model processes digital images of coal microstructures and automatically classifies them into different Maceral types, eliminating the need for manual examination while maintaining high classification accuracy and reducing analysis time significantly.
Solution Approach 2:
The patent creates digital copies of the coal microstructure images and uses AI algorithms to analyze these copies. By working with digital representations rather than physical samples requiring manual inspection, the system achieves both speed and precision in classification without the variability inherent in manual examination.
2Reliability
If manual counting method is used to analyze Maceral composition, then equipment complexity is low, but analysis variation among examiners increases
Solution Approach 1:
The patent substitutes the manual counting and classification process with an automated AI system. The AI model consistently applies the same classification criteria to all images, eliminating inter-examiner variability and ensuring reliable, repeatable results. The system processes images through standardized computational algorithms that do not vary between operators.
3Measurement precision
If skilled workers perform visual analysis to distinguish coal Maceral, then classification accuracy is high, but the process requires specialized expertise and is time-consuming
Solution Approach 1:
The patent uses digital imaging to create precise copies of the coal microstructures, allowing the AI system to analyze and distinguish Maceral types with high accuracy. The digital copies preserve all visual characteristics needed for classification while eliminating the need for skilled human observers to interpret these features.
Solution Approach 2:
The patent replaces the expertise-dependent manual analysis with an AI system that has been trained to recognize and classify Maceral types. The AI model captures and applies classification knowledge consistently, achieving expert-level accuracy without requiring the operational skills of trained examiners.
Data Source
AI summary
The present disclosure relates to a material analysis method which may comprise the steps of: (a) preparing a specimen for structure analysis; (b) training an artificial intelligence model with training images labelled with structural aspects of arbitrary specimens; (c) analyzing a plurality of images for analysis not labelled with structural aspects of specimens by using the trained artificial intelligence model, and removing images for analysis classified as preset noise structural aspects; and (d) using the trained artificial intelligence model to analyze the images for analysis that remain after the images for analysis classified as the noise structural aspects are removed, and classifying the remaining images for analysis as at least one target structural aspect.