Automatic Iron Ore Pellet Maturation Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The classification of the degree of maturation of fired iron ore pellets is currently subjective and prone to errors due to human intervention, leading to a lack of reproducibility in microstructural analysis.

Innovation Solution

An automatic method using digital acquisition and processing of microscopy images of polished cross sections, employing image processing techniques such as background correction, edge enhancement, segmentation, and morphological post-processing, followed by analysis and classification through a supervised software procedure to determine the degree of maturation independently of human intervention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual observation and classification by human operators is used, then the classification process can be performed with existing equipment, but the results are subjective and lack reproducibility

Engineering Contradiction:

Improvereproducibility of classificationVSAvoidautomation of classification process

Core Design Contradiction:

ReliabilityVSExtent of automation

Solution Approach 1:

The patent replaces the manual mechanical observation system with an automated image processing system. Digital microscopy images are processed through computer-based image analysis that automatically identifies microstructural features and classifies degrees of maturation, eliminating human subjectivity while maintaining measurement capability.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The patent creates digital copies of the microstructural images for automated analysis. Instead of direct human observation of optical microscope images, the system captures digital images and processes them through software algorithms, allowing multiple analyses of the same sample without human variability.

Inventive Principle:

Principle #26Copying

2Reliability

If automated image processing is implemented, then objectivity and reproducibility are improved, but the device complexity increases

Engineering Contradiction:

Improveobjectivity of classificationVSAvoidcomplexity of image processing system

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent employs a universal image processing platform that can analyze multiple types of microstructural features across different samples and classification categories. The same software system handles background correction, edge enhancement, segmentation, and classification for all degree of maturation categories, reducing the need for multiple specialized systems.

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Measurement precision

If multiple image processing steps are applied, then measurement precision is improved, but the processing time increases

Engineering Contradiction:

Improveprecision of microstructural analysisVSAvoidtime for image processing

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary image processing steps such as background correction and edge enhancement before the main classification analysis. These preprocessing operations prepare the images in advance, making subsequent segmentation and feature extraction more efficient and accurate, thereby reducing total processing time while maintaining precision.

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS9207185B2Automatic classification of the degree of maturation for iron ore pellets

Publication Date: 2015.12.08 VALE SA

AI summary

An automatic method or the classification of the Degrees of Maturation (DM) for fired iron ore pellets, independent of human intervention, based on the digital acquisition of microscopy images of polished cross sections, and their processing, analysis and classification by a suitable software procedure.