Rock Type Classification via Spectral Ratio Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional ore grade assessments in mining are delayed due to the time-consuming analysis of sample materials, which hinders timely planning of blasting and transport operations in pit-mining, especially with the need for improved geology identification in automated mining techniques.
Innovation Solution
The method involves scanning rock bodies with spectral sensors to obtain spectral data, determining spectral parameters and ratios indicative of rock types, and using these to classify rock types accurately, allowing for real-time ore grade assessments and informed mining operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional sample material analysis is used for ore grade assessments, then measurement precision can be maintained, but loss of time increases significantly
Solution Approach 1:
The patent replaces conventional mechanical sample collection and laboratory analysis methods with optical spectral scanning technology. The spectral sensor captures reflectance data from rock surfaces, enabling rapid non-contact identification of rock types and ore grades, thus eliminating the time-consuming mechanical sampling and lab processing while maintaining assessment accuracy.
Solution Approach 2:
The patent creates optical copies of the rock surface properties through spectral reflectance data. Instead of physically analyzing sample materials, the system captures and analyzes the spectral signature (optical copy) of the rock surface, which contains sufficient information to identify rock types and ore grades without requiring physical sample processing.
2Productivity
If spectral scanning is used to identify rock types, then productivity increases, but device complexity increases
Solution Approach 1:
The patent segments the spectral scanning system into distinct functional components: a spectral sensor for data collection, a processing unit for analyzing spectral ratios, and a classification system for rock type identification. This modular segmentation allows each component to be optimized independently while working together to achieve rapid rock type identification.
Solution Approach 2:
The patent transforms the complex spectral data into simplified diagnostic parameters, specifically spectral ratios at different wavelength bands. By converting the full spectral signature into key ratio parameters (e.g., ratios at specific wavelength pairs), the system reduces data complexity while retaining sufficient information for accurate rock type classification, making the overall system more manageable.
3Area of stationary object
If spectral data from high angle reflectance is included, then measurement coverage increases, but measurement precision decreases
Solution Approach 1:
The patent extracts and removes high angle reflectance data from the spectral measurements. By identifying and excluding these problematic measurements, the system maintains measurement precision for the remaining data while still achieving comprehensive rock surface coverage through the valid spectral observations.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables fast, objective, and accurate identification of rock types, improving mining efficiency by enabling real-time classification and decision-making, reducing delays in blasting and transport processes.
Implementation Method 1
scanning a surface of the rock body with a spectral sensor to obtain spectral data from the rock body surface
Data Source
AI summary
Described herein is a method and system for classifying rock types in a rock body. The method comprises the steps of obtaining spectral data from a spectral measurement (202) of a surface region of the rock body and then determining a first spectral ratio between two wavelength bands of the spectral data. From the first spectral ratio it can be assessed (204) whether the measurement is a high-angle measurement, and if the measurement is not a high-angle measurement then a further spectral ratio between two further wavelength bands of the spectral data is determined (208). The further spectral ratio is then compared (210) with a corresponding diagnostic criterion to assess whether the surface region comprises a first rock type associated with the further spectral ratio and diagnostic criterion.