Ore Characteristic Detection via Imaging and Machine Learning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Ore processing facilities face challenges in accurately determining ore characteristics in real-time, which affects efficient processing and can lead to equipment damage due to undetected anomalies in the ore stream.
Innovation Solution
An imaging capture system records video or images of ore fragments and uses a machine learning model, trained on parameters like XRD, XRF, and EDS measurements, to correlate and determine characteristics such as mineral composition, density, and anomalies, allowing for real-time adjustments in processing operations or stopping the conveyor belt to prevent damage.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional ore processing methods are used without real-time imaging and machine learning analysis, then the processing flow is simpler and equipment is less complex, but the determination of ore characteristics is inaccurate and delayed, leading to inefficient processing and potential equipment damage
Solution Approach 1:
The patent replaces traditional mechanical and manual ore analysis methods with an automated imaging and machine learning system. Cameras capture images of ore fragments on conveyor belts, and machine learning models analyze these images to determine ore characteristics such as mineral composition, size, and anomalies. This substitution enables real-time, accurate measurement without requiring complex manual intervention or destructive sampling.
Solution Approach 2:
The patent creates visual copies (images) of the actual ore fragments using imaging systems. These images serve as digital representations that can be analyzed by machine learning models without physically handling or altering the original ore samples. This copying approach allows for non-intrusive, real-time analysis while maintaining the integrity of the processing flow.
2Productivity
If real-time imaging and analysis systems are implemented, then ore characteristic determination becomes accurate and timely, but the device complexity and initial investment increase
Solution Approach 1:
The patent implements a continuous analysis system where ore fragments are imaged and analyzed in real-time as they move along conveyor belts. The machine learning models process images continuously, providing ongoing feedback on ore characteristics without interrupting the processing flow. This continuous operation maximizes productivity by eliminating delays between sampling and analysis.
Solution Approach 2:
The system employs machine learning models that automatically analyze ore images and determine characteristics without requiring constant human intervention. Once trained, the models independently process images, identify ore types, detect anomalies, and provide analysis results, enabling the system to serve itself in the analysis function while improving overall productivity.
3Reliability
If anomalies in the ore stream are not detected, then the processing continues uninterrupted, but equipment damage may occur and operational safety is compromised
Solution Approach 1:
The patent implements a feedback mechanism where the machine learning system continuously monitors ore images, detects anomalies such as foreign objects or abnormal mineral compositions, and can trigger alerts or stop the conveyor belt. This closed-loop feedback enables real-time detection and response to potential equipment threats, significantly improving reliability and safety.
Solution Approach 2:
The system performs preliminary detection of anomalies before they can cause equipment damage. By analyzing ore images in real-time and identifying potential hazards early in the processing flow, the system can take preventive actions such as alerting operators or stopping the conveyor belt before damaged ore reaches vulnerable equipment components.
Data Source
AI summary
Techniques for processing ore include the steps of causing an imaging capture system to record a plurality of images of a stream of ore fragments en route from a first location in an ore processing facility to a second location in the ore processing facility; correlating the plurality of images of the stream of ore fragments with at least one or more characteristics of the ore fragments using a machine learning model that includes a plurality of ore parameter measurements associated with the one or more characteristics of the ore fragments; determining, based on the correlation, at least one of the one or more characteristics of the ore fragments; and generating, for display on a user computing device, data indicating the one or more characteristics of the ore fragments or data indicating an action or decision based on the one or more characteristics of the ore fragments.