Predictive Ore Placement for Selective Deep Raffinate Injection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing leaching operations face inefficiencies due to unpredictable ore mineralogy, oxygen availability, temperature fluctuations, and operational costs, leading to suboptimal copper recovery and increased costs in mining operations.
Innovation Solution
A system utilizing predictive models trained with historical data to optimize ore placement and leaching processes by integrating mineralogy, irrigation, and environmental data to adjust parameters in real-time, enhancing recovery and reducing costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional ore routing based on mineralogy is used, then processing simplicity is maintained, but copper recovery efficiency deteriorates due to unpredictable ore placement and mineralogy variations
Solution Approach 1:
The system performs preliminary analysis of ore mineralogy and placement predictions before the ore is processed. By using machine learning models to forecast ore characteristics in advance, the system can pre-determine optimal routing decisions, thereby improving copper recovery efficiency without adding complex real-time processing equipment.
Solution Approach 2:
The system implements a feedback mechanism where actual ore mineralogy data and processing results are continuously fed back into the machine learning models. This allows the system to learn from past performance and continuously improve its routing predictions, enhancing copper recovery while maintaining manageable system complexity through iterative optimization.
2Productivity
If deep raffinate injection is activated without selective ore placement, then operational simplicity is maintained, but copper recovery from sulfide ores deteriorates due to oxygen starvation in heap interior
Solution Approach 1:
The system applies different leaching strategies to different locations and ore types within the heap leach structure. By using machine learning to identify specific zones with sulfide ores and predict their mineralogy, the system selectively activates deep raffinate injection only where needed, improving copper recovery from sulfide ores while avoiding unnecessary complexity in areas where it is not required.
3Productivity
If acid is provided in sufficient quantity to leach all copper, then copper recovery is maximized, but operational costs deteriorate due to gangue mineral acid consumption
Solution Approach 1:
Instead of providing acid in excessive quantities to all ore uniformly, the system applies acid selectively based on predicted ore mineralogy and copper content. By using machine learning models to identify ore that is economically leachable, the system applies acid only where it will effectively dissolve copper, thereby maximizing copper recovery while minimizing unnecessary acid consumption by gangue minerals.
4Productivity
If ore placement is not optimized, then operational simplicity is maintained, but leaching effectiveness deteriorates due to oxygen starvation and temperature fluctuations in heap interior
Solution Approach 1:
The system performs preliminary prediction of ore placement characteristics using machine learning models before the ore is actually placed in the heap. By forecasting mineralogy and other key parameters in advance, the system can pre-plan optimal placement strategies that ensure adequate oxygen distribution and temperature control, thereby improving leaching effectiveness without requiring complex real-time monitoring and adjustment equipment.
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
Improves copper recovery by up to 8-16% through optimized ore routing and leaching processes, reducing operational costs and increasing mine life by optimizing ore reserves.
Implementation Method 1
A system utilizing predictive models trained with historical data to optimize ore placement and leaching processes by integrating mineralogy, irrigation, and environmental data to adjust parameters in real-time
Implementation Method 2
Exposure to dilute sulfuric acid carries sufficient chemical energy to put the copper into solution, so that the copper can be purified and recovered by the downstream processing methods of solvent extraction and electrowinning
Implementation Method 3
When ferric iron oxidizes copper sulfide minerals, the ferric iron is converted to ferrous iron. The ferrous iron is converted back to ferric iron to further oxidize copper sulfide minerals
Implementation Method 4
Air or oxygen may either be introduced by physically piping or blowing it into the ore structure
Implementation Method 5
The system may include a full block model of the final placement tracking system using sensor and Global Positioning Satellite (GPS) data to determine the location of ore in the stockpile
Data Source
AI summary
The method may comprise receiving historical data (e.g., mineralogy data, irrigation data, raffinate data, heat data, lift height data, geographic data on ore placement and/or blower data); training a predictive model using the historical data to create a trained predictive model; adding future assumption data to the trained predictive model; running the forecast engine for a plurality of parameters to obtain forecast data for a mining production target; comparing the forecast data for the mining production target to the actual data for the mining production target; determining deviations between the forecast data and the actual data, based on the comparing; and changing each of the plurality of parameters from the forecast data to the actual data to determine a contribution to the deviations for each of the plurality of parameters.