Real-time ‘Scientific’ AI (the fusion of Physics-based models with Machine Learning techniques) is transforming the industry
Digital solutions play a crucial role in enhancing the technical and economic performance of mineral processing. Mining operations can achieve unprecedented efficiency, accuracy, and sustainability by harnessing the power of digitalization and artificial intelligence (AI). However, existing technologies may fall short in addressing the nuanced challenges faced in complex interaction systems, especially within the context of mineral processing.
These processes must adhere to and incorporate physical laws, advanced computational modeling, and operational constraints, besides requiring big change management in the workforce.
In the relentless pursuit of continuous operational improvement, a digital transformation journey through the adoption of cutting-edge technologies such as IntelliSense.io’s Scientific AI (the fusion of physics-based models with Machine Learning techniques) can help unveil patterns to optimize processes like floatation and thickening.
During the recent Minexcellence 2023 conference in Santiago, we showcased two of our Scientific AI-driven projects, highlighting their role in digitally transforming the mining industry and creating tangible value.
Increasing Efficiency in a 125-cell Flotation Circuit
In the realm of flotation, reaching the desired throughput, grade, and recovery objectives presents a big challenge. Operators typically adopt a reactive and manual approach, responding to the visual cues of froth behavior, which becomes more complicated due to frequent fluctuations in feed properties. Furthermore, the lack of real-time circuit visibility and limited feedback on optimal control setpoints pose a significant threat to flotation performance.
In one of our prime AI-driven Flotation projects, we have implemented more than 1,100 hydrodynamic and kinetic virtual sensors alongside our Flotation Optimizer functionality for one of the world’s largest copper mines in Chile.
With that, operators and metallurgists can now track flotation process parameters in real-time and pinpoint operational ranges for individual cells that would optimize the entire circuit’s overall performance.
Findings in the rougher circuit showed a significant increase in Cu recovery, exceeding 1.1%. This improvement is estimated to positively impacting:
1) overall copper recovery of the plant by +1.0% (median);
2) resulting in approximately $8 million in additional copper concentrate production over the analyzed 2.5 months ($38 million annual gain);
3) securing margins and ensuring more metals for the energy transition.
Explore More About this Project
Flotation real-time monitoring and optimization enhanced metal recovery by 1%, a value of $38M
Preventing Costly High-Torque Events in Thickeners
The use of artificial intelligence to optimize thickeners can be seen as a great opportunity to increase process efficiency and recover more water for mining industrial reuse.
In this AI-driven Thickeners project, IntelliSense.io’s Thickener Optimization Application was deployed at a major Chilean copper mine to support site metallurgists and operators in their daily operational decision-making. Real-time virtual sensors (VSs) and our Optimizer capability were implemented by configuring a digital process model for their three thickener circuits. This process involved training machine learning models and utilizing historical data to create process variables VSs and predict thickener performance based on feed variables, properties, and control settings.
EEarly detection through the Thickener App enabled proactive measures to stabilize the circuit, preventing a single stoppage event in one of the Thickeners and positively impacting in various ways:
1) predictive analytics anticipated a high-torque event 15 hours before it happened;
2) save approximately 22,000 m3 per event (by not emptying the tank);
3) enable production of additional 340 tonnes of fine copper, valued at $1.8 million;
4) Avoid maintenance costs for that specific event, estimated to be around $10 million.
Explore More About this Project
Preventing high-torque stoppage events in thickener operations to save $1.8M
Ready to Start?
Adopting cutting-edge technologies like Scientific-AI for digital transformation presents a revolutionary strategy to enhance mineral processing. This approach aims to boost productivity, lower operational costs, and promote sustainability.
What sets IntelliSense.io apart is its commitment to continuous improvement, regularly updating applications with state-of-the-art practices and models. This ensures ongoing value extraction within the circuit as models evolve. Additionally, by integrating operational unit applications, we aim to amplify both upstream and downstream impacts throughout the mineral processing value chain.
Curious about the seamless integration of Scientific AI into your operations?