Data-Driven Mining: The Role Of AI And Machine Learning
The field of machine learning and artificial intelligence (ML/AI) is rapidly evolving today and slowly beginning to reshape the mining sector. With the mining machinery becoming larger and equipment more sophisticated, the sector can gain immensely from these advanced technologies in terms of operational efficiency and ramping down costs.
What is machine learning/artificial intelligence?
ML/AI is a field of computer study that deals with the creation of intelligent machines that work and react like humans. It covers a wide spectrum from speech recognition and visual perception up to language translations and decision-making, which normally require human intelligence. ML algorithms and AI is considered the next step for digital mine transformation. AI can be successfully leveraged at different stages of mining to identify and unlock potential use cases. From the prospecting and exploration stage to the actual mining process, AI and analytics can be used in multiple ways.
Top 4 reasons for choosing ML/AI
- Get real-time data – Retrieved by AI instruments that are installed onto drill rigs, real-time data aids in accelerating timelines for multiple mining stages and decision-making intelligence. Remote sensing data is used for rock-face identification and soil classification, while satellite imagery, aerial photography, geophysical maps, and drone-based monitoring are used to predict mineral prospectivity, or the locations of potential ores.
- Go eco-friendly – Tracking systems and devices with wireless communications can monitor ecological parameters like ground water, temperature, and subterranean ventilation changes to help assess the impact of mining activities. Remote sensing technologies, e.g., satellite imagery, can monitor environmental changes and predict changes in erosion, wildlife habitats, topsoil redistribution, and vegetation.
- Reduce mining risks – Ensure mining personnel safety with automated and tele-operated drilling mechanisms. ML-based predictive algorithms can warn operators and maintenance crews hours in advance of downtimes in critical equipment or potential pressure spikes in pumps. It can also assess ore fragmentation in underground and open-pit mines in less than a minute, compared to hours of manual processing by geotechnical engineers. Augment this with ML techniques, and you get a system that can analyze risks associated with mine sludge deposits.
- Simplify mining operations – Robotic devices powered by AI can perform a wide range of tasks, including drilling, blasting, loading, hauling, ore sampling, and rescuing trapped miners. At Rio Tinto’s Cape Lambert port, robots are used for iron ore sampling, while autonomous load-haul-dump vehicles are used in underground diamond mines in Western Australia. Robots work in an enclosed area in iron ore sample stations, aided by in-feed and out-feed conveyors, bucket and tray storage racks, ovens, and weigh scales. The technology also allows operators to control a drill from a remote location without entering hazardous areas.
Summing up the future
The rapidly evolving field of AI and robotics can certainly simplify the complex mining tasks of extraction and processing. The transformation that AI can bring in the mining industry is immense, and its adoption can improve productivity and cost savings. The good news is that deployment has become simpler, particularly when it’s be done using edge and cloud computing.
Learn how to bring new technologies and services together to power digital transformation by downloading “The IoT Imperative for Energy and Natural Resource Companies.” Explore how to bring Industry 4.0 insights into your business today by reading “Industry 4.0: What’s Next?”
This article originally appeared on http://www.digitalistmag.com/