TOMRA Mining opens a new era in sensor-based sorting with Deep Learning technology

TOMRA Mining will launch its latest innovation, OBTAIN™, at the Mining Indaba trade show in Cape Town, South Africa, from 5 to 8 February 2024.

albert du preez

TOMRA Mining will launch its latest innovation, OBTAIN™, at the Mining Indaba trade show in Cape Town, South Africa, from 5 to 8 February 2024. This breakthrough software leverages deep learning to achieve single-particle accuracy in high-throughput particle sorting, taking capacity, quality and recovery to new levels and unlocking value through large volumes of highly detailed and accurate data to make better decisions. Smart decisions.

Albert du Preez, Head of TOMRA Mining said: “The Mining Indaba is one of the most important events in the mining industry and is the perfect platform for us to launch the revolutionary OBTAIN™. This is an exciting innovation that marks the beginning of sensor-based sorting. The beginning of a new era will enable mining operations to unlock untapped value and extend the life of mines.”

Artificial intelligence has been making headlines and creating buzz since ChatGPT. However, artificial intelligence has been around for a long time and has been working quietly behind the scenes. For decades, the ability of computer systems to mimic human reasoning and decision-making to perform tasks that have traditionally required human intelligence has played an important role in TOMRA’s sensor-based sorting solutions, automating processes and improving sorting machines. The accuracy and efficiency add value to the enterprise. Mining operations.

TOMRA Mining’s experience with artificial intelligence dates back to 1993, when its predecessor CommoDaS developed a sensor-based sorter that used artificial intelligence in its vision system to identify particle properties. Sensor-based sorting technology has continued to evolve over the years, and TOMRA has been using machine learning in its X-ray transmission (XRT) and near-infrared (NIR) sorters for 10 years.

Ideal for mineral sorting – more efficient, cost-effective and sustainable

Artificial intelligence includes two subfields that have made significant progress in recent years: machine learning, which can recognize patterns, learn from data and improve without programming; and deep learning, a type of machine learning that uses artificial neural networks to analyze data. Used to solve complex problems. These technologies can process large amounts of data very quickly and use this data to make decisions without the need for human intervention.

Machine learning and deep learning can further improve the sorting process for mining operations that already use sensor-based sorting, and can also open up new possibilities by processing extremely low-quality materials that were previously discarded. Another advantage of artificial intelligence is the large amount of data it generates and processes. This provides mining operations with valuable insights into sorter performance and predictive maintenance.

It’s important to note that machine learning and deep learning are not one-size-fits-all solutions. With many years of expertise and extensive research and development in the field of artificial intelligence, TOMRA always selects the most appropriate technology for each case.

The OBTAIN™ Revolution: Unprecedented Throughput in Sensor-Based Sorting

TOMRA is now breaking new ground with its latest innovation, leveraging deep learning to launch an industry first: single-particle precision in high-throughput ore sorting. This revolutionary software uses neural networks to accurately identify the characteristics of each particle, regardless of sorter capacity, enabling unprecedented accuracy and reliability in detection and ejection. Depending on their specific needs, mining operations have the flexibility to increase sorter throughput while maintaining sorting efficiency, or increase sorting accuracy without impacting existing throughput. This is a real game changer.

Leave a Reply

Your email address will not be published. Required fields are marked *