Tag Archives: Artificial Intelligence

Rio Tinto to extend use of Palantir Technologies’ AI-based solutions

Automation, IoT, Mining services, Mining software, , , , , ,

Palantir Technologies Inc has renewed its multi-year enterprise agreement with Rio Tinto, extending the pair’s pact for an additional four years and securing Rio Tinto’s ongoing access to the Palantir Artificial intelligence Platform (AIP).

As an early adopter of Palantir Foundry (Foundry), Rio Tinto has already primed its operational landscape for the deployment of AI through the creation of a robust digital twin (or Ontology), Palantir says. Via the Ontology, AIP will enable Rio Tinto to build, test, and validate AI use cases at an accelerated pace and deploy them to production safely.

These AI use cases will follow and augment critical operational workflows Rio Tinto conducts in Foundry today. From managing plant operations to monitoring geotechnical risk to coordinating dozens of unmanned trains carrying iron ore, Foundry is enabling Rio Tinto to make well-informed decisions and take appropriate actions based on a single, unified source of truth, it added.

Bold Bataar, Rio Tinto’s Chief Commercial Officer, said: “Foundry has helped to transform the parts of our business where it has been applied. In our most high-stakes environments, we are empowering our people to find better ways of working, to improve how we operate our assets, increase performance and to innovate. The Foundry Ontology has made our structured data accessible, and AIP is doing the same for our unstructured data while enabling us to attack with pace problems previously deemed too complex.”

For network specialists and train controllers in the RTIO Operations Centre, in Western Australia, Foundry provides a view of rail operations, assembled from real-time data from hundreds of equipment units and systems in the value chain. With the Ontology providing a unified view of all assets, network specialists coordinate the haulage of iron ore by 53 driverless trains, each with 240 wagons, across the Pilbara rail network. They can optimise, collaborate on and execute complex routing decisions to balance production targets and maintenance needs. As a result, both railway throughput and safety have been improved.

In Mongolia, Foundry equips Rio Tinto with a dynamic understanding of geotechnical risk at Oyu Tolgoi, one of the world’s deepest and largest block cave mines. The mine’s challenging conditions require advanced risk management and constant surveillance to ensure safe production. The Ontology Rio Tinto has configured in Foundry integrates data from thousands of sensors across the mine and serves as a single source of information for cave health, instrumentation and risk, according to the company. This represents a new paradigm for block cave mining and has enabled various adjacent workflow innovations which will be further expanded through Palantir AIP.

Ted Mabrey, Palantir’s Head of Commercial, said: “We have high expectations for Rio Tinto’s utilisation of Palantir’s AIP based on what they have already achieved with Foundry and their ambition for secure use of AI. The Ontology created by Rio Tinto’s team in Foundry over the past three years enables fast deployment of AI solutions to some of Rio Tinto’s most pressing challenges and ensures best and safe operator practice in areas like risk identification, asset management, and supply chain order and fulfilment processes.”

AI-infused plug-and-play tech stack needed to further exploration, Tata Nardini says

Mineral exploration, Mining events, Mining services, Sustainable mining, , , ,

Technological innovation is the cornerstone of human progress. At their best the foundational technologies of the modern world – such as the global internet, digital technologies, space travel, clean energy, and AI – fill me with a belief that hard problems are not permanent fixtures in time and space, Flavia Tata Nardini* writes.

They are mutable barriers humanity must overcome to build a brighter future for our planet.

We now face a paradox on the road to net zero: delivering the minerals needed to fuel the global adoption of clean energy technologies depends on the rate of new mineral discoveries. That makes the global mining industry not only an essential partner on the road to net zero but elevates the complexity and structural obstacles involved in modern exploration as critical problems that must be solved to achieve climate progress.

Innovators in this field need a reality check: mineral exploration is a balancing act of constantly shifting macro-level conditions (market pressures, investment cycles, shifts in exploration strategy, regulation, budgets and price volatility, etc).

This means every exploration company faces unique operating conditions that are either enabling their progress, slowing it down, or forcing it into stasis. However, when you examine the challenges of explorers on the ground and how they compound across the exploration lifecycle, a clear innovation path starts to emerge.

At the project level implementing a strategy in highly remote and rugged environments with incomplete datasets and changing budgets can be a real struggle. Exploration teams are often being pulled in several directions at once while managing the planning, logistics, data interpretation, strategy modification and budget for each stage of their program.

Add the complexity of integrating vast amounts of data of various types and quality – each with their own weighted significance for the specific project – while reducing human bias in the analysis represent incredibly time and cost-intensive steps for exploration teams.

This is a significant contributor to why it takes up to 16.5 years to identify and operationalise a new mine (according to the International Energy Agency).

When I survey the technology landscape of the world today there are some very specific capabilities that can address these fundamental challenges in the exploration workflow.

Satellite connectivity, for real-time exploration data collection and processing. High-quality and scale invariant 3D multiphysics data, for streamlined integration of diverse 3D and 2D exploration datasets. Multimodal and multiscale artificial intelligence (AI) to radically narrow the exploration search space, enhance data-driven decision making, while also de-risking and identifying new opportunities faster.

Expecting major or early-stage explorers to cultivate the expertise and resources needed to develop and integrate these technologies is unreasonable: their focus is and needs to stay fixed on discovery. They also don’t need multiple new technology providers and software to build into their planning cycle and strategy, adding more complexity.

The real-time and predictive capabilities enabled by advanced satellite connectivity, real-time multi-physics data acquisition and AI must be combined into a plug-and-play technology stack that can be deployed rapidly at any stage of the exploration journey with minimal environmental impact. This represents more than just profound gains in efficiency at every level of exploration. It represents a unification of the end-to-end exploration journey, enabling data-driven learning in exploration on a previously unimaginable scale.

The key to maximising the value of high-quality real-time data acquisition and processing is AI. By linking a continuous feed of high-quality exploration data to custom multi-scale, multimodal AI models, the on-site teams working on the frontlines of exploration today can integrate and interpret vast amounts of data, challenge hypotheses and arrive at actionable decision points faster. This creates shorter and more insightful learning cycles, strengthening a positive feedback loop of enhanced decision making at every stage of the exploration journey.

Looking at the arc of mining innovation before us, I see a deeper integration of these technologies across the global exploration value chain.

As we continue to strive for a net-zero future the operational challenges involved with mineral discovery can no longer be viewed as isolated hurdles. They must be addressed through a unified technological approach that empowers exploration teams with real-time data, AI-driven insights and streamlined workflows, enabling them to deploy resources towards opportunities faster, with enhanced precision, while minimising environmental impact.

Instead of accepting complexity and operational headwinds as table stakes, we must view them as opportunities to drive down the time and costs involved between each step of the exploration journey using the latest wave of innovation in space, 3D multi-physics integration and AI.

With this approach we can meaningfully reduce the time to discovery, unlock sustainability across the mining lifecycle and set the industry up for a renaissance in data-driven exploration. Then, as mineral supply and demand equalises, clean energy technologies scale, and the inputs needed for the advanced technologies of the future are secured, the critical role of our industry will come into focus as the foundation of the clean energy future we aim to build.

The convening power of IMARC drives the future of the global mining value chain into the present. IMARC’s invaluable role in forming a shared understanding of the challenges we face, opportunities for collaboration, and solutions that can move the industry forward, is critical to the progress we work tirelessly to achieve.

We look forward to seeing you there!

*Flavia Tata Nardini, co-founder and CEO of Fleet Space Technologies, is a keynote speaker at IMARC 2024 in Sydney, Australia, from October 29-31. International Mining is a media sponsor of IMARC 2024

Metso plays software hand in face of mining market competition, industry challenges

Automation, Comminution of minerals, IoT, Mining equipment, Mining services, Mining software, Sustainable mining, , , , , , , , , , , , ,

With the mining industry’s growing understanding and openness to the benefits of digitalisation and artificial intelligence (AI), it was only a matter of time before some of the big OEMs ventured further into the software development space. That time is now with Metso having, today, opened a Digital Design and Development Studio in Krakow, Poland, to complement its already wide digitalisation offering.

Many mining companies around the world regularly interact with software carrying the Metso name: think of the ACT/OCS-4D™ platforms for advanced process control, the Geminex™ digital twin and HSC Chemistry for minerals and metals process simulation and optimisation, or the Metrics monitoring service.

The company’s latest software developments will go beyond these legacy solutions, leveraging what it refers to as “leading-edge digital capabilities” to solve some of the industry’s major issues.

Olivier Guyot, Senior Vice President for Minerals Digital at Metso, admits the minerals industry might have “missed the first train” when it comes to developing software that leverages AI and machine learning, but he still sees a major market opportunity for Metso, with customers more prepared to embrace digitalisation.

“We have recently had many customer meetings where we have shared our digital strategy,” he told IM. “It has been clear from these interactions that there is an opportunity for us to make inroads into this market.”

Metso doesn’t have an intention to compete with pure software players in this space. It is also cognisant its customers will not be open to adding another vendor to their already extensive list of digital suppliers without a proven value proposition.

“As a result, what we are focused on when it comes to software development, user experience design, data and AI is related to our expertise – equipment, services, process and materials technology, etc – and how to embed and integrate it seamlessly into an already mature plant ecosystem,” Guyot added.

“We really see digital as a complement to our core competencies, rather than something separate.”

When broken down, the rationale for Metso dipping its toe into the software development space now makes sense.

Guyot explains: “I feel we also need to go back to basics: start off with the right level of automation, sensors and analysers at site – these are the data generators. Without the optimisation of these hardware elements, the data coming back will not be accurate enough to produce valuable digital insights and analytics. This is the information that AI and machine-learning algorithms require.

“Without the right quality of data and the right domain knowledge, the outcome of these AI solutions might not be directly usable. We feel we have that domain knowledge, providing a legitimate claim to come and deploy our expertise digitally in many forms for our customers.”

The growing number of digital experts working in the Krakow office – currently estimated to be around 50 – can build these software solutions with knowledge of the underlying hardware in mind. This knowledge will come from interactions and collaborations with product and service experts, personnel at Metso Performance Centers across the globe, and more.

Geminex
Metso’s Geminex uses “first-principle” dynamic process and equipment models for calibrated performance to help provide an ‘accurate’ digital twin for existing operations

The brief for these digital designers is to focus on three key areas:

  • Equipment performance to provide digitally-enhanced Life Cycle Services (LCS), remote condition monitoring and prescriptive maintenance;
  • The process performance digital portfolio to optimise customers’ ore-to-metal operations for efficiency and sustainability; and
  • Business enablement to enhance customer experience and improve employees’ productivity within a data-driven, AI-augmented environment.

“To support these three priorities, we need to continuously develop our digital capabilities and that is what we are doing in Krakow to complement our existing capabilities,” Markku Teräsvasara, President Minerals & Deputy CEO at Metso, told IM.

Of course, the investment in this studio also reflects the industry’s continued requirement to address a growing labour and skills shortage, as well as the expected need to produce more metals for the electrification transition.

“If the industry is to produce more metals in a more sustainable and safe manner, digital solutions will be needed,” Teräsvasara added.

There is clearly an opportunity for Metso to leverage software as a market differentiator, but the move also reflects a growing sense of responsibility to in-source more of the digital supply chain.

Guyot explained: “Cyber security is not something we can delegate to anyone when it comes to servicing customers – especially with more of the information being on cloud-based platforms now.

“The Krakow Studio will allow us to responsibly develop this software hand in hand with cyber security in mind.”

And Guyot and Teräsvasara say this software development responsibility goes beyond just the Metso equipment portfolio, with customers able to also use this new software on all their equipment, irrespective of the supplier.

“Our software will be available to ourselves and our customers,” Teräsvasara said. “We will help our customers with all their equipment and performance issues, as we do with some existing LCS contracts.”

With the investment in this new Digital Design and Development studio, Metso is putting another marker down that could have positive ramifications for its customers and the wider mineral processing sector.

Major Drilling eyes unique AI-powered offering with DGI/KORE partnership

Mineral exploration, Mining mergers and acquisitions, Mining services, Mining software, , , , , , , , , ,

Major Drilling Group International Inc has announced a new partnership with downhole technology company DGI Geoscience Inc (DGI) and its affiliate company, artificial intelligence (AI)-powered core logging tech innovator, KORE GeoSystems Inc, that, it says, positions Major Drilling at the forefront of AI advancements in the drilling industry.

The combination of Major Drilling’s fleet, skilled drilling teams and its TrailBlazer Rock5 technology, with KORE’s digital rock analysis platform, provides the opportunity to deliver valuable data to customers, Major Drilling says. This is complemented by the borehole data acquisition services offered by DGI to provide a unique service offering in the industry today, it added.

Denis Larocque, President and CEO of Major Drilling, said: “This alliance is a continuation of Major Drilling’s progression in drilling innovation, and also part of our growth strategy as we invest in the future of mining.”

Marc Landry, newly appointed Chief Technology Officer, added: “As our traditional drilling services evolve, the full complement of DGI/KORE products and services alongside Major Drilling’s developing technologies will see our service offering transform and help our customers during this mining upcycle. For example, KORE uses AI to automate processing of core logging, greatly reducing time and improving consistency, enabling our customers to get real-time, remote access to results across the globe.”

Under the agreement, Major Drilling will acquire an approximate 40% interest in DGI/KORE for a C$15 million ($10.8 million) cash consideration. As part of this investment, Canadian Shield Capital, a Toronto-based growth equity firm, is selling its interest in DGI/KORE.

The value of this transaction for Major Drilling resides in adding geological solutions to its specialised drilling, providing a unique service offering that encompasses the latest advanced technology, it says. This investment supports the company’s efforts to position itself as the contractor of choice to the drilling industry by providing solutions to help accelerate customers’ projects with timely and quality data contributing to their geological model.

Vince Gerrie, President and CEO of KORE, said: “We are thrilled to support Major Drilling with KORE’s cutting-edge SPECTOR integrated technology suite. Our transformative AI powered digital core logging platform significantly increases productivity, consistency and enhances data insights for our customers.”

Chris Drielsma, President and CEO of DGI, said: “Through our powerful new partnership with Major Drilling, the mining sector can access turnkey geological, geophysical and geotechnical drillside orebody intelligence solutions. We are very excited to be part of this evolution of drill performance, helping maximise the value from drilling through our geoscience solutions.”

TOMRA taps into deep learning AI network for latest ore sorting advances with OBTAIN

Automation, Comminution of minerals, Environmental, Mineral processing, Mining services, Mining software, Sustainable mining, , , , , , , , ,

TOMRA is looking to leverage artificial intelligence as part of a plan to unlock new opportunities for mining operations using its sensor-based sorting technology.

The company explained: “The ability of computer systems to mimic human thought and decision making to perform tasks that traditionally required human intelligence has played an important role in TOMRA’s sensor-based sorting solutions for decades, automating the process and improving the accuracy and efficiency of the sorters, unlocking value for mining operations.

“Over the years, sensor-based sorting technology has developed, and TOMRA has been using machine learning in its X-ray Transmission (XRT) and Near-Infrared (NIR) sorters for the last 10 years.”

Now TOMRA Mining is opening a new era in sorting with its latest innovation, OBTAIN™, which leverages deep learning to bring single-particle precision to high throughput particle sorting, it says. This solution takes capacity, quality and recovery to a new level, and unlocks value through a wealth of extremely detailed and accurate data for better-informed decision making, it added.

This software uses a neuronal network to identify the properties of each particle accurately and independently of the sorter’s capacity, achieving new-found precision and reliability in detection and ejection. Based on its specific requirements, the mining operation has the flexibility to either enhance the throughput of the sorter while maintaining consistent sorting efficiency or improve sorting precision without compromising the existing throughput.

TOMRA says: “OBTAIN proves advantageous for a fully operational mine by enhancing recovery rates and elevating product quality within the existing throughput. Conversely, in mines with additional capacity, it facilitates increased throughput without compromising product quality. Furthermore, this innovative technology has the capability to unlock untapped value from low-grade ore, waste dumps, or materials previously deemed uneconomical for processing.”

OBTAIN will also add value to a mining operation with a wealth of extremely detailed and accurate data, such as precise online particle size distribution of the feed.

When used in combination with TOMRA Insight, it can provide the customer with detailed reporting on the performance of the sorter and its components to help them optimise the process, as well as enable them to plan for predictive maintenance, the company says.

The OBTAIN software has been developed for TOMRA’s XRT sorters. It will be available on new models, but there will also be an upgrade package available for existing machines, providing a significant opportunity for customers already operating TOMRA XRT sorters, to substantially enhance the sorting performance where it proves to be a suitable solution.

TOMRA has partnered with two customers to test the OBTAIN in real working conditions. The software has been operating for close to 18 months at the Wolfram Bergbau & Hütten tungsten mine in Mittersill, Austria, where it has delivered consistent and reliable performance. The vicinity of the mine to TOMRA’s development team, based in Germany, has made it a suitable testing ground for the first phase, as they have been able to monitor it closely. A second phase of testing to quantify the improvements has been carried out with a trusted long-standing customer in a magnesite application. The successful tests have shown that OBTAIN is ready to transform sensor-based XRT sorting in numerous applications, according to TOMRA.

Hexagon to Augment blast movement offering with AI-based partnership

Explosives and blasting, Mining services, Mining software, Sustainable mining, , , , , , ,

Hexagon has announced it is partnering with Western Australia’s Augment Technologies to help mines maximise ore yield and optimise operational efficiencies by accurately accounting for blast movement.

The partnership will harness a blend of block model data, artificial intelligence (AI), bespoke movement models and measured 3D movement data to create a blast movement solution that enables mines to unlock significant value, Hexagon said.

The Hexagon MinePlan Block Model Manager enables users to simultaneously and effectively design, populate, manage and share block models while centrally managing the amount of sample points, variables and outputs associated with orebody data.

Augment Technologies, meanwhile, leverages a physics engine powered by an AI algorithm to create a Muckpile Block Model™ that is continuously improved through a machine-learning process. The process uses vast amounts of blasting data to ensure that the model’s controlling parameters and simulated physics are as accurate as possible, resulting in a bespoke solution for each customer, the company says.

The collaboration between Hexagon and Augment will allow customers to view and manage the Muckpile Block Model that retains all the data and fidelity of the grade control model, with high accuracy and resolution. Users will have the option of incorporating Hexagon’s Blast Movement Monitors as an additional measure for blast movement and for training the AI model, with transparency into all the data inputs and output, it says. They can also combine operational data with insights from the Hexagon Block Model Manager API to help optimise upstream and downstream processes, all within its geological modelling software platform.

“The implications for the industry are profound,” James Dampney, Vice President, Resource Optimisation, Hexagon’s Mining division, said. “Ore loss, dilution and misclassification cost mines millions of wasted dollars a year. Our partnership with Augment Technologies will help mines to optimise digging locations and downstream handling of ore, resulting in valuable processing efficiency and reductions in energy consumption.

“Customers will save training time and operation time by remaining in the same software used to model their ore. The incorporation of an industry-first block model manager provides auditability and traceability to reduce errors while managers and corporate stakeholders will see time-stamped changes of the block model.”

Augment Technologies co-founder and Chairman, Greg Hardwich, said the partnership was setting a new industry standard in minimising ore loss and dilution due to blast movement, bringing enormous efficiency to mining processes.

“We’re very excited to be working with global autonomous technology leader Hexagon to inject our AI-powered capability to create a Muckpile Block Model, transforming the way blast movements are modelled and measured to create significant value for our customers,” he said. “Through this partnership, Hexagon’s customers will have the opportunity to realise demonstratable reductions in ore dilution, allowing miners to return more consistent grades, and higher tonnages of ore for processing.”

Eramet’s SLN leverages Rockwell control system to improve uptime at nickel furnace

Automation, Base metals, Mine operation news, Mineral processing, Mining services, , , ,

Société Le Nickel (SLN), part of the Eramet Group, has managed to improve uptime at its nickel furnace in New Caledonia by leveraging a new control system from Rockwell Automation.

Processing ores is a complex activity requiring the stable control of the rotary furnaces’ temperature profile and automating operations across different operating ranges. Feed ore introduced into the rotary kiln undergoes calcination as it travels through the length of the furnace. If the calcined product is not at a high enough temperature, product quality is compromised.

Heat is distributed across the furnace with air being supplied for combustion to occur. If there’s too much air supplied, more fuel needs to be burned to maintain the same product temperature, thus decreasing energy efficiency. Excess oxygen must be minimised to a safe level to reduce operating costs and greenhouse gases.

SLN was using an expert system, an existing fuzzy logic controller, designed to automate the operation of the furnace. However, the company faced several challenges with the legacy system, particularly with varying ore content and variable heating values leading to temperature spikes and frequent electrical trips, Rockwell explained. Trips were being caused by high product temperature, which compromises both the quality of the product, and the integrity of the equipment.

“The fuzzy logic was unable to reduce fuel fast enough to prevent trips from occurring and when in manual operation, the operators were not able to react quickly enough,” Leslie Hii, one of Rockwell Automation’s Advanced Process Control Engineers responsible for delivering the SLN project.

“Maintaining the required furnace temperature can be complex and challenging given the number of variables that need to be managed. Fuel type can be oil, coal, or a mixture of the two – each with their unique thermal characteristics. Moreover, the rate of feeding material impacts the furnace temperature and needs to be carefully managed.”

SLN upgraded to Rockwell Automation’s FactoryTalk Analytics Pavilion8 to boost efficiency and performance (image copyright: Société Le Nickel, part of the Eramet Group)

The expert system can only be turned on when the furnace is operating normally and, in the event of any instability, the operators turn it off and take control. The expert system also rated poorly in terms of user friendliness and ease of maintenance, both factors contributing to low system uptime, Rockwell said.

To rectify the situation, SLN upgraded to Rockwell Automation’s FactoryTalk® Analytics™ Pavilion8®. This model predictive control (MPC) solution offers an intelligence layer that sits on top of automation systems and continuously assesses current and predicted operational data, according to the company. It then compares this data with desired results, and drives new control targets to reduce process variability, improve performance and boost efficiency – all autonomously and in real time.

“Using a MPC solution is an ideal example of how Rockwell Automation is using artificial intelligence to drive better operational results by making use of available data,” Hii said. “In this project, we also used machine learning, process knowledge and data to develop kiln models tailored to SLN’s operations.”

The initial phase of the enhanced solution was successfully completed in just 13 months in contrast to the years it took to implement the expert system. It has already been implemented in five rotary furnaces at SLN’s facility. Operators now have the option to minimise the usage of high value fuel oil while maximising lower value pulverised coal during mixed mode operation, Rockwell said.

Mickael Montarello, Process Control Manager, SLN, said: “The MPC application can handle significant variability on ore feed and heating values and prevents trips from occurring, allowing the furnace to stay in operation at a higher rate. The calcined product temperature error was reduced by 6% and the furnace temperature profile variability reduced by 16.1%.

“The average uptime of Rockwell’s MPC is 83% compared with 70% with the earlier expert system. The new solution allows the furnace to stay in operation for longer.”

He added: “Users appreciate the tool’s user-friendliness and flexibility. In the event of a problem with one element of the process, operators can easily intervene on the element in question, while allowing the MPC to continue controlling the other manipulated variables.

“Thanks to this tool, new opportunities for optimising control and management are opening up, which were not possible with the old fuzzy logic controller. Our target for 2024 is to achieve a 90% utilisation rate.”

Testing: the secret sauce of Sandvik R&D

Automation, Communications in mining, Environmental, Explosives and blasting, IoT, Mining equipment, Mining maintenance, Mining services, Mining software, Power supply for mines, Sustainable mining, , , , , , , , , , , , , , ,

Jani Vilenius has his plate full at Sandvik Mining and Rock Solutions. As Director of Research and Technology Development, he is brought into most conversations the business area has about future mining products.

In fact, he even works across the Sandvik Rock Processing business area on occasion, as well as overseeing the design centre in Bangalore, India, which provides “value engineering” across Sandvik Mining and Rock Solutions divisions.

“We coordinate research programs and projects, not products,” Vilenius told IM recently in the company’s newest office in Tampere, Finland. “This may be overseeing the concept machines that we have been producing for several years, as well as technology partnerships with universities.

“We aim to think long term within the Research and Technology Development and Services team, but not too long term as the world is much more agile nowadays than it used to be.”

This means Vilenius’ team has to coordinate all of the activities taking place at the Test Mine in Tampere, provide a ‘steer’ on engineering services and safety processes needed to satisfy today’s and tomorrow’s requirements and regulations, drive cybersecurity and sustainability developments across Sandvik Mining and Rock Solutions in the R&D phase, plus integrate the thinking between the rapidly-expanding Digital Mining Technologies division within Sandvik Mining and Rock Solutions and the R&D team.

And, as of a month ago, his team also coordinates testing at the new Surface Test Pit: a new surface mining test bed being developed 40 km northwest of the underground test mine.

This is all underwritten by the strategic priorities across the business area he primarily works in, as well as the Sandvik group goal of ensuring 25% of revenue comes from products that are less than five-years-old.

To tackle these tasks, he has a sandbox (soon to be two) that all equipment providers would like to have.

The Test Mine in Tampere comes with 6 km of tunnels at a depth of 40 m, with potential to expand further. Positioned beside a glass factory and close to the company’s rock drills factory, this test mine offers the company and its customers everything they need to make strategic business decisions in an environment that can, for instance, replicate the heat and humidity of a deep underground mine in South Africa, as well as the biggest and widest mine galleries the industry has on offer.

This facility – which has everything your typical underground mine has except a daily throughput target – allows the company to run all its underground drills through a rigorous testing procedure prior to customer dispatch. It also allows the various divisions under the business area a chance to test out prototypes, applications and products from time to time.

For the concept machines Sandvik is becoming renowned for, the test mine acts as a place to validate conceptual thinking in a real-life environment, helping engage customers in detailed discussions as to what on-board and off-board technology elements would provide the greatest value to their operations in the near-, medium- and long-term.

The aim is to replicate this process on surface with the Surface Test Pit, providing the catalyst the company needs to reach its ambitious surface drilling market goals over the next several years.

IM sat down with Vilenius to find out how he coordinates all this R&D work, and how day-to-day testing works from a practical perspective.

IM: I imagine your department is inundated with requests from various business lines when it comes to testing. How do you go about prioritising these requests and turning them into an easy-to-follow roadmap that can lead to commercial solutions?

JV: I’ll answer that by taking a step back.

We have a technology focus built on supporting both Sandvik Mining and Rock Solutions and Sandvik group strategy. We then have roadmap items where we try to leverage technologies across many applications. These technology platforms are not always 100% suitable for both surface and underground mining, but there are elements that have similarities. For example, our latest electric concept surface rig uses the same thinking and philosophy used on other concept machines for underground. Of course, there are new elements included, but the platform thinking remains in place.

Jani Vilenius, Director of Research and Technology Development

Based on this, we have different forums and conversations with the divisions and the R&D heads, discussing together where we need to put the focus in terms of testing. There are, of course, differences in sizes of the division with those who invest a bit more in R&D entitled to more access, but we also have to remain strategic about how to capture the market attention within Sandvik Mining and Rock Solutions; knowing when and what to launch, as well as what developments will allow us to achieve the required technology momentum to support both our own internal goals and the goals set by our customers.

With all these technology developments – projects, concept machines, theoretical testing – there needs to be a value proposition. For the concept machines, for instance, there is value from a marketing perspective to showcase Sandvik as a technology leader, but there is also the value of engaging with customers in conversations that, through the actual machine development, allow them to comprehend what the technology may mean for them on a practical operational level.

This rapid agility – which I would say is unique to Sandvik – means we can receive valuable customer feedback on these concept machines before we commercialise certain elements. It allows us to effectively manage risk in a market calling out for technology breakthroughs to solve complex challenges.

IM: How many tests/trials can you have going on at the same time at the Test Mine?

JV: It varies. All underground drill products are tested there before they go out to customers, which puts a lot of load on the facility, while ensuring that when customers get these units, they have been run in an environment similar to a real-life mining operation.

Then we have new prototypes not under my remit that are tested ahead of becoming ‘products’, for example in underground drilling. Then, we have several technologies we test on a daily basis with different types of test benches and subsystems.

The reality is that we would not be as agile as we are without this test mine. It is not easy to go to a customer site and get permission to test equipment as it can negatively impact their (the customer’s) production. The ability to test at our own facility gives us a layer of comfort and confidence ahead of getting to the customer site.

We cannot try or test every application in our test mine, but those scenarios we do test provide real value.

IM: Are there plans to expand the test mine further?

JV: We have a roadmap for our test mine, but this is determined with a cost versus value equation. We don’t want to have empty tunnels without testing going on regularly.

We have all the opportunities to have a third, fourth and fifth level at the Test Mine. We have, for example, recently expanded into a new area to support our underground drill products to allow testing for that. This is a function of the offering getting wider and the need to expand the tunnels to make sure the new products receive the same testing opportunities as the existing ones.

We have expansion plans focused on automation and electrification too.

IM: Speaking of automation, is fully automated (without any personnel involved) battery swapping one of the ongoing projects you are working on?

JV: I can say we have some ideas on this. It is a topic that needs addressing and discussing as automation is coming on all our equipment and all processes in the future.

Fully automated battery swapping testing is, of course, part of the roadmap.

IM: I also understand that your team originally came up with the MineGame tool for modelling battery-electric equipment fleets and infrastructure. What was this designed for?

JV: Yes, this is a tool we needed to develop to support fleet-wide electrification. It is not designed to recommend the type of machine you will get; it is more about how you implement the many electric machines in the mine, what impact this has on infrastructure, how many tonnes we can get out of different fleets, etc.

This modelling tool gives comfort to customers about the value proposition of fleet-wide electrification, while also showcasing how new, developing technologies can be implemented in greenfield and brownfield mines.

This tool – on top of those from Deswik and Polymathian within the Digital Mining Technologies division – will be a game changer for us.

IM: What about the interaction of manual and autonomous equipment? Is this something you are already testing at the Test Mine?

JV: This is an ongoing requirement from customers, who look to always alleviate production stoppages.

It is not an easy challenge to address though. Everyone knows we want to get safe systems in place with a mixed fleet as not all machines are currently automated.

There is obviously a value case for this, and the Test Mine is a good place to test it out.

All I can conclude with is to say we have many tests going on in the Test Mine…

IM: A cheeky question, I know…What will be the next concept vehicle? You’ve set yourself a big challenge with bringing one of these out every year. How are you keeping up with this?

JV: We have smaller concepts, and we have bigger concepts on the table. We need to ensure we develop the technology to get those concepts done in a timely manner and in a way that, as I keep saying, provides value.

Maybe the next one coming out will be one of those smaller concepts.

Then, of course, we have wild ideas for underground equipment further down the line.

IM: The Digital Mining Technologies division is becoming a much bigger part of SMR. Do you see a point where you will start using the day-to-day data coming off sensors on your machines to revamp existing machine designs and come up with new machines?

JV: Yes, this is mandatory for us to do at some point in time. Integrating data from the field and systems into the engineering process is a tried and tested policy in many industries – some of which Sandvik are serving – so we need to do that more in mining.

The big step I foresee on this front is when we truly understand the value of using artificial intelligence in mining. Leveraging these tools will ensure there is a continual optimisation loop that goes throughout our software, hardware and services.

SentianAI

Weir expands digital capability with acquisition of AI-focused SentianAI

Automation, Comminution of minerals, IoT, Mineral processing, Mining mergers and acquisitions, Mining software, Sustainable mining, , , , ,

Weir has acquired Sweden-based SentianAI in a move that, it says, will accelerate its technology roadmap and expand its digital capability to provide enhanced productivity and sustainability offerings to customers. SentianAI is a developer of artificial intelligence-based solutions that optimise performance in minerals processing. Founded in 2016, it is based in Malmö and has a team of software developers and data scientists.

The software that SentianAI develops uses advanced AI algorithms that continuously learn and adapt to the dynamic processes within a mine, providing continuous improvement and optimisation over time, Weir says. Jon Stanton, CEO of The Weir Group, said: “Digital technology has an important role in helping address the challenges of declining ore grades, production efficiency and CO2 emissions for our customers. SentianAI’s advanced software solutions complement and will bridge our Synertrex® and Motion Metrics™ technologies well. Together, these will enable us to provide holistic performance monitoring and optimisation for smart, efficient and sustainable mining.”

Earlier this year, SentianAI and Xore Analyzers formed a strategic cooperation to combine XORE’s XRF analysers, which provide real-time data on metal content, with SentianAI’s machine-learning technology, which adapts to variations in ore properties. The pact, SentianAI says, could allow mining operations to improve their recovery rates and overall efficiency.

IM interviewed SentianAI Founder and CEO Martin Rugfelt last year on its technology and approach. He said it already had a flotation project targeting increase of recovery rate but also the stabilisation of the circuit performance. It was also working on optimising a crushing and grinding circuit with the primary goal of an increase in throughput.

Martin Rugfelt, SentianAI Founder and CEO

When asked how its approach differed to other AI approaches in industry he commented: “A lot of the ‘traditional’ AI systems we see are actually AI toolkits/platforms that are sold on the basis that the customer can create AI logic that they need to solve specific problems without having to understand the detailed data science. Unfortunately, without knowledge of the underlying AI and data science, creating AI for complex systems eg control processes is very difficult. As a result, many ‘traditional’ AI systems are abandoned after purchase. Sentian has taken a different approach. Our SentianController is explicitly designed to optimise control of industrial processes, so when customers buy it, they already have the AI algorithms developed and tested for the complexity of control system optimisation. It is effectively a point solution that means you do not need a large data science team to build and run the AI solution.”

He added on the underlying technology: “SentianAI has worked for many years to select the best algorithms and refine how these algorithms work to deliver a unique AI system that has been designed to control and optimise industrial processes. This is very complex and requires some of the latest technologies in AI to be able to achieve the necessary control. We have also developed a system that can uniquely be applied in stages as data quality improves and operator confidence increases – going from making recommendations to fully autonomous control at the speed our customers want. This allows customers to build confidence before committing to fully autonomous control. We have chosen not to patent our solution as it would have exposed the technology, however, we would argue it is very unique.”

He said the system is also capable of self-adaptation, which can be achieved when you have both the right data and the right AI models. “The AI creates a dynamics model that is made from both historical and ‘live’ operational data. It can then choose the set of control parameters that deliver optimum performance towards a specific goal, eg maximum production for minimum energy usage. In comparison to traditional supervisory control systems it adapts to changes in the process. For example, if the process changes for some reason, leading to new data points, the AI incorporates these into its model, new predictions are made, and new control parameter settings are used. New goals can also be set, resulting in SentianController choosing the best control parameters to achieve those goals.”

Humyn.ai and Dundee Precious Metals put out call to accelerate mineral discoveries

Mineral exploration, Mining services, , , , ,

Humyn.ai has partnered with Dundee Precious Metals to launch a crowd-sourced open data competition looking to fast track the discovery of mineral deposits.

The competition, which will run until May 2024, is a worldwide call for geologists and data scientists to collaborate with the DPM team and develop innovative ways to accelerate mineral discoveries.

Humyn.ai says: “Mineral exploration currently has a less than 1% success rate globally, in terms of discovering new economic orebodies. One of the challenges, especially on the near-mine data rich exploration environment, is the increasingly complex and multi-layered datasets that geologists need to collect and further integrate with already available heterogenous historical data.”

Dundee Precious Metals sees this challenge as an opportunity to work closely with geologists and data scientists, to share industry, technical and site-specific knowledge in order to collaboratively develop an innovative targeting approach applicable in such an environment, Humyn said.

The Future Explorer Challenge comes with the chance to win up to $250,000 in prizes, as well as the prospect of future closer collaboration with the DPM team, Hymun.ai says.

David Rae, President and Chief Executive Officer of Dundee Precious Metals, said: “We are excited to be launching this innovative competition. While the overall objective is the potential discovery of significant new deposits, we are also targeting the opportunity to work with top innovators – both geoscientists and data professionals – to develop new ways of unlocking the value in our data.”

Humyn.ai Founder and Director, Holly Bridgwater, said: “This crowd-sourced data competition will engage a global community of innovators, many of whom have no experience with the mining industry. We can’t wait to see how people with diverse skills from around the world will contribute to solving a hard problem faced by industry.”