Tag Archives: Artificial Intelligence

Windfall Geotek adds drones to AI-driven exploration tech offering

Mining technology services company, Windfall Geotek, says it has launched a new drone-based solution for artificial intelligence (AI) driven digital exploration in mining.

A services company using AI with a portfolio of gold, copper and zinc properties in Quebec, Canada, Windfall Geotek has been using AI and advanced knowledge-extraction techniques since 2005 in the mining sector. EagleEyeTM leverages this experience, it said.

Michel Fontaine, President and CEO of Windfall Geotek, said: “Our new services have allowed us to bring to market the survey, sensor, and AI-driven software for digital exploration. Our ability, in the mining sector, to find targets is directly tied to the quality of the source data we receive from our customers.

“EagleEye will allow us to work more closely with our customers, generating a better return for their investors with our CARDSTM AI-generated targets.”

Windfall’s CARDS (Computer Aided Resources Detection System) solution consumes open data from around the world to identify a high statistical probability of target identification within known areas of interest, the company said.

Don Moore, CEO of Playfair Exploration, a previous user of Windfall Geotek’s technology, said: “Windfall Geotek’s experience in collecting and analysing data has been proven over the past 15 years. We recently worked closely with Michel and his team on a great project in Finland.”

EagleEye will begin tests in mining sector with the acquisition and analysis of survey data. The company plans to partner with operators of leading surveying companies to obtain geophysical data and generate potential drill targets using drones, modified sensors, and the CARDS AI software system, it said.

Exyn drones help Rupert Resources map Pahtavaara gold mine

Exyn Technologies says it has completed a successful mission for Rupert Resources at its historic Pahtavaara gold mine in northern Finland.

By harnessing Exyn’s autonomous drones, Rupert Resources was able to produce highly detailed 3D models of the mine, which is otherwise completely inaccessible to traditional CMS tools or even manually piloted drones, Exyn said.

“Rupert Resources needed to plan for a potential restart of operations by estimating tonnage previously removed from the mine, as well as calculating the remaining ore in heavily restricted areas,” the company said.

Exyn’s fully autonomous aerial robots mapped 30 stopes in three days with a single drone. In addition, Exyn mounted a version of its robot to a car to scan all access drifts which, together with the stope maps, provided a complete mine map in under four days.

Jukka Nieminen, Managing Director of Rupert Finland, said: “Rupert is actively seeking new technologies where we think big gains can be made in terms of safety, productivity and accuracy.

“Exyn achieved accurate assessment of the volume of remaining stopes at Pahtavaara with an unprecedented level of detail, and obviously the use of remote technologies means that this was achieved with a greatly reduced degree of risk. We have no hesitation in recommending this technology.”

Exyn’s autonomous drones are built on the exynAI™ platform, enabling aerial robots to fly intelligently without a human pilot using a multitude of high-tech sensors and AI-based software, the company says. The system operates without the need for GPS or external communications, and is deployed as an all-in-one software and hardware package.

Raffi Jabrayan, Director of Markets & Industries, Exyn Technologies, said: “Our mission with Rupert presented some of the most difficult and seemingly impossible challenges to navigating, analysing, and assessing a mine – which therefore makes it exemplary in demonstrating the heights of Exyn’s capabilities.

“Our AI-based software and state-of-the-art sensors were able to get the job done quickly and safely, proving once again that no exploration task is impossible for Exyn drones.”

Zyfra leveraging AI for bucket tooth, fragmentation detection and analysis

Zyfra says it has developed an automated system using artificial intelligence (AI) to monitor the condition of excavator bucket teeth based on its machine vision BucketControl system.

The system is designed to detect the presence or absence of excavator bucket crowns quickly and features functions to alert the excavator operator if a crown is lost or ceases to work.

The application, developed jointly by the AI and Mining divisions of Zyfra, uses an on-board controller to acquire images from the camera, process and analyse them using internal software and sends a signal to the operator if a crown is lost or ceases to work. The wear of the tooth is also assessed, and when a critical value is reached, a notification is sent to the dispatcher, according to the company. This data is transmitted to the server in real time, Zyfra added.

Alexander Smolensky, Business Development Director of Zyfra, said: “With the help of machine vision, you can locate a broken tooth immediately and prevent it from getting into the crushing compartment, whose breakdown threatens the company with a loss of up to $200,000.”

He added: “When mining ore, a broken tooth may cause damage to the bucket, which would entail additional damage worth several million rubles. Our BucketControl system will ensure a cost reduction of 90% when finding a broken tooth.”

The automated system to monitor excavator bucket teeth has been further developed to look at fragmentation. This application measures continuously the size of the pieces of rock in the excavator bucket. “Correlating that size with the location coordinates yields a performance map of rock which measures the efficiency of rock blasting to balance the cost of blasting against the quarry output,” the company said.

Smolensky explained: “In contrast to images taken after the blast, the entire depth of exposed rock is analysed. That enables us to increase excavator productivity by up to 3%, minimises the chances of oversized pieces hitting the crushing compartment, makes it possible to track the quality of blasting operations and ultimately increase rock removal by up to 10%.

“Using the system to analyse previous blasting operations will also help determine the amount of explosives required for future blast works.”

GMG expands AI and automation focus with new projects

The Global Mining Guidelines Group (GMG) has launched new projects in the fields of artificial intelligence and autonomous equipment to ensure mining companies can best leverage these technologies.

The ‘Open Data sets for AI in Mining’ project will be used for building open data sets to advance AI research and development, while the ‘Autonomous System Safety’ sub-project (under the Functional Safety for Autonomous Equipment project) looks to deliver valuable context and education on system safety, GMG said.

As GMG states: “Open and curated data sets can enhance the ability to build meaningful solutions for the industry by providing typical data relating to assets or operations for training and testing models and improving benchmarking and research by offering an alternative to proprietary data.”

The open data sets project will seek to leverage what the wider AI community has learned over time and ensure the approaches used in the mining domain are consistent with best practices, it added.

In terms of deliverables, the GMG is hoping for three core outcomes. Namely, a register of suitable candidate data sets, a set of guidelines for the collection and curation of these data sets and a set of repositories of gathered data.

“AI research and progress in many spheres has benefited hugely from having a set of public and curated datasets,” GMG said. “This has allowed for developers and researchers to have suitable data to test and train their models on for a variety of applications. Even more importantly, it has provided data which can be used to benchmark various solutions and allow for effective and fair comparison, as well as allowing for research to be repeated and validated.”

The ‘Autonomous Safety System’ sub-project, meanwhile, covers overall system safety. It will be a white paper to “provide valuable context and education on system safety, its history in other industries and how to deliver safe systems that can be operated effectively”, according to GMG.

The GMG said: “An outlook that expands the focus from functional safety to system safety will enable improved outcomes to the delivery of autonomous mining systems because:

  • To ensure functional safety, autonomous systems need to perform their functions correctly;
  • A technological system and its design within the operating environment can influence human performance;
  • Delivering and benefiting from complicated and complex systems requires addressing the behaviour of their interactions;
  • Cybersecurity risks affect all aspects of autonomous system safety; and
  • A full picture of system safety is needed to achieve a balance of operations, reliability and other associated disciplines.

AI lays groundwork for process control improvements at Boliden Aitik

A series of tests at Boliden’s Systems Technology division has indicated that artificial intelligence (AI) could unlock further gains from its productivity efforts at the Aitik copper mine, in Sweden.

The company, which partnered up with ABB for these tests, conducted the AI studies to see if technology is available today that could make its concentrators “self-learning,” it said.

The trial took place during the autumn and took a closer look at how AI could be used by Boliden to optimise its concentration processes.

Aitik, meanwhile, is in the middle of an expansion plan that will see production increase from 36 Mt/y to 45 Mt/y of copper ore starting in 2020.

Development Engineer and Project Manager, Johannes Sikström, explained: “At Systems Technology, we develop dynamic simulations of our processes. These simulations can be used in the same way as a game where we define what is a win and what is a loss.

“In the case of self-learning algorithms – so-called deep learning or reinforcement learning – the challenge is the great quantity of data necessary for the algorithm to learn enough about the system for it to make effective decisions.

“This is why games are such a major area within AI research. Games are well suited to enable algorithms to train themselves, and what constitutes a successful result – a win – is also well defined,” he said.

The simulation models enable the company to re-create data equivalent to several decades in just a few hours, according to Boliden.

In its previous projects, Boliden primarily researched machine-learning techniques that analyse data without allowing the algorithm itself to influence it. The aim of the latest project was to allow the algorithm to self-learn instead.

Following initial studies into suitable tools together with Anders Hedlund from data analysis firm BI Nordic, the project led to a degree project in a collaboration involving ABB and Boliden. Max Åstrand from ABB was appointed Supervisor, with his colleague Mattias Hallén taking the lead.

Sikström said: “We directed our attention to the grinding process in Aitik, where we have a well-developed simulation model. We wanted to see if AI was able to do better than our existing control strategy.

“Mattias did a fantastic job setting up the architecture and getting the various environments to ‘play ball’ with each other. We were then able to test various algorithms and different goal functions.”

To begin, Boliden tested a “Q-learning algorithm” which had a goal of trying to control the mill’s load within a given range. After around 40 attempts, the algorithm taught itself to do just that, according to Boliden, acknowledging that it solved the task using a method that would not work in the real world.

In the next step, Boliden investigated the ability of the algorithm to optimise a “gain” instead of optimising a process variable. The goal function for the gain was created as a theoretical model using metal prices, grinding and throughput, for example.

Sikström said: “With this goal function, the AI algorithm succeeded in beating our PID (project initiation documentation) structure to produce a greater gain. So-called wall time was around 80 hours before AI had learned to run the process profitably, in this case equivalent to a plant operating time of more than 300 years.

“The study highlights the value of simulations, and the AI technology shows exciting development opportunities for Boliden’s future process control.”

While the test results were positive, with AI performing better than Boliden’s current control method, Sikström said further studies were necessary before the company considers approaching a viable production solution.

He concluded: “Several technical details need to be resolved, and it is important to use accurate simulation models and well-defined goal functions.

“Because an algorithm is only able to solve the problems formulated for it, process knowhow and experience are at least as important in this type of development as classic process control.”

First Ore-Mining looks to VIST’s AI solution for Pavlovskoye lead-zinc development

First Ore-Mining Company and ZYFRA have signed a memorandum of understanding (MoU) that could see the Pavlovskoye lead-zinc deposit deploy artificial intelligence-based solutions for mining and processing operations.

Pavlovskoye is set to become the most northerly mine in Russia, once First-Ore, a Rosatom State Atomic Energy Corp division, moves ahead with development. It is scheduled to have a 3.5 Mt/y ore processing capacity.

The MoU document was signed at the St Petersburg International Economic Forum by Igor Semenov, Executive Director of First Ore-Mining Company, and Igor Bogachev, CEO of ZYFRA.

Bogachev said: “It is more difficult for companies to operate in extreme climatic conditions because of factors such as the high cost of resources and special work safety regulations. The robotised systems offered by our subsidiary, VIST Group, including Intelligent Mine, will reduce equipment downtime by 10-20% and maintenance costs by 15-18%, thereby cutting production costs by 2-3%.”

Intelligent Mine is a set of digital technologies for managing open-pit mining processes based on robotised lоad and haul systems, together with industry solutions in the fields of artificial intelligence and predictive analytics. “One of the advantages of the system is that it enables extraction of minerals in inaccessible and remote regions with severe climatic and subsurface conditions,” the digital solutions provider for heavy industries said.

The parties aim to explore a possible project to implement robotics and remote control of quarry equipment at the Pavlovskoye deposit of the Novaya Zemlya archipelago. A bilateral working group will be set up within 45 days for this purpose, while the MoU covers a period of three years.

Semenov said: “Rosatom State Corp and First Ore-Mining Company have a strong focus on occupational safety. We are beginning this work in advance, so that the very first ore will be produced using advanced technologies in the safest possible conditions. Cooperation with Zyfra, which has extensive experience in developing digital smart solutions, will help us achieve this.”

Austmine 2019 to showcase global mining innovations

“Mining Innovation – The Next Horizon” is the tag line for the fast-approaching Austmine conference in Brisbane, Australia.

Taking place at the Brisbane Convention & Exhibition Centre from May 21-23, the program for Austmine 2019 has been developed specifically for those driven by innovation and working within mining companies, mining equipment, technology and services (METS) companies, as well as relevant academia and government, according to the event organisers. Over 800 attendees are expected at the bi-annual event.

“The Next Horizon for the industry will see fundamental shifts in mining technology which will alter the entire value chain, placing an emphasis on current planning decisions to ensure optimal future outcomes,” Austmine’s organisers said.

The three-day program contains over 40 presentations featuring more than 50 experts drawn from six continents, as well as hands-on workshops, panel discussions, and networking opportunities, held in conjunction with the sold-out exhibition, featuring over 90 of the industry’s foremost companies.

Austmine Chief Executive Officer, Christine Gibbs Stewart, said: “This is now the leading mining innovation conference in the world; there are a lot of conferences out there, but nobody is as sharply focussed on innovation as we are.

“We have brought together the premiere thought leaders around innovation, which is quite exciting for us; the fact that we have so many international speakers and attendees is a credit to our previous conferences.

“It demonstrates that overseas miners are interested in what is happening in Australia, and they see Australia leading the way with some of the new innovations and technologies that are entering the market.”

Current confirmed speakers include Rag Udd (Vice President, Global Transformation, BHP), Natascha Viljoen (Global Head of Processing Operations, Anglo American), Marco Orellana (CIO, Codelco), Rob Labbé (Director of Information Security, Teck Resources), Rafael Estrada (CIO & Manager of Information Systems, Telecommunications and Process Control, Antamina Mining), John Welborn (Managing Director & CEO, Resolute Mining), and Frans Knox (Head of Production, BMA Coal, BHP).

The conference themes range from new machinery technology and techniques, including automation and artificial intelligence, as well as the human element of mining, the use of analytics and big data, digital connectivity in mining, and finally sustainability for the industry, encompassing renewable resources and resource management.

The event features the Austmine Industry Leaders’ Dinner and Awards on May 22, which will also celebrate the association’s 30 years of advocacy for the Australian METS sector.

Schauenburg launches artificial intelligence camera for mine safety

Schauenburg Systems says it has partnered with dotNetix to deliver an artificial intelligence-equipped camera to improve safety at mine sites.

The South Africa-based original equipment manufacturer (OEM) for mine-industry safety and productivity solutions said this will enhance its existing proximity detection system (PDS) range.

The SCAS PDS Artificial Intelligence Camera is an advanced driver assist system (ADAS), which is the first South Africa developed and manufactured camera with artificial intelligence specifically designed for mine safety/traffic management, allowing for event and video logging.

It has been identified in the mining environment that there are certain scenarios where tag-based PDS systems are not practical. For these scenarios, object detection systems are required that use passive PDS sensor technology, according to the company.

“This technology, in layman’s terms, is when a vehicle PDS system can detect and warn a driver of other objects without having any active PDS equipment installed on these objects,” Schauenburg Systems said. “There are many passive sensor technologies that assist tag-based PDS systems or act as standalone PDS systems. Schauenburg’s AI Camera stands for high accuracy, reduced false alarms, distance detection and data/video logging capabilities for effective incident analysis.”

This camera, specifically designed for the harsh mining environment, combines 3D-image processing with AI integrated into camera systems. The system uses advance algorithms to detect objects; depending on the risk profile the cameras are positioned in front, rear or on the sides of the vehicle, the company said.

“The potential of a collision is analysed by the system and the driver is warned with an audible alarm and/or voice command. The 3D cameras were designed to accurately calculate the distance to an object by means of configurable dynamic zones of up to 150 m,” Schauenburg said.

Ettiene Pretorius, Business Manager at Schauenburg, said although the product is designed at this stage specifically to fulfil mining PDS requirements, it is evident there are many other applications where this product can assist in automating operations. “Schauenburg and dotNetix are excited about the official launch of this product, after the product went through stringent test, trial and certification phases which were part of the industrialisation process,” the companies said.

Dieter Kovar, CEO of Schauenburg International-Africa Group, said Schauenburg’s vision is to innovate new products through latest digital technologies and by ingraining a customer-centric culture.

“In line with the latest Mining Charter it strives for developing and manufacturing products primarily in South Africa. It considers itself as a prime partner for supporting the digital drive in mining,” he said.

Newtrax AI helps out Agnico Eagles’s Goldex mine maintenance team

Newtrax Technologies says it has applied machine-learning algorithms to help Agnico Eagle Mines’ Goldex mine predict mobile equipment maintenance issues up to two weeks in advance.

With the two companies already having an existing relationship at the mine, in Quebec, Canada, Newtrax was approached in the fall to discuss the data Agnico had collected from sensors over the past six years. This amounted to 10 billion data points, according to Newtrax.

“This data was exactly what was needed to apply machine-learning algorithms in order to predict mobile equipment maintenance issues at least two weeks before they were supposed to happen,” Newtrax said.

Daniel Pinard, Team Lead, Special Projects with Agnico Eagle, said this predictive Newtrax AI solution allowed the company to intervene before incurring serious problems that could potentially break vehicle engines.

“Through the use of machine-learning algorithms with Newtrax, we were recently able to analyse an engine that had a potential problem and we saved it from failing. This helped Goldex mine avoid serious damage on that engine which saved them C$85,000 ($63,610).”

The Newtrax AI solution is unique in three ways, according to Michel Dubois, VP QA & Artificial Intelligence at Newtrax, “first, Newtrax has years of unique data that is extremely well suited for machine learning (ML)”.

This creates a source of training data for ML that is unique in the world, with the data growing every time a mining company decides to join in, he said.

“Second, we have a unique AI team who knows how to generate actionable results using existing AI algorithms. And, third, we have a unique approach where our AI specialists go underground and focus on quick wins, and they leverage those existing algorithms to solve high-value problems.”

This is the first ever applied case study for ML in the underground hard-rock mining industry with a defined return on investment, according to Newtrax.

Newtrax said it worked with artificial intelligence and ML researchers such as IVADO to apply existing algorithms to the data collected in mine sites.

Codelco looks to Uptake’s AI solution for equipment maintenance gains

Uptake says it and the world’s largest copper producer, Codelco, are working on an artificial intelligence (AI) solution to monitor the health of mining equipment and ensure operations run efficiently and maintenance needs are predicted.

The agreement, part of Codelco’s digital transformation plan, includes mining and processing equipment at Codelco’s Division Ministro Hales (DMH) mine in Calama, Chile. In addition, Uptake will monitor grinding mills, roasters, crushers, pumps, haul trucks, and other machines with a view to creating a comprehensive and enterprise-wide Asset Performance Management solution across all of the company’s operating mines.

In 2017, the company’s DMH mine produced 215,086 t of copper alongside more than 126 t of silver.

Jaime Rivera, Codelco General Manager of the Andina Division, said: “Deploying artificial intelligence will allow Codelco to make best use of our operational data and allow us to reach our goals of boosting mining productivity, reduce costs and maintain safe machine operations through the predictive capabilities of Uptake’s Asset Performance Management (APM) software.”

Jay Allardyce, Uptake Executive Vice President of Industry, Product and Partnerships, said: “Codelco is the world’s leader in copper production and we’re pleased to support their digital efforts to make operations and maintenance expenditures more efficient by increasing visibility into the real-time and future health of mining machines.

“We are excited to partner with Codelco given their forward thinking to accelerate not only their operations, but the industry. With their data first approach coupled with our AI leadership, the transformation impact is outstanding and with leaders like Codelco it sets the tone for what is possible.”

Uptake’s APM software solution improves operational efficiency by leveraging AI to create business value from operational data, according to Uptake.

“Traditional asset management only covers routine maintenance tasks and fails to anticipate and adjust to the ways industry operates its business,” Uptake said. “Today’s asset-intensive environments require a new approach with industrial data science generating OEM (original equipment manufacturer)-agnostic insights, predictions and recommendations for any asset.”

By deploying Uptake APM, industry can unlock new operational efficiencies by making proactive maintenance decisions based on predictive insights, the company said. “Our industrial AI and machine-learning engines detect asset anomalies and help predict and prevent problems before they happen. Industry can also leverage the data analytics to understand how to drive more financial outcomes that impact business.”