Mining
This industry comprises establishments primarily engaged in manufacturing oil and gas field and underground mining machinery and equipment.
Assembly Line
Mining Technology from Lab to Market: VC Insights for Deep Tech Startups
The mining industry, particularly advanced mining, is facing significant technological and environmental challenges. These hurdles not only slow down progress but also present opportunities for innovation.
Let’s take a look at 3 main areas in the mining value chain where new solutions are needed today:
- Low Hit Rates in Exploration: A Fundamental Challenge
- Comminution: Tackling Energy-Intensive Rock Grinding
- Waste Valorization: Turning Byproducts into Resources
Watercycle Technologies Achieves Major UK Breakthrough in the Production of Large-Scale Battery-Grade Lithium Carbonate from UK Brines
Watercycle Technologies Ltd, a climate tech spinout from the University of Manchester specialising in the development of sustainable mineral recovery systems, has produced over 100kg of battery-grade lithium carbonate from UK-sourced brines. This result represents a major achievement towards building a robust battery innovation ecosystem in the UK and developing a globally competitive battery minerals supply chain.
Dr Ahmed Abdelkarim, CTO and Co-Founder highlighted ‘These results mark yet another technological breakthrough by our DLEC™ technology, one of the first in Europe to produce such quantities of lithium carbonate crystals. We understand our customers’ needs to obtain this product more efficiently, so we’ve designed our end-to-end solution to meet this demand. With the ability to generate refined lithium carbonate onsite, our technology offers customers the ability to capture more of the value chain. We are now positioning ourselves to supply lithium salts at the ton-scale for OEMs and chemical suppliers.’
Hybrid machine learning approach for accurate prediction of the drilling rock index
The drilling rate index (DRI) of rocks is important for optimizing drilling operations, as it informs the choice of appropriate methods and equipment, ultimately improving the efficiency of rock excavation projects. This study presents a hybrid machine learning approach to predict the DRI of rocks accurately. By integrating grey wolf optimization with support vector machine (GWO-SVM), random forest (GWO-RF), and extreme gradient boosting (GWO-XGBoost) models, the aim was to enhance predictive accuracy. Among these, the GWO-XGBoost model exhibited superior predictive performance, achieving a coefficient of determination (R²) of 0.999, mean absolute error (MAE) of 0.00043, root mean square error (RMSE) of 1.98017, and severity index (SI) of 0.0350 during training. Testing results confirmed its accuracy with R² of 0.999, MAE of 0.00038, RMSE of 1.80790, and SI of 0.0312. Furthermore, the GWO-XGBoost model outperformed the other models in terms of precision, recall, f1-score, and multi-class confusion matrix results for each DRI class. The GWO-RF model also demonstrated high accuracy, ranking second, while the GWO-SVM model showed comparatively lower performance. This research aims to advance rock excavation practices by providing a highly accurate and reliable tool for DRI prediction. The results highlight the significant potential of the GWO-XGBoost model in improving DRI predictions, offering valuable intuitions and practical applications in the field.
Artificial intelligence investments reduce risks to critical mineral supply
This paper employs insights from earth science on the financial risk of project developments to present an economic theory of critical minerals. Our theory posits that back-ended critical mineral projects that have unaddressed technical and non-technical barriers, such as those involving lithium and cobalt, exhibit an additional risk for investors which we term the “back-ended risk premium”. We show that the back-ended risk premium increases the cost of capital and, therefore, has the potential to reduce investment in the sector. We posit that the back-ended risk premium may also reduce the gains in productivity expected from artificial intelligence (AI) technologies in the mining sector. Progress in AI may, however, lessen the back-ended risk premium itself by shortening the duration of mining projects and the required rate of investment by reducing the associated risk. We conclude that the best way to reduce the costs associated with energy transition is for governments to invest heavily in AI mining technologies and research.
Komatsu and ABB collaborate through open electrification platform
Komatsu and ABB have signed a Strategic Collaboration Agreement to jointly develop and bring to market integrated solutions that will help move net zero emissions for heavy industrial machinery a step closer to reality. The two global leaders will leverage industry expertise and equipment in a bid to create world-class interoperability, ranging from renewable energy generation to fully electrified mining equipment for customers, through an open platform.
The global mining industry remains responsible for up to seven percent of global greenhouse gas emissions, according to strategy and management consultancy McKinsey & Co.1, with a large volume attributed to diesel-driven vehicle movements in open-pit and underground mines. It’s widely recognized that decarbonization of mobile mining equipment is needed to help mine operators achieve their greenhouse gas reduction targets. ABB and Komatsu’s collaboration is geared towards reducing diesel consumption and ultimately eliminating it through the electrification of mine operations.
Time series prediction model using LSTM-Transformer neural network for mine water inflow
Mine flooding accidents have occurred frequently in recent years, and the predicting of mine water inflow is one of the most crucial flood warning indicators. Further, the mine water inflow is characterized by non-linearity and instability, making it difficult to predict. Accordingly, we propose a time series prediction model based on the fusion of the Transformer algorithm, which relies on self-attention, and the LSTM algorithm, which captures long-term dependencies. In this paper, Baotailong mine water inflow in Heilongjiang Province is used as sample data, and the sample data is divided into different ratios of the training set and test set in order to obtain optimal prediction results. In this study, we demonstrate that the LSTM-Transformer model exhibits the highest training accuracy when the ratio is 7:3. To improve the efficiency of search, the combination of random search and Bayesian optimization is used to determine the network model parameters and regularization parameters. Finally, in order to verify the accuracy of the LSTM-Transformer model, the LSTM-Transformer model is compared with LSTM, CNN, Transformer and CNN–LSTM models. The results prove that LSTM-Transformer has the highest prediction accuracy, and all the indicators of its model are well improved.
The Silicon Valley Startup Using AI to Scour the Earth for Copper and Lithium
KoBold is betting it can modernize the mining industry by using artificial intelligence to scour the earth for copper, lithium, nickel and cobalt. It says machine-learning techniques allow it to collect and analyze more sophisticated data about deposits than conventional exploration methods.
To realize their vision they hired scores of tech-savvy workers from the likes of Apple and Google with little experience in mining. More than half of KoBold’s employees are data scientists or software engineers. Geoscientists and data scientists work in pairs on KoBold’s projects, in contrast to most traditional mining companies, where geoscientists typically outnumber their data brethren.
KoBold creates computer simulations of underground mineral deposits using borehole drilling, laser guns, satellite imagery and electromagnetic detection, among other techniques. Its algorithms then determine the best way to drill to test the validity of its models, helping narrow down which models are most accurate.
Introducing HORIZON: Pioneering Critical Metals Exploration with Deep Learning and Databricks
Durendal Resources has developed HORIZON, an advanced Deep Neural Network designed for mineral exploration. Named the High-Resolution Ore Investigation Network, HORIZON can accurately classify mineral occurrences without relying on surface geochemical or direct detection methods, making it a valuable tool for exploring areas with cover. Utilizing deep learning, HORIZON analyzes extensive geological and exploration data to reveal hidden patterns Deng et al. (2021).
HORIZON represents the first step in a revolutionary suite of models designed to transform mineral exploration worldwide. While significant progress has been made, further development is needed to create models that can make highly accurate predictions with minimal geoscience data. This ongoing work promises to enhance the efficiency and effectiveness of mineral exploration, uncovering hidden resources and driving the industry forward.
Durendal Resources Unveils TerraDX: Revolutionizing the Discovery of Critical Metals with Cutting-Edge Technology
Durendal Resources, is thrilled to announce the launch of TerraDX, the ground-breaking integrated operating system poised to transform the search for critical metals vital to a sustainable future. TerraDX promises to streamline the mineral exploration process by making earth science data more accessible and actionable.
TerraDX stands out as a high-performance, web-based Geographic Information System (‘GIS’) platform, meticulously designed to democratize access to earth science data. By facilitating the seamless discovery, manipulation, and sharing of structured and unstructured data, TerraDX fosters a community-driven approach to mineral exploration. This innovative platform combines advanced data analysis tools and social features, enabling users to share insights, rate information, and collaboratively refine exploration strategies.
Rithmik Solutions Secures $2 Million in Funding to Revolutionize Mobile Mining Equipment Management
Rithmik Solutions, a leader in AI-powered analytics for mobile equipment optimization in the mining industry, is thrilled to announce the successful closure of a $2 million funding round. This investment was spearheaded by a syndicate of new and existing investors, demonstrating strong confidence in Rithmik’s innovative approach to reducing greenhouse gas emissions, enhancing equipment uptime and improving operational efficiency. Rithmik Solutions is poised to use this investment to accelerate its growth, further enhance its product offerings, and expand its reach to help mines around the world maximize the efficiency and lifespan of their mobile equipment.
Deep-sea mining: Norway approves controversial practice
The deep sea hosts potato-sized rocks called nodules and crusts which contain minerals such as lithium, scandium and cobalt, critical for clean technologies, including in batteries. Norway’s proposal will open up 280,000 sq km (108,000 sq miles) of its national waters for companies to apply to mine these sources - an area bigger than the size of the UK.
Although these minerals are available on land, they are concentrated in a few countries, increasing the risk to supply. For example, the Democratic Republic of Congo, which holds some of the largest reserves of cobalt, faces conflict in parts of the country.
Walter Sognnes, co-founder of Norwegian mining company Loke Minerals, which plans to apply for a licence recognised that more needs to be done to understand the deep ocean before mining begins. The Norwegian government will not immediately allow companies to start drilling. They will have to submit proposals, including environmental assessments, for a licence which will then be approved on a case-by-case basis by parliament.
How Rio has made the world’s biggest iron ore business into a machine
Rio Tinto’s Gudai-Darri mine is one of three new wave DSO mines in operation across WA’s Pilbara alongside BHP’s South Flank and Fortescue’s Eliwana, while FMG also recently opened its Iron Bridge magnetite mine. At 43Mtpa, Gudai-Darri is among the most advanced in the world. Its diggers and loaders are manned, but its Caterpillar trucks are fully automated, run out of an operations centre in Perth with code to direct their passage across the 5km by 3km Kara pit. Of its 430 haul trucks across 17 mines, 361 are automated. For the first time, Caterpillar has also delivered autonomous water carts. The company says the unmanned vehicles deliver productivity and safety benefits. It is looking to enhance automation and bring a tech focus into other areas of the site.
This robot (or row-bit if you’re Futurama’s Dr Zoidberg) is being trained to use a thermal sensor to test idlers along the 5-7km of conveyor belt taking iron ore from Gudai-Darri’s crusher to its stockpiles. There are around 3000 idlers (spinning bits of metal that propel the conveyor along) for every km of belt. From early next year Rio’s engineers hope to have the robot automated, perpetually running a process manual assessors only complete in full every 12 weeks. By catching symptoms of failing idlers early, the company hopes to reduce the 60 hours of downtime each eight months from unplanned maintenance shutdowns at the fixed plant attributed to idler failure.
Notorious DLE: The lithium extraction technologies gunning for the crown
Instead of concentrating lithium by evaporating brine in large pools, DLE technologies aim to extract about 90% or more lithium through different methods, the most common of these being sorption (also known as adsorption), ion exchange, and solvent extraction. But investors still have a lot to learn when it comes to DLE, with the term commonly used to capture technologies that are still in the R&D phase.
“The lithium market is still really small, we’re up to 1 million tonnes of global lithium production, and it takes longer to build these projects than it does a hard rock mine. But a lot more are being built so there will be an exponential rise in the production from these projects in years to come.”
Optimizing Mineral Processing Plant Performance
Some commonly used methods in mineral processing are X-ray fluorescence, which is a well-established industry standard and is sometimes used for online analysis and process control in mineral processing plants.
However, X-ray fluorescence has its limitations as it is not well-suited to the measurement of light elements in complex mixtures such as slurries. Some approaches for mineral processing that overcome some of the limitations of X-ray fluorescence is prompt gamma neutron activation analysis (PGNAA) and pulsed fast neutron thermal activation (PFTNA). PGNAA uses an isotope as its neutron source, whereas PFTNA uses an electrically generated neutron source.
PGNAA is ideal for cross-belt analysis in mineral processing plants as no sample preparation is required for analysis of the material, and the technique can be multiplex, so multiple conveyors can be analyzed simultaneously.
⛏️ International investors pile into BHP-backed mining tech start-up, Plotlogic
BHP-backed mining tech start-up Plotlogic has banked a $US28 ($43 million) series B funding round, co-led by Galvanise Climate Solutions, a US-based investment firm founded by former Democratic presidential candidate Tom Steyer and SE Ventures, the venture arm of French energy and automation giant Schneider Electric.
Founded in 2018 by ex-mining executive Andrew Job while doing his PhD at the University of Queensland, Plotlogic uses advanced sensors and artificial intelligence to determine the quality of minerals and metals. Mr Job said Plotlogic’s revenue had increased 10-fold over the past 10 months and the technology was being used by the likes of BHP, Brazilian miner Vale, South32 and leading lithium company Pilbara Minerals to help increase output and reduce waste.
Plotlogic’s OreSense technology combines LIDAR (laser-based light detection and ranging, hyper-spectral imaging) and machine-learning algorithms to deliver a more accurate view of an orebody.
Innovating Metallurgical Equipment Design to Meet Flotation Plant Layout Challenges
One of the key design principles that holds true is that minimizing the equipment’s hydraulic head requirements can potentially minimize the number of pumps needed in a plant. This not only reduces energy demand, but also lowers operational and maintenance costs. Additionally, by minimizing the head requirement, one can free up space for additional process functions needed in the plant.
An example of this principle in action is the design of large flow rate sampling equipment. Traditional sampling systems for flow rates of 35,000 cubic meters or more often require splitting the final tails into two samples, which results in complex reconciliation and recombination processes. However, samplers that can operate at flow rates of up to 40,000 cubic meters an hour and incorporate all sampling stages at one floor level not only simplifies the process, but also saves height in the tails of the plant, reducing the overall cost of construction.
🚃 Missouri start-up gets $200,000 grant to accelerate US autonomous railcar technology
Intramotev, a Missouri based technology startup working on developing autonomous, zero-emission rail solutions, has been awarded a $200,000 grant from Michigan’s Office of Future Mobility and Electrification to support the deployment of three of its TugVolt self-propelled railcars at a mining site in the Upper Peninsula of Michigan in late 2023.
The civic investment will catalyze the first deployment anywhere in the world of self-propelled, battery-electric railcars for commercial use in a freight rail operation, Intramotev said, adding that it will also begin to fulfill the company’s goal that initial applications of its technology will include captive routes between mines and processing facilities, as well as intra-plant and ports.
This AI Hunts for Hidden Hoards of Battery Metals
The mining industry’s rate of successful exploration—meaning the number of big deposit discoveries found per dollar invested—has been declining for decades. At KoBold, we sometimes talk about “Eroom’s law of mining.” As its reversed name suggests, it’s like the opposite of Moore’s law. In accordance with Eroom’s law of mining, the number of ore deposits discovered per dollar of capital invested has decreased by a factor of 8 over the last 30 years. (The original Eroom’s law refers to a similar trend in the cost of new pharmaceutical discoveries.)
Our exploration program in northern Quebec provides a good case study. We began by using machine learning to predict where we were most likely to find nickel in concentrations significant enough to be worth mining. We train our models using any available data on a region’s underlying physics and geology, and supplement the results with expert insights from our geologists. In Quebec, the models pointed us to land less than 20 km from currently operating mines.
Over the course of the summer in Quebec, we drilled 10 exploration holes, each more than a kilometer away from the last. Each drilling location was determined by combining the results from our predictive models with the expert judgment of our geologists. In each instance, the collected data indicated we’d find conductive bodies in the right geologic setting—possible minable ore deposits, in other words—below the surface. Ultimately, we hit nickel-sulfide mineralization in 8 of the 10 drill holes, which equates to easily 10 times better than the industry average for similarly isolated drill holes.
Improving Conveyor Belt Safety For Mining Worksites
In 2020 alone, the Mine Safety and Health Administration (MSHA) reported 29 fatalities in the mining industry in the United States. Additionally, the MSHA reports that the rate of non-fatal injuries in mining was 2.9 per 100 full-time workers in 2020–indicating the importance of ensuring proper safety measures are in place to prevent accidents and injuries in mining operations.
While essential to many large-scale mining operations, conveyor belts are involved in many mining site safety incidents. Conveyor belt accidents often highlight a lack of training, an absence of proper PPE, or a failure to implement the right safety measure to protect the employees who operate, maintain, or work alongside of these belts.
Lockout Tagout (LOTO) is a safety procedure used to protect workers from hazardous energy machinery and equipment, such as conveyor belts. Wireless emergency stops are a valuable safety feature that can make bulk material handling on conveyor belts in mining safer. These stops allow workers to shut down the conveyor belt quickly and safely from a distance if an emergency arises. Unlike traditional emergency stops that require physical contact with the machinery, wireless emergency stops can be activated remotely, providing an additional layer of safety if something unexpected occurs.
⛏️ Inside Albemarle’s Kings Mountain North Carolina lithium mine
Albemarle Corporation, which supplies lithium to Tesla and other automakers and operates the only active lithium mine in the US at the Silver Peak mine in Nevada, owns the ~1,100-acre site that includes the former mine in Kings Mountain, along with a lithium hydroxide plant and R&D facility. The Charlotte-based specialty chemicals company doubled its lithium conversion capacity in 2022, and over the next few years it plans to build a facility capable of processing 100,000 tonnes of lithium and other battery materials somewhere in the Southeast.
But even with skyrocketing demand from the influential US auto industry, federal support, and a site that previously provided lithium for decades, Albemarle could still be five to 10 years away from production in North Carolina—and that’s if things go smoothly for the company
Caterpillar Announces Collaboration with Luck Stone to Scale Autonomous Solutions to the Aggregates Industry
Caterpillar Inc. (NYSE: CAT) announced a collaboration with Luck Stone, the nation’s largest family-owned and operated producer of crushed stone, sand and gravel, to deploy Caterpillar’s autonomous solution to Luck Stone’s Bull Run Plant in Chantilly, Virginia. This will be Caterpillar’s first autonomous deployment in the aggregates industry and will expand the company’s autonomous truck fleet to include the 100-ton-class (90-tonne-class) Cat® 777.
Looking to accelerate autonomous solutions beyond mining, Caterpillar will implement its existing Cat® MineStar™ Command for Hauling system at the Bull Run quarry, on a fleet of 777G trucks. This will allow Caterpillar to gain greater insights on quarry operations in order to tailor the next generation of autonomous solutions specific to quarry and aggregate applications. This project supports the acceleration of autonomous technology for operations with fewer mobile assets to allow a step change in safety and productivity, as currently experienced at large mining operations.
Achieving the Next Level with New Industry Standard Drilling Rig
Unlike most conventional rigs, this Flex3 walking rig is a side saddle configuration to reduce flat time during common rig activities such as drilling, pad to pad rig moves and well to well rig walks. It was thoughtfully designed with environmental stewardship and safety in mind.
A hookload of 1,000,000 pounds, a 720,000-pound setback capacity, and the capacity to set almost 24,000ft of 5 ½-inch drillpipe in the racking board, equips the rig for highly complex lateral wells. Its walking capability offers the flexibility of 500ft in a straight line, or multiple rows within a 200 x 50 ft box. A patented H&P BoomBox removes the need to break electrical connections during walks, allowing the rig to stay energized continuously. Complex connections are reduced and rig-up time is minimized through the substructure-mounted choke manifold, mud gas separator, trip tanks and pump back tank.
The condensed box-on-box substructure of the Flex3 reduces the number of rig move loads, allowing for an efficient rig down and rig up. No cranes are needed to move the rig’s backyard skids, including the engines, mud pumps and mud tanks. Furthermore, the mast, raised and lowered hydraulically, contains an integrated block and top drive that does not need to be removed.
How mining companies reach the operational excellence gold standard
While the ten largest companies in the manufacturing and business services industries have seen their productivity index grow by around 15 percent and 25 percent respectively over the past 25 years, the ten largest companies in the mining industry have seen only marginal growth of around 1 percent over the same period.
The mining industry also has several unique features that may help explain why a culture of operational excellence has not yet been widely adopted. Productivity in the sector is often constrained by physical factors, such as ore quality. The industry also has a heavy focus on technical elements and capital levers rather than organizational culture and processes, while its dispersed and fragmented nature creates barriers to sharing best practices.
Miners Are Relying More on Robots. Now They Need Workers to Operate Them.
In this remote corner of western Australia, surrounded by clusters of low-lying scrub and red rocky outcrop, the world’s second-biggest mining company has built its most technologically advanced mine. For Rio Tinto, PLC finding the workers to run the new high-tech operation is a challenge.
Automation helped miners to become more efficient and avoid disruptions triggered by the pandemic, when sudden border closures marooned workers who used to jet in from afar for their shifts. But the companies’ investments are doing little to solve a broader labor crisis affecting an industry that still needs a large staff to keep their operations running smoothly.
Moving mining forward: Reducing downtime during mill relining
A new perspective on the mining industry
Certain geologies and structures ultimately have different vulnerabilities. Entering known data into a simulated environment or kind of digital twin, can help figure out the unknowns, assisting miners to decide where and how to apply their efforts. This is essential for remotely managed or autonomous vehicles that can achieve low waste, and efficient extractions in harsh or dangerous locations. Autonomous vehicles can actually extend operation hours, increasing productivity as well as reducing the use of energy hungry and personnel centred equipment. In an IoT network these may increasingly incorporate ‘intelligent’ or ‘smart’ devices that not only store or transmit but process data – as in a ‘smart factory’. “We’re seeing opportunities with sustainability oriented projects in Canada and Europe,” Sym-Smith says.
Minexx’s software platform uses blockchain digital distributed ledger, payments, biometric and IoT technologies to create much-needed trust and transparency around quality and methods of production. This helps clients manage aspects of know your customer (KYC) and anti-money laundering regulations as well, giving them and the artisanal miners access to markets and better prices. “Once data is on the blockchain, you can’t change it. Then essentially you give the manufacturer the key,” Scaramanga says.
KoBold Metals Raises $192.5 Million to Use AI to Find Battery Minerals
KoBold aims to change the mind-set of an industry that has long relied heavily on sampling soil and sediment and drilling holes in the ground to determine whether areas contain valuable minerals. While the company still leans on those techniques, it hopes to limit the chances of failure by drawing on machine learning and other scientific computing techniques.
In September [2021], KoBold formed an exploration alliance with BHP, the world’s largest mining company by market value. It is one of a number of partnerships it has with resources companies world-wide.
Accelerating mining safety and smart mines with limitless connectivity
Digitalization can have a tremendous impact on safety, giving mine operators a clearer picture of the full breadth of operations, monitoring critical factors like air quality and tunnel strength. An optimized mine, especially one with the latest in 5G-enabled private networks, can give miners those crucial seconds that can save lives.
As private wireless networks, including the latest generation in 5G, help revolutionize mission critical industries across the country, mining stands out as a place where connectivity can foster major improvements, from safety to efficiency and productivity to better sustainability. Mine operations can be optimized by collecting and analyzing tracking data on the precise location and performance of vehicles, equipment and personnel.
An App for Bulk Material Handling and Analysis in Cement Manufacturing
Cement analyzers provide real-time online elemental analysis of an entire raw material process stream using technologies like Prompt Gamma Neutron Activation Analysis (PGNAA) and Pulsed Fast Thermal Neutron Activation (PFTNA) technology. These analyzers can aid in consistent stockpile quality, reduced chemistry variability, decreased kiln upsets and kiln fuel costs, extended quarry life, and minimized use of highest cost materials.
Reducing Energy Costs by 8% by Optimizing Autogenous Mills
The grinding process alone accounts for 80% of the energy consumption. It consists of pulverizing limestone blocks to obtain the calcium carbonate used as a mineral filler in paper pulp.
Mills are the plant’s main equipment:
- 5 x 355 kW autogenous mills operating without prior crushing;
- 20 electric mills of various powers between 250 and 355 kW.
The case presented concerns only the autogenous mills, which are the most energy-consuming.
Mining 4.0 with SampleManager LIMS
The mining industry presents unique and complex challenges when it comes to data management. Responding to international regulations, integrating technologies used in different business units, controlling accurate inventory data and reliably managing mineral information are critical needs.
Companies in the mining industry need to efficiently manage all the variables that come into play, especially considering that it is a long production chain made up of diverse units that are physically separated from each other. Integrating the laboratory data with the rest of the production chain is key to improving operations and unlocking growth.
Why resources companies are looking to evented APIs
Resources companies that want to get the most value from their data will process it the instant that it is created. The longer that data is left unprocessed, the more it diminishes in value. Operational excellence can be driven by evented APIs that can produce, detect, consume, and react to events occurring within the technology ecosystem.
Evented APIs can be applied to our example use case to deliver an autonomous feedback loop that incorporates smarter decision making in real-time.
Using AI to Find Essential Battery Materials
KoBold’s AI-driven approach begins with its data platform, which stores all available forms of information about a particular area, including soil samples, satellite-based hyperspectral imaging, and century-old handwritten drilling reports. The company then applies machine learning methods to make predictions about the location of compositional anomalies—that is, unusually high concentrations of ore bodies in the Earth’s subsurface.
How did one of the world's largest robots end up here?
The autonomous train, consisting of three locomotives and carrying around 28,000 tonnes of iron ore, travelled over 280 kilometres from our mining operations in Tom Price to the port of Cape Lambert. It was monitored remotely by operators from our Operations Centre in Perth more than 1,500 kilometres away. Our AutoHaul™ team at the Operations Centre in Perth continued to hone the technology, running thousands of hours of tests. The AutoHaul™ project was made fully operational in June 2019, making it the world’s first fully autonomous, long distance, heavy-haul rail network.
“The time-saving benefit is enormous because the train network is a core part of the mining operation. If we can prevent those stoppages, we can keep the network ticking over, allowing more ore to be transported to the ports and shipped off more efficiently,” says Lido. “The other major benefit is safety,” he continues. “We are removing the need to transport drivers 1.5 million kilometres each year to and from trains as they change their shift. This high-risk activity is something that driverless trains will largely reduce.”