Tag Archives: Big data in mining

AI helping underground mines

AI Myths in Mining

AI in Mining: Myths and Facts

AI helping underground mines

Can Artificial Intelligence be applied in the underground mining sector? Or is it a myth?

Maybe because it’s so new, and for so long has been in the realm of science-fiction, but Artificial Intelligence is surrounded by a number of myths. So too is Machine Learning, AI’s little sibling.  

But it shouldn’t be the realm of myth. AI may seem intimidating, but it won’t take over your mine. In the contrary, efficiency is what AI and ML target so that operations are optimized.

To help bust some of those myths, we’ve put together a guide to address some of what you may have heard about Artificial Intelligence and Machine Learning, and where reality truly exists. 

Myth: Machine Learning and Artificial Intelligence require huge investments only big corporations can make.

Fact: In underground hard rock mines, it’s easy to pick up quick wins on small projects. AI can do things as simple as sifting through the maintenance data you already have to help predict when haulage trucks will break down. 

Myth: AI and ML will replace all the people in your operation with algorithms

Fact: The technology doesn’t replace people at all. What it does is enhance workers’ ability to do their jobs with better information. Read our blog about ML algorithms do just that! 

AI improving Underground Hard Rock Mining operations

Myth: Working with AI is like working with a sentient person.

Fact: AI and ML algorithms are far, far away from human-like consciousness. There are ways in which algorithms are able to mimic some particular, narrow functions of the human brain. For example, they can play and learn to excel at games like chess or GO. But an algorithm designed for chess is never going to be able to have a conversation with you, and a conversational robot isn’t going to play chess. AI-driven technologies are designed to perform specialized tasks. And even if they can sound human, and can learn certain human thinking patterns, they aren’t nearly at the stage of full blown sentience.  

Myth: Machine Learning can work with any quality of data without problems.

Fact: While ML algorithms can work well with data that includes a lot of noise, there is a limit. If data is of poor quality, no matter how sophisticated the algorithm, it can’t be used. You can have mountains of data that is missing key information. Consider a mountain of data from a fleet of trucks, but the data is missing a timestamp—so the algorithm doesn’t know what day or time the data is from. Or maybe the data doesn’t identify what sensor it’s from—is it transmission temperature, or tire pressure? Automatically collected data by machines also tends to be more reliable than data manually entered by humans, particularly if it’s been over a long period. 

Myth: Artificial Intelligence and Machine Learning are dangerous.

Fact: Like any other piece of technology, AI is fallible. When using AI—or any technology—you should do so with a healthy skepticism. It’s important to counter-verify anything output from an AI or ML system. Like with any other new technology, you should make sure there is a person in the loop of the system. Not only will you prevent errors, but you will enhance that person’s ability to do their job. It has the added benefit of removing the repetitive, perhaps boring, tasks from many jobs, leaving the more interesting, in-depth analytical tasks for the user. 

Myth: Machine Learning is perfectly objective.

Fact: There are many ways bias can find its way into Machine Learning. Classic ML techniques rely on the engineering that created them. And the biases of the people that built those algorithms can shape and bias the system’s output. On the Deep Learning side of ML, data is given to the algorithm in the rawest possible form. In that case, the system can only be as objective as the data it is given. Any information given to an ML system by a person is subject to the biases of that person. The algorithms learn from what they are given. 

CIM addressed the power and pitfalls of predictive algorithms applied to mining last year through this article – an interesting read for more perspective.

Artificial Intelligence and Machine Learning Help Underground Mines Improve

Artificial Intelligence is the Next Frontier of Improving Underground Mining Operations

Artificial Intelligence is the Next Frontier of Improving Underground Mining Operations

Artificial Intelligence and Machine Learning Help Underground Mines Improve

What is Artificial Intelligence to Mining?

Artificial intelligence IS the next frontier of improving underground mining operations. But, we’re not talking about turning your mine into a hive of drones. This isn’t about upending your operations. Machine learning (ML) algorithms pull out patterns in data collected around your mine and fleet to predict problems before they occur. This vastly improves the efficiency of your mine.

"What machine learning algorithms do is pull out patterns in data collected... to help predict problems before they occur..."

At Agnico Eagle’s Goldex Mine near Val d’Or, Que., they’re saving on maintenance costs for the engines of their haulage trucks. This is thanks to the predictive analysis made using their historical data collected by Newtrax and applied to ML algorithms.

The maintenance team at Goldex discovered that their truck engines were sometimes failing, a lot earlier than expected. The team had suspicions on what was causing the problem and were alerted by the Newtrax Mobile Equipment Telemetry (MET) system. This provided them with a good indication. However, by using ML, we were able to sift through the data collected from the truck’s engine sensors far more quickly. We were able to pick out the patterns of what was happening with confidence resulting in faster time to action.

“[Newtrax] developed a system that enables us to predict issues at least two weeks in advance, even before the alarms, so we can intervene before we incur problems that break our engines,” Agnico's Daniel Pinard says.

Rather than spending $100,000 to replace an engine, they only had to spend about a quarter of that to make the necessary repairs. And at the same time were able to leave the truck in production, where it moves about 500 tonnes of material a shift.

This is what AI is all about. Finding small, manageable solutions that save costs and optimize processes.. Newtrax combined its in-house advanced ML expertise with the client’s data to achieve quick wins.

Read our previous article on how AI also improves Safety, Productivity and Profitability.

Machine Learning Intern explains ML algorithm in meeting on whiteboard for Underground mining

Newtrax AI Intern Léo Boisvert explains an algorithm to team members.

"It's not just engine failures that machine learning algorithms can predict in advance, it can see failure in smaller components, too."

It’s not just engine failures that machine learning algorithms can predict in advance! ML can see failure patterns in smaller components, too. Take batteries, as an example. Typically during normal usage, a battery puts out a precise voltage that holds steady for its entire life. But as a battery ages, and approaches failure, subtle variations start to appear.

Newtrax engineer Louis-Pierre Campeau saw the algorithm was picking up a change in the output. When he looked at it, and said, “Well, it’s 26.7 Volts, and it was 26.7 before so it’s okay.” But the algorithm was saying there was a problem.

“Then looking deeper, the average was 26.752, and afterward it was 26.716,” Campeau says. “It’s a very small change you just couldn’t pick up by looking at it.”

"This is the REAL power of machine learning. A single person isn't able to look at all the data... but an algorithm can..."

This is what he says is the real power of machine learning. A single person isn’t able to look at all the data for the different measurements given off by a fleet of vehicles. But an algorithm can, and it’s able to draw connections of things a person isn’t likely to even see as related.

“Sometimes there are too many factors put together that you can’t really look at as a whole,” Campeau says. “If one measure goes up while another goes down, at this average and the temperature is going down. There’s a certain limit of information you can process out simultaneously.”

"Newtrax has a large collection of anonymized data..."

What Newtrax brings is a focus on underground mining. You won’t be a client with a company that’s adapting their algorithms for the train yard to fit the underground environment. Newtrax has a large collection of anonymized data from our client base of underground mining companies. We’re able to draw on right from the start, Campeau says.

“Each mine is part of the large pool of clients we have, and can use all of these insights we get from our previous experience to apply it right away,” he says. “Rather than having to figure out everything from scratch.”

"You may not have seen your LHD's in every possible situation, but there's a good chance we have, and can pull patterns from it right when we start."

We’re able to draw on a large database collected from a number of different mines, that gives us a huge wealth of real-world data to train our algorithms. You may not have seen your LHD’s in every possible situation, but there’s a good chance we have, and can pull patterns from it right when we start.

We recommend reading ‘Live to learn – The Future of Mining Innovation’ by Mining Magazine to further explore the value of AI and Machine Learning.

For more information on Newtrax successes at Goldex, you can read this case study:

Data collection mining

How Data Collection and AI Will Change The Future of Mine Safety and Profitability

How Data Collection and AI Will Change The Future of Mine Safety and Profitability

Data collection mining

1.  Safety in Mines

Data collection and analysis, especially with the availability of AI algorithms, makes it easier to foresee possible risks that can arise in underground mines, and prevent them.  Predictive maintenance would be the best example of this. According to the Occupational Safety and Health Administration, companies with a 9% reactive maintenance rate had a recordable incident rate of .1%, while those with a 64% reactive maintenance had a recordable incident rate of 4.3%.

These statistics highlight how having reliable equipment is safer.  Interpreting real-time data on your equipment and how they interact in the mining environment keeps everyone safer in the mine.  These algorithms are preparing today for the future needs of safety compliance in safety and prevention.

2.   Mining Productivity and Profitability

Productivity in mines is lower than in other industries, and working underground creates a gap of knowledge transfer between supervisors of different areas of the mine in real-time.  Decisions are made while there are still variables which are unknown. Data collection and analysis however, makes it possible to have a global view of situations for better decision making. There are serious cost savings when you can make important decisions with a full and clear picture in mind.

— Download the Slide Deck to Learn How Use AI on Mining Data To Create Value In Less Than 3 Months —

Download the AI Slide Deck To Learn More

This AI Slide Deck prepared by Newtrax VP of Artificial Intelligence, Michel Dubois, shows how to create value with data collected in underground mines using Artificial Intelligence algorithms.

3. Data collection for Mining

Mines have started digitalizing their fleets and collecting data.  This is where data contextualization comes in. Through the fleet and network agnostic systems at Newtrax for example, the data collected can be connected and contextualized.  Being able to have the full context of any piece of data will bring more possibilities and using trends and algorithms trained by multiple mines can help predict events in any given mine.

Mining will be much more calculated in the next 5 – 10 years, this means knowing exactly what is going on under the surface from to make the mine safer, more profitable and understanding how all of these elements interact with each other to have the most productive operation possible.

Mine Evacuation Best Practices

Best Practices for a Safe Underground Evacuation

Best Practices for a Safe Underground Evacuation

Mine Evacuation Best Practices
Photo Credit: https://www.workplacesafetynorth.ca/news/news-post/mining-safety-report-new-heat-stress-standard-released-ontario

One of the biggest challenges underground mining operations face is visibility of events happening underground from the surface. When monitoring an evacuation situation, this limitation is even more pronounced when ensuring miner safety during an emergency.

Newtrax recently spoke to Michael Place, Unit Manager at Gold Fields’ Granny Smith mine, about the best practices to follow during emergency evacuations. Michael has spearheaded the implementation of the Newtrax Evacuation Notification system at Granny Smith and will be speaking about the benefits of this digital system at the upcoming IMARC 2018 conference in Melbourne.

***

Newtrax: What types of dangers are miners exposed to underground that  could trigger an emergency evacuation?

Michael Place: When it comes to dangers facing miners underground, the most terrifying would be fire. Operating diesel powered equipment in a confined space can deplete oxygen when fire and smoke break out. Some other triggers of an emergency include, but are not limited to, seismicity (underground earthquake), fall of ground, unintentional initiation of explosives, any personnel medical emergency, gas intersection, water inrush, vehicle vs vehicle collision and so on.

 

Newtrax: What are the first 3 things personnel working underground should do when an emergency has been announced?

Michael Place:

  1. Park up equipment off main travel ways
  2. Make their way to the nearest refuge chamber
  3. Maintain radio silence to allow the airways to be clear for communication to the incident scene

 

Newtrax: What are the most important things to think about during an emergency underground?

Michael Place: Accounting for all personnel and if there is an injured person, getting them to the surface as quickly and as safely as possible.

 

Newtrax: How are emergencies in underground mines different from any other emergency alarm?

Michael Place: The sheer size of an UG mine adds a layer of complexity to an emergency. Accounting for personnel and communicating from above ground to underground are some of the hardest things to manage. Generally, the assistance required in an emergency comes from above ground through the form of a medical professional or the emergency response team (ERT).

 

Newtrax: How does technology enable emergency evacuation to be safer?

Michael Place: Accounting for personnel underground without the use of the radio allows the radio to remain clear for communication to the incident scene. Allowing real time tracking of personnel gives the incident controller data like never before to focus on the incident at hand.

 

Newtrax: What kind of advice would you give to other underground mines about best practices regarding safer emergency evacuations?

Michael Place: When it comes to enhancing safety UG during emergency evacuations, the most important aspect is getting all personnel out from UG or to a safe location in a safe manner, as quickly as possible.

Best practice now combines multiple technologies including stench gas, voice over alarm and the Newtrax Evacuation system to ensure communicating to all personnel that an emergency in in place is done as fast a possible. Investing in technology to enhance safety in UG mines ensures everyone goes home safely every day.

Learn how Big Data, IoT, and Predictive Maintenance can help you?

Contact a Newtrax Expert to answer all your questions on how our custom solutions can integrate seamlessly with your underground mining operation.

Underground Mine is the Future

Will underground mining replace surface mining in the future?

Will underground mining replace surface mining in the future?

Underground Mine is the Future

A wave of influential factors – including economic, political, environmental and technological advances – strongly suggest that underground mining will be the miner’s method of necessity in the not-so-distant future.

Mineral explorers and project developers are increasingly unable to find economically viable deposits with a proven plan for open-pit mining operations. Many companies currently operating surface mines will be looking towards brownfield underground operations to expand operations and extend mine life.

This, however, is not the entire foundation for the future of underground mining.

Emerging economies across the globe are growing their middle-class populations in bustling urban centers, putting ever-increasing demands on mining operations to produce the raw materials that make modern society possible, from infrastructure to consumer goods.

However, while consumers want a new car, a television and even renewable energy infrastructure, they tend to no longer accept the environmental and social costs that surface mining has on their communities. Policymakers and neighbors of mining operations vocally reject the visual impact of an open-pit, a waste dump and the destruction of habitat it brings during construction and operations.

“They are unwilling to accept the loss of farmland, the possible impacts on ground and surface water, loss of recreational space or the noise and traffic issues stemming from truck traffic associated with surface mining,” according to the research. “Underground Mining for Meeting Environmental Concerns – A Strategic Approach for Sustainable Mining in Future.”

The pioneering work of Newtrax is eliminating the current digital divide between surface mines and underground mines to make operations safer, environmentally sustainable and more profitable.

Big Data is helping to reach ore deposits more economically

Artificial Intelligence and Machine Learning are helping miners reach underground ore deposits more economically.  Digital twinning, first created by NASA, allows geologists and engineers to develop predictive work models using real-time data from the field to test out production scenarios before they are implemented, leading to productivity and environmental improvements.

Real-time data improving productivity

Rio Tinto generates 2.4 terabytes of data every minute from mobile equipment and sensors at its  16 mines, 1,500km of rail, three ports around the globe. Data-driven precision mining powered by machine learning will make the mining industry more profitable.  The data helps miners know how much of the ore has been extracted and which direction it has traveled – key performance indicators vital to driving improvements in the mine. This can be especially helpful in block caving, an efficient underground mining method that uses gravity to force ore to strategic draw points below. Other miners are reducing fuel and energy costs by using smart machines to sort mined material based on set criteria defined by real-time analytics.

IoT technology is making underground mining safer

Working deep within an underground mine is dark, wet and inherently hazardous. Having initially adopted a ‘fast follower’ approach to IoT technology, the notoriously risk-averse sector is finally waking up to the fact that data is now, arguably, its most precious commodity, with 40% of mining businesses now expecting to leverage the technology within the next 12 months.

IoT has the potential to improve safety, automate machinery operation, facilitate predictive rather than preventative maintenance, improve traceability and harness real-time data and analytics.

Equipment performance and maintenance

Unplanned downtime is very costly to mining operations. Mobile equipment sensors give miners real-time health checks of their equipment, including temperature, speed, and vibration. This allows operators to predict when to schedule planned maintenance. In underground room and pillar settings, this can keep an operation in continuous production, avoiding costly shutdowns.

The ability to access this data empowers mining companies to understand the precise manner in which their machines are being used, how well each individual machine is functioning, and can offer predictive suggestions to increase both productivity and profit.

The data mining of today is literally setting the groundwork for the next-generation underground mine that will be powered by Artificial Intelligence (AI) and Machine Learning capable of producing incredibly productive operations that protect human life and the environment.

Learn how Big Data, IoT, and Predictive Maintenance can help you?

Contact a Newtrax Expert to answer all your questions on how our custom solutions can integrate seamlessly with your underground mining operation.

Using Technology to Increase Safety during Mine Evacuations

Using Technology to Increase Safety during Mine Evacuations

One of the biggest challenges underground mining operations deal with is visibility of events happening underground from the surface.  When monitoring an evacuation situation, this limitation is even more pronounced when ensuring miner safety during an emergency.

The team at Gold Fields’ Granny Smith mine recently decided to change this by using technology to increase safety.  Newtrax was engaged to provide an underground personnel tracking system using their enabled cap lamps.

Through the Newtrax enabled-cap lamp technology, the Granny Smith Mine was able to improve:

  1. Safety
  2. Performance
  3. Profitability
  1. Improved Safety

The technology incorporated into the Newtrax enabled cap lamps transform the lamp into more than just a Personal Safety Device, it is an integral part of a mine evacuation system. Where the limitations of communication through two-way radio make it difficult to be 100% sure of the miners’ safety during an emergency, the Newtrax Evacuation Notification system is able to position each team member underground in real-time.

All existing Cap Lamps at the Granny Smith Mine were replaced with the Brando Corded and Cordless Cap Lamps with Newtrax Safety Features and a High-brightness Light. This allowed Granny Smith to integrate with the Newtrax Evacuation system which sends an emergency message underground to every cap lamp. When activated from the surface, the lamp lights flash, notifying all employees that an emergency has been initiated. They set up their system to work in parallel with their stench gas system and their voice over alarm.

The Newtrax Evacuation system allows Supervisors and the Emergency Response Team (ERT) to quickly determine the location of all employees below the surface, improving safety.

  1. Improved Performance

Emergency drills are important, and they take time and resources to effect, ensuring that all personnel are accounted for while handling the incident. Mines rely heavily on two-way radio for communication, and in an emergency visibility can be lost when the understanding is only as good as the radio calls made to and recorded on the surface.  

The first ever Newtrax Evacuation test was conducted at Gold Fields’ Granny smith mine on July 31st, 2018 through an underground mock emergency exercise. This is the second time worldwide that the Newtrax Evacuation system was adopted in its full capacity, and the hardware functioned seamlessly.

These systems allow the Emergency Rescue Teams (ERT) to know exactly which miners are in which refugee chambers in the mine, and refocus their energy on those who have not yet made it to their chamber.

  1. Increased Profitability

The Newtrax Evacuation system allows for effective and accurate safety drills. Using Newtrax technology reduces the time and resources needed to effectively execute and complete the drill, leaving more time for production.

The result of setting up the Newtrax Evacuation system in the Granny Smith mine was evident: improved safety, performance and profitability during an evacuation drill. Due to the safety features that the Newtrax enabled cap lamps offer, additional features can be added on to the software as required. These include vehicle proximity detection and full mine employee tracking and positioning through an expanded Newtrax Minehop network.

Talk to an expert today on how to best implement the safety measures your mine requires today.

Improve Safety, Performance and increase Profitability.

Have a Newtrax expert contact you to learn how our Custom systems can integrate into your current infrastructure.

Future of mine safety

The Future of Mine Safety and Profitability through Data Collection

The Future of Mine Safety and Profitability through Data Collection

Future of mine safety

“I think that what we are doing right now at Newtrax is defining the future needs of the mining industry.” Louis-Pierre Campeau, an AI expert with Newtrax Technologies said while describing his role and its impact on mining.

Campeau was the subject of our recent blog on  “How Big Data is Solving Three of Mining’s biggest Challenges”.  Since his role and expertise will have such a huge impact on how the mining industry will conduct business in the future, we took some time to sit down with him and talk about his personal journey, and where he sees his work impacting the mining industry over the next 5-10 years.

  1. Future of Safety in Mines
  2. Future of Mining Productivity and Profitability
  3. Future of Data collection for mining

The Mining Industry is very niche, what inspired you to branch off into Mining Engineering?

“I always knew that I wanted to go into engineering, but I wanted to do something different and unexpected.” Said Louis-Pierre who took Mining Engineering with Polytechnique. He has found the mining industry to have become much more of a passion than expected.

The new reality will make it easier to foresee possible risks and prevent them...

1.  Safety in Mines

How will the algorithms you are developing impact safety for the underground mines of the future?

“The new reality will make it easier to foresee possible risks and prevent them.  Predictive maintenance would be the best example of this” explained Campeau. According to the Occupational Safety and Health Administration, companies with a 9% reactive maintenance rate had a recordable incident rate of .1%, while those with a 64% reactive maintenance had a recordable incident rate of 4.3%.

These statistics highlight how having reliable equipment is safer.  Interpreting real-time data on your equipment and how they interact in the mining environment keeps everyone safer in the mine.  These algorithms are preparing today for the future needs of safety compliance in safety and prevention.

2.   Mining Productivity and Profitability

How do you see the shift toward technology impacting the future of Underground Mining profitability?

Louis-Pierre explains how productivity in mines is lower than in other industries, that working underground creates a gap of knowledge transfer between supervisors of different areas of the mine in real-time.  “Decisions are made while there are still variables which are unknown. Solutions like what Newtrax offers makes it possible to have a global view of situations for better decision making.” There are serious cost savings when you can make important decisions with a full and clear picture in mind.

3. Data collection for Mining

Once mines are collecting data and digitizing their systems and fleets, what’s next?

Mines have started digitizing their fleets and collecting data.  This is where data contextualization comes in. Through the fleet and network agnostic systems at Newtrax, the data collected can be connected and contextualized.  Louis-Pierre explains “Being able to have the full context of any data will bring more possibilities. Using trends and algorithms trained by multiple mines to predict events in any given mine.”

Mining will be much more calculated in the next 5 – 10 years, this means knowing exactly what is going on under the surface from to make the mine safer, more profitable and understanding how all of these elements interact with each other to have the most productive operation possible.

Digitally transform your operation today!

Speak to an expert about how with Newtrax you can monitor data in real time, improving Safety, Productivity, and Maintenance.

How Big Data is Solving Three of Mining’s Biggest Challenges

How Big Data is solving three of mining’s biggest challenges

Blog_BigDataSolvingMiningChallenges

Advancements in Industrial IoT systems have made data collection in hard to reach places such as underground mines more accessible than ever before. Thousands of sensors can now automatically upload millions of data points, revealing potential insights that were previously unattainable.

The pioneering work that Newtrax is investing in to collect this data is on the forefront of the digital transformation that the mining industry is going through, helping mining companies around the world solve their three biggest challenges:

  1. Increasing Safety while optimizing productivity
  2. Reducing costs
  3. Reducing waste to increase sustainability

However, while invaluable, all of this data can quickly become overwhelming.

To sift through the data-noise, Business Intelligence (BI) analysts can interpret past data to understand the historical performance of a business, while Machine Learning (ML) algorithms can analyze the past data (trends or patterns) to make future predictions.

Louis-Pierre Campeau, Ph.D. candidate and expert in mining optimization joined Newtrax to help us do the latter.

“If you’re on the sidelines waiting for the right moment to enter the world of Big Data and Machine Learning, you could easily get left behind,” Campeau said. “The bigger the datasets you start building now, the better equipped your Machine Learning algorithms will be five years from now, giving early adopters an incredible competitive advantage.”

For a typical large-scale operation, the mine accounts for a third or more of total operational cost. Some mid- to late-stage mines can expect capital and operational costs to double in the next five years as they navigate geological, operational and regulatory challenges.

That’s why operators of Tier 1 assets are accelerating their investments in data collection and analysis capabilities to be better prepared for the wave of Artificial Intelligence and Machine Learning.

The Big Data collected underground through IoT systems will solve mining’s biggest challenges in the following ways:

 

1. Through the data collected from people working underground, Machine Learning algorithms will be able to clearly identify trends in dangerous and hazardous situations based on past behaviour and incidents. This will enable mine management and the Health & Safety departments to take preventive measures to significantly reduce the risk of accidents and fatalities underground.

2. The data collected from mobile equipment, such as tire pressure and engine performance, will enable the prediction of maintenance so precisely that time and cost associated to unplanned maintenance will be significantly reduced, or even practically eliminated. The better we can predict the previously unpredictable, the more productive the mine will be.

3. The environment, such as water, ground and gas levels, are also very powerful data points that can enable the mine to significantly reduce waste and mine with precision. By collecting, analyzing and interpreting historical data on the environment, underground mines can increase the safety of their workers and significantly reduce waste for a more sustainable mining operation.

_________________

Is it time to go Big Data?

Big Data is, well, really big. It can be overwhelming for companies to determine where to start. Newtrax is well-positioned to provide the services, the technology, and the coaching to guide mining companies on their Big Data journey. Our staff of engineers, technology experts, and data scientists are here to help you become the industry’s next data-driven underground mining operation.

Using Big Data will help your underground operation.

Get in contact with a Newtrax expert.  Learn more about how Big Data can increase safety, reduce costs and increase overall sustainability.