The Industrial Internet, and How It’s Revolutionizing Mining
The Industrial Internet and How It Is Revolutionizing Mining
“The Industrial Internet in Mining” is sponsored content from GE Digital
The Industrial Internet is the convergence of the global industrial sector with big data and the internet of things.
Big Data: New insight to make decisions in real-time is made possible by combining the ability to process and make sense of large amounts of data with a universally standard industrial platform.
Internet of Things: By 2020, 50 billion devices will be connected to the web. Many of these will be sensors, which can now be produced at a lower cost, creating new levels of network connectivity between machines and people.
The result of this convergence will be up to a $15 trillion increase in global GDP over the next 20 years stemming from smarter decisions, optimized performance, higher productivity, and substantial savings in fuel and energy.
How the Industrial Internet works
The Industrial Internet encompasses vast amounts of the complex physical machinery and processes that make our world work. It costs trillions of dollars each year to run these intensive systems. That’s why improving efficiency by just 1% can create millions in cost savings.
For example: the combined operating expenditures for the Top 40 miners in 2014 were $531 billion. 1% of that is $5.3 billion in potential savings.
Examples of the Industrial Internet in motion:
- Predictive analytics warn airline operators of potential engine failures before they occur, saving millions by avoiding downtime and flight delays
- Driverless haul trucks will soon be the new norm for miners around the world. These robots are more efficient, and are controlled remotely from hundreds of miles away.
- Drivers and engineers can get real-time reporting on a train as it is in transit. Analytics calculate engine temperature, fuel efficiency, speed, weight, and vibration patterns. The location is tracked to optimize the efficiency of the entire system.
- By consolidating all the mill asset and process information in a common platform, a mining production manager can see the whole picture. As a result, she knows where the team needs to focus to maximize throughput, recoveries, and quality.
When Hardware Meets Software
The revolution in data analytics and connectivity is changing how people work with heavy-duty machines around the globe, and mining is no exception.
Major mining companies have all started to incorporate big data into operations through the industrial cloud. This allows them to avoid unplanned downtime, to act in the best interest of shareholders by converting insights into outcomes, and to use the best available technology.
Using predictive analytics and process optimization, the industrial internet can save miners millions of dollars each year.
Here are just some examples of the minimum potential savings from a given asset per year using predictive analytics:
- Crusher: $119,000
- Pump: $62,000
- Mill: $312,000
- Haul truck: $62,000
Here are just some examples of the minimum potential savings gained per year by optimizing entire processes:
- Flotation: $1.6 million
- Grinding: $0.7 million
- Surge: $0.2 million
- 50 PID Loops: $1.5 million
The senior metallurgist of a platinum mining company had a problem: the milling circuits were processing more and more waste material together with ore from the main reefs, causing significant operational issues. Even though the different sources were blended, the characteristics of the ore being fed to the mill changed dramatically, often in the space of minutes. This led to extreme variability in the circuit.
The Challenge: The company believed that it was losing potential revenue as a result of sub-optimal throughput and efficiency in the milling circuits.
The Action: Implemented GE’s Mine Performance solution for process optimization on one of the milling circuits, to stabilize the circuit and optimize throughput.
- Increased average throughput by more than 5.5%
- Decreased power consumption per ton of material fed by almost 2%
- Decreased density variation of the cyclone feed
Embed This Image On Your Site (copy code below):