Advanced Analytics Paves the Way for Intelligent Mines & Mining
Mines and mining processes have some tough challenges, especially given the remote locations of many mines, the harsh and demanding nature of extracting the raw materials, and the complexity of the involved processes. Planta managers, process engineers, and operators in this industry definitely deal with their unique work headaches. It ain’t easy managing complex mining operations to ensure adequate safety and to optimize resources and processes. They also have to deal with decreased ore quality and an increased pressure to get more metals and minerals out of less ore. And let’s not forget the lack of access to water and energy and the exorbitant maintenance costs due to increased labor costs and reduced availability of spare parts. We should also mention troubleshooting mining processes which sure as heck ain’t easy.
Divisions and strategies of the biggest mining companies worldwide include at least one of the following targets in their agendas: smart/intelligent mining, automation, digitalization, big data, advanced analytics, and energy and emissions reduction. Addressing any one of these directly relates to the real day to day challenges plant managers and process experts face on the ground and at the mines.
Solving the Data Scientist Predicament
So how do you address your metals and mining process issues? Do you use Excel along with your Historian trend clients or do you plot the data and put up these graphs on a window to try to see what is going on? Maybe you might even be doing some analytics. Or is there a specialized group that is responsible for making sense out of the huge amount of process data?
Many companies use data scientists to do the heavy analytics lifting and to get more business insights into the mines and processes. These same companies also know that there just aren’t enough data scientists to go around, and there especially aren’t many data scientists with process knowledge. Which is really what is needed to efficiently solve process issues. So …… how to solve this data scientist predicament?
Simple – use advanced self-service analytics to empower your plant managers, process engineers, and operators with analytics, so they can leverage the sensor-capture data. They will then be able to analyze the data to do the daily troubleshooting on their own and monitor and predict the processes to make data-driven decisions. They will also be able to predict maintenance to save asset life and costs and achieve operational excellence.
Advanced self-service analytics also has capabilities that are especially useful for mines and mining processes which eliminate data silos through the contextualization and sharing of process data. These same capabilities allow for the setup of dashboards, so teams in any location around the world can have eyes on the processes. All of this leads to process transparency and effective team collaboration thus paving the way for intelligent mines and mining.
But to understand the more technical benefits of advanced self-service analytics, let’s look at two use cases: Low Pox Recovery and Conveyor Belt Optimization.
Use Case #1: Low Pox Recovery
Situation: Regular gold recovery analysis after pressure oxidation showed low gold recovery for one of the autoclave runs. Both the cause and the frequency were unknown. Here’s the breakdown of the use case and the value that was gained using advanced self-service analytics.
- Find the root cause of low recovery without having any leads.
- Determine if similar issues have occurred.
- Set up monitoring for dynamic pressure oxidation process.
- Visualization of relevant period through context data.
- Comparison with normal runs.
- Use of high-throughput correlation analysis to find root cause.
- Use of search functionality to find incident frequency.
- Use of fingerprints to monitor press-oxidation profiles.
- Identification of the mixer failure as recurring source of problems.
- Problem resolution through maintenance.
- Set up of system monitors to send out alerts at the earliest signs of an issue.
Substantial valued was gained through this use case. The recurring source of low performance was eliminated, and more importantly, an average 2% increase in gold recovery was realized after pressure oxidation.
Use Case #2: Conveyor Belt Optimization
Situation: Conveyor belt energy usage needed to be investigated and optimized, so the company could move from fixed-time maintenance to performance-based maintenance. Here’s this use case breakdown.
- Determine conveyor belt throughput.
- Determine relation between energy usage and throughput.
- Determine optimal operating point.
- Monitor performance to schedule maintenance.
- Create throughput formula tag based on hopper weight.
- Make formula tag for energy used per kilogram transported (specific energy).
- Determine relation between throughput and specific energy.
- Monitor operating zones for condition-based maintenance.
- Identification of optimal throughput.
- Improved hopper control for better energy performance.
- Set up of operating area monitor giving a clear objective indication of when maintenance is needed.
Again, substantial value was gained. Energy usage was decreased by 2%, and the average period between maintenance increased by 11%.
Get Rid of Your Work Headaches with Advanced Analytics
Advanced self-service analytics will empower you and your team, so you can:
- increase asset reliability
- prevent unexpected failures and downtimes
- reduce maintenance and labor costs
- reduce safety risks
- increase operation time.
You’ll have 24/7 eyes on your process to analyze, monitor, and predict the most important aspects of your mines and mining processes. You’ll also be able to contextualize your process data and share this with the whole team, thus eliminating data silos. This process transparency and knowledge exchange adds to team efficiency and collaboration.
At the end, you’ll simplify your work and your life and get rid of your work headaches. Actually, a pretty darn good deal, indeed.