Challenge

When operating a Grinding Mill, there is a tension between maximising throughput and maintaining the desired product size. Very often high feed rates into a mill can lead to it becoming overloaded - meaning that is filled beyond the point where it can sufficiently grind down and discharge material. If corrective action is not taken in time, this can cause a runaway situation that requires the mill to be stopped.

What if you could know in advance when an overload event will take place?

Our Solution

IntelliSense.io's solution to this challenge is the Mill Overload Predictions.

The Grinding Application's Overload Prediction Model is a real-time AI model that gives the probability if a future mill overload, every minute. This model is trained on historical Mill feed and performance data, so that it knows how the Mill responds to changes in solids feed rate, dilution water, material properties and control variables like mill speed and ball additions.

It then uses this digitalized knowledge to predict how the mill will respond to current conditions – and you are alerted of a potential mill overload long before it happens.

Value

This early alert enables you to take corrective action in time to prevent radical feed cuts or a mill stoppage. This means that you will:

  • Achieve more stable Grinding Circuit performance
  • Prevent mill stoppages – thereby increasing throughput over time

Dashboard Example

These predictions can be trended using a Dashboard. Below is an example of a Dashboard showing the Overload Prediction with other key Mill variables:

Steps

  1. Navigate to the ‘SAG Mill Overload Monitoring’ dashboard.
  2. Monitor the alert widget for predictions that the Mill will breach this limit, along with the current mill performance.
  3. When a mill overload is predicted, the Alert widget turns red.
  4. Follow the in-house procedures to reduce the mill weight.
  5. Keep an eye on the variables you have made changes to and the overload probability, to ensure that you have successfully averted a mill overload event.

For more info, please do reach out to us via Intercom. We'd be happy to help!

Did this answer your question?