Html code will be here

Optimisation of Flotation Circuit

The Conundrum flotation optimisation application controls the operation of equipment for maximum circuit performance, optimising control of the pulp level, air supply and reagents based on data from real time analytic sensors or video of foam removal.
Example of flotation curcuit
Example of flotation

Challenge

Achieving high performance, quality, and extraction targets is a difficult task because for optimal control flotation circuit operators must monitor large arrays of flotation machines and the sensors that present hundreds of indicators simultaneously

The task is further complicated by other factors as well:
Variability in equipment performance and amortisation over time
A high variability and irregularity of concurrent processes
Irregular ore quality and lack of operational information about it
Heterogeneous management as a result of operations, including shift changes, scheduled maintenance, and other variables

Conundrum Solution:
An Optimal Control Model

The control model operates on a combination of AI neural network principles and fuzzy logic. This allows for the flexibility to change the array of sensors and controls used. Optimal control actions are selected for all flotation machines based on the prediction of grades and flowrates at all points of the section taking into account connections between flotation machines. The controls maximise recovery, ensuring concentrate grade does not fall below the required minimum.

How does the model work?

  1. Virtual Sensors. The model calculates flowrate and recovery from sensor reading through grade changes and mass balance.
  2. Prediction. The model predicts grades and concentrate flowrate 60 minutes in advance.
  3. Self-correction. The predictive model is corrected in case of discrepancies between the estimates and the sensor data.
  4. Selection of control settings. Controls that maximise recoveries, while meeting the specified limits on metal grades and concentrate flowrate are required based on the predictions.
  5. Incident handling. In case of equipment malfunctions the system notifies the operator and continues control taking into account the detected abnormal situation.

Control logic for flotation machines

1. Development of a core predictive model on one flotation machine and control of that machine at the head of a given flotation section
2. Development of links between several core models of flotation machines (including pump models, sump) and the development of joint control
3. Scaling and working out end-to-end control of the entire flotation section

The end-to-end optimisation of flotation circuit:

ML applications

Virtual sensors for flowrate and recovery rate estimation
Prediction of metal grade in concentrate and tailings
End-to-end control of the entire flotation section
ML applications

Results

Accelerated handling of abnormal situations

Reduction of the tail grade

Stabilisation of the concentrate grade

Increase recovery rate

Industrial AI for metals & mining
Copyright © Conundrum Industrial Limited, 2024
Platform
CONUNDRUM INDUSTRIAL LIMITED,
Merlin Place, Milton Road, Cambridge, United Kingdom, CB4 0DP
CONTACTS
company
Contact us
By clicking the "Submit" button, you agree to the privacy policy
Contact us
By clicking the "Submit" button, you agree to the privacy policy