Virtual Sensor Portfolio

Plug Information Gaps, and Uncover Unique Insights into Processes

A Virtual Sensor is the output of a digital asset; a real time model output (including uncertainty) based on both dynamic and static inputs which can be used in operational and financial decision making, automated control and both machine learning and empirical simulation-based prediction models. 

They differentiate from the “soft sensor” as they are processed in the cloud, and so benefit from constant retraining and re-calibration. The accuracy and robustness of the outputs are cross verified using equivalent outputs of parallel models. Their deployment is non-intrusive.

Virtual Sensors are used to plug information gaps, and provide unique insights into process and asset performance delivered through user friendly dashboards and reports. 

A combination of physical modelling and machine learning is applied to gain increased understanding about the current conditions of the thickener wear, and what future conditions will be under a given set of control variables.

Virtual Sensor Portfolio

Avoiding instrumentation investment; A real time model output (including uncertainty) based on both dynamic and static inputs which can be used in operational / financial decision making and automated control.

Reporting and Alerts

All of the data generated through the digital mine and plant can be manipulated using configured dashboards and report subscriptions giving the user one platform to view normally individually siloed data. Any data, including the virtual sensors and financial model outputs, can also be downloaded in raw csv form. The application provides configurable push notifications.



  • Mine sites typically have limited ability to assess their data quality
  • Time is often wasted dealing with multiple versions of the same data circulating in various systems and spreadsheets
  • Mine sites are amongst some of the most challenging operating environments and data can often be lost when sensor are damaged or go out of calibration


  • Virtual sensors are real time model outputs of digital assets, based on dynamic and static inputs
  • Combined with the material model tracking material flows and properties, they provide values for the parameters of interest including uncertainty


  • Improved understanding of the process and its parameters and ability to predict, simulate and optimize it

Using Virtual Sensors it is possible to gather data in places where physcial sensors would not be possible for example within a Grinding Mill. Virtual Sensors can also reduce the need for additional sensors along water pipelines and other equipments.


Tonnes of material processed


Petabytes of data processed

New Data Points

Supplement existing data points and physical sensors without the need for maintenance.

The Application Portfolio