Virtual Sensors

Plug Information Gaps and Uncover Unique Insights into Processes’s Virtual Sensors deliver real-time model outputs of information that uncovers rich insights into both process and asset performance, delivered through user-friendly dashboards and reports.

What are Virtual Sensors?

A set of real-time model outputs based on dynamic and static inputs which can be used in operational and financial decision-making and automated control.  

Typically based on both dynamic and static inputs, the combination of physical modeling and machine learning is applied to gain an increased understanding of the current condition of assets, and what the future condition will be under a given set of control variables.

They differentiate from “soft sensors” as they are processed in the cloud thus avoiding instrumentation investment, and so benefit from constant retraining and re-calibration.

Made for Your Mining Challenges

Lack of Data Certainty Limits Process Efficiency

Mine sites typically have limited ability to assess their data quality, and time is often wasted dealing with multiple versions of the same data circulating in various systems and spreadsheets.

Physical sensors placed in harsh environments are easily damaged and often go out of calibration.

How it Helps

Digital Sensors for Current and Future Process States

By using a combination of physical modeling and machine learning, the virtual sensors increase understanding of processes’ current conditions and what future states will be under a given set of control variables.

Combined with the material handling model they provide values for the parameters of interest never seen before (including uncertainty).

    What you Get

    Greatly Increased Process Visibility

    The set of virtual sensors improves understanding of the process and its parameters.

    They are capable of predicting, simulating, and combining various data streams in real-time to uncover hidden states & real-time process KPIs.

    Virtual Sensors in Action

    The Virtual Sensor Portfolio has been developed and refined over several years at multiple customer sites, creating an ‘out-of-the-box’ product that can be rapidly deployed to deliver value within weeks.

    Using Virtual Sensors it is possible to gather data in places where physical 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 equipment.

    1 billion

    tonnes of material processed


    petabytes of data processed

    Mine to Market: Value Chain Optimization

    Our suite of real-time decision-making applications use Scientific AI to optimize each process; from mine to market.

    Our Material Handling model connects these applications to drive even greater efficiency.

    Our process optimization apps can be deployed on a specific process bottleneck or expanded across the entire value chain.

    They are powered by our Scientific AI Decision Intelligence Platform,

    Stockpile and Inventory Optimization

    Stockpile & Inventory Optimization

    Grinding Optimization App

    Grinding Optimization

    Thickener Circuit Optimization

    Thickener Optimization

    Flotation Circuit

    Flotation Optimization

    Solvent Extraction Optimization App

    Solvent Extraction (SX) Optimization

    Leaching Optimization App

    Leaching Optimization