Skip to content

Try it on the model first.

A digital twin is a model of a machine, line or plant kept in step with live data. It lets teams see the current state in context and test what-if changes - a new product, layout or schedule - without risking production.
Digital twin

What It Is

Twins come in levels. The simplest is a structured model of the plant - every asset, its data and its place in the hierarchy - fed by live data. Next comes a process or flow simulation that can run faster than real time. Some projects add a 3D view, or use the twin to test PLC code before commissioning.

The value comes from starting with a clear question - where is the bottleneck, will this line handle the new product, what happens if this machine is down - and building only as much model as that question needs.

How It Works

The system from the sensor to the people who act on it. Every project is sized to the site, but the layers stay the same.

  1. Data

    Live signals

    Tags from PLCs, SCADA and MES published in a common structure.

  2. Model

    Asset model

    Equipment hierarchy and information models that give every value its meaning.

  3. Simulate

    Process & flow

    Discrete-event or physics-based simulation of lines, buffers and utilities.

  4. View

    Visualisation

    Dashboards, plant overviews or 3D scenes, linked to live and simulated data.

  5. Decide

    What-if

    Scenarios compared side by side before money is spent on the floor.

Key Technologies

The protocols, standards and components we work with on this use case.

Modelling

  • ISA-95 equipment hierarchy
  • OPC UA information models
  • Asset Administration Shell
  • Unified namespace

Simulation

  • Discrete-event simulation
  • Virtual commissioning
  • PLC emulation
  • Physics models

Visualisation

  • 3D scenes (glTF / USD)
  • Web dashboards
  • Time-series historian
  • MQTT

Typical Deliverables

What a project usually hands over. We agree the exact scope with you before work starts.

  • Questions the twin must answer, agreed up front
  • Asset model and data structure
  • Live data connections
  • Simulation model, validated against real data
  • Scenario reports and recommendations
  • Hand-over so your team can run new scenarios
The practice behind it: Industrial AI

Where It Applies

Industries where this use case answers a problem we see often. Each links back to the sector page.

Let's Scope Your Project.

Tell us about your site and what you want to improve. Our engineers will help you scope a practical first step.