EIRS

All demos · Industrial challenges

AR · Situated analytics · Live process data

Situated Analytics in Digital Twins

A digital twin links a digital representation of equipment with data from the real system. Explore this connection through a physical process testbed, a virtual reality (VR) model and an augmented reality (AR) view that places live measurements and historical trends beside the equipment.

Situated Analytics in Digital Twins
The JuiceMixer testbed shown in its physical, virtual reality and augmented reality forms.

Live data, in context

Bring process information into the operator’s view of the equipment. Measurements appear beside the components they describe, supporting inspection of the machine and its data together.

What the demo shows

  • Temperature, pH and liquid-level readings linked to individual components.
  • Historical trends showing how measurements change over time.
  • An AR interface for inspecting data around the operating equipment.
  • VR views for exploring equipment interaction and assembly.

Testbed and equipment

The JuiceMixer is a physical process rig with liquid vessels, sensors and pumps. It provides a testbed for connecting equipment with digital information. A HoloLens 2 headset presents the AR interface, and a related VR model supports exploration of the equipment.

What it enables

Operators can move from an overview of the process to readings and trends for an individual vessel. The related VR views support exploration of equipment layout, interaction and assembly.

The operational challenge

Conventional dashboards often separate measurements from the equipment being inspected. Operators must identify which component a value belongs to and relate it to the current process state. This becomes harder when several similar vessels or components need attention.

System overview

The testbed combines an instrumented physical process, a digital equipment model and an AR data interface. The application associates each selected measurement or trend with its corresponding vessel, giving operators a component-level view of the process.

How the data flows

A Raspberry Pi coordinates sensing and control on the testbed. Python and Flask provide backend services. MQTT messaging carries live data and commands, while InfluxDB 2.0 stores historical readings. The Unity application retrieves selected values and trends for display around the physical equipment.

How operators use it

Through HoloLens 2, an operator selects a vessel and inspects its current readings or historical trends. MRTK, the Mixed Reality Toolkit, supports hand interaction through pinch, touch and grab gestures. The related VR view provides a separate way to explore equipment interaction and assembly.

Technology behind the testbed

Temperature and pH sensors measure process conditions, and ultrasonic sensors measure liquid level. Peristaltic pumps move liquid through flexible tubing, while motor speed is used to derive flow-rate information. A Raspberry Pi connects the physical equipment to a Python and Flask backend. MQTT provides messaging over local Wi-Fi, and InfluxDB 2.0 stores time-series data. The AR application is built in Unity for HoloLens 2. This implementation runs on a local network.

Next development opportunities

Extend the testbed with additional sensors, equipment models, and industrial data interfaces. Industry projects can adapt the visualisations to specific workflows, test them with operators, and define on-site connectivity and performance requirements.

Potential industrial applications

  • Operations and process monitoring: inspect live temperature, level, and flow values beside relevant equipment.
  • Troubleshooting: compare current readings with historical trends at the asset.
  • Maintenance and inspection: locate relevant component information while working at the equipment.
  • Commissioning and training: explore equipment layouts and interactions in VR before hands-on work.

Industrial applications

When measurements are separated from the equipment, operators must work out where each reading belongs. Bringing information into the physical workspace can support inspection and investigation of changing process conditions.

Machine data in spatial context

Connect readings and historical trends to the vessels, components or locations they describe. Teams can inspect measurements while keeping their relationship to the process visible.

Machine information in AR

Make relevant information available beside the equipment being inspected. An application could connect approved machine data with an augmented view designed around the operator’s task.

Understand abnormal machine conditions

Bring unusual readings, historical changes and component locations together for investigation. Machine-specific indicators and thresholds could be developed around the conditions the team needs to recognise.

Bring your process into view

A collaboration could identify the measurements, equipment locations and inspection tasks that would benefit from information in context.

Explore research and collaboration →

Media

Videos

Images

Live sensor values overlaid on the physical JuiceMixer testbed.
Live sensor values overlaid on the physical JuiceMixer testbed.
AR overview of temperature and pH across six tanks.
AR overview of temperature and pH across six tanks.
Tank readings and historical trends anchored beside the vessel.
Tank readings and historical trends anchored beside the vessel.
AR tank panels beside the physical control cabinet.
AR tank panels beside the physical control cabinet.
Temperature, pH and liquid-level indicators for each vessel.
Temperature, pH and liquid-level indicators for each vessel.
Live readings across the six process vessels.
Live readings across the six process vessels.
Situated tank panels beside the JuiceMixer apparatus.
Situated tank panels beside the JuiceMixer apparatus.
First-person view of the JuiceMixer and its AR data panels.
First-person view of the JuiceMixer and its AR data panels.
Figure 1 from The Juice Mixer: A Platform for Developing and Evaluating Immersive Analytics, HFIA 2025.
Figure 1 from The Juice Mixer: A Platform for Developing and Evaluating Immersive Analytics, HFIA 2025.
Figure 2 from The Juice Mixer: A Platform for Developing and Evaluating Immersive Analytics, HFIA 2025.
Figure 2 from The Juice Mixer: A Platform for Developing and Evaluating Immersive Analytics, HFIA 2025.
Figure 3 from The Juice Mixer: A Platform for Developing and Evaluating Immersive Analytics, HFIA 2025.
Figure 3 from The Juice Mixer: A Platform for Developing and Evaluating Immersive Analytics, HFIA 2025.

Research and reports

Project and programme

This work is part of DDIA, Data Driven Immersive Analytics in Digital Industries.

DDIA is an FFG COMET Module (2022 - 2026) at Know Center Research GmbH.

↑ Top