Leader
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum.
Hosting Facilities
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum.
TwinLearnXR
Creation of Insights
An adaptative Digital Twin for autonomous circular manufacturing adaptative XR training powered by a high-fidelity Digital Twin for sustainable manufacturing
Challenge: Product-production Digital Twins
TwinLearnXR combines Artificial Intelligence, Digital Twins, and Extended Reality (XR) to improve sustainable plastic extrusion manufacturing and workforce training. The project creates a high-fidelity virtual replica of the production process to optimise recycled material usage, reduce waste and energy consumption, and maintain product quality. At the same time, operators train inside an adaptive XR environment connected to industrial process data, enabling safer, faster, and more effective learning through immersive simulation, AI-driven guidance, and interactive optimisation scenarios for real industrial challenges.
Leader
Hosting Facilities
ARVRtech provides the technical infrastructure required for implementation, including GPU-enabled development workstations, XR headsets, cloud and local server infrastructure, software development environments, version-control and collaboration platforms, and testing facilities for immersive applications. The project will additionally utilise Arçelik’s industrial environment and process infrastructure for pilot integration, validation, and operational testing activities.
Background
The challenge addressed by TwinLearnXR is the difficulty of increasing recycled plastic usage in extrusion manufacturing without negatively affecting product quality, process stability, waste levels, and energy consumption. Industrial operators also face challenges related to complex process monitoring, fault handling, and lengthy training periods. In many cases, process knowledge, quality behaviour, and operational training are fragmented across disconnected systems, limiting optimisation, sustainability improvements, and efficient workforce preparation.
Solution
TwinLearnXR addresses sustainability, quality-control, and workforce-training challenges in plastic extrusion manufacturing through the integration of Artificial Intelligence (AI), Digital Twins, and Extended Reality (XR). The solution combines a high-fidelity AI-driven Digital Twin of the extrusion process with an adaptive XR training environment connected to industrial process data, quality measurements, and operational workflows. The Digital Twin uses historical and live production data, quality-control records, and sensor information to simulate process behaviour, predict production outcomes, analyse defect probability, optimise recycled material ratios, and support energy-efficiency improvements. The XR environment enables operators and engineers to interact with realistic process simulations and immersive training scenarios reflecting real industrial operations and troubleshooting situations. The solution also supports AI-driven guidance, process optimisation, and more efficient workforce upskilling.
Objectives
- Increase the ratio of recycled plastic while maintaining product quality
- Reduce waste and scrap generated during extrusion production
- Reduce energy consumption through process optimisation and monitoring
- Develop an AI-driven Digital Twin of the extrusion process for prediction and optimisation
- Develop an adaptive XR training environment for faster and more effective operator training
- Improve process understanding, operational efficiency, and sustainability through AI, XR, and data-driven decision support
KPIs achieved
Development
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum. Duis vel nulla hendrerit augue aliquet posuere. In erat arcu, accumsan ut rhoncus in, fringilla at elit. Morbi non gravida ligula. Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum. Duis vel nulla hendrerit augue aliquet posuere. In erat arcu, accumsan ut rhoncus in, fringilla at elit. Morbi non gravida ligula.
Feedback
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum.
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum.
Mauris et nulla tellus. Nulla consectetur placerat nunc placerat bibendum. Sed sit amet consequat ex. Pellentesque id odio felis. Etiam tellus dui, maximus non vehicula ut, suscipit vel ex. Maecenas quis lorem ut sem aliquet fermentum.