Predictive digital twins for optimizing food thermal and mixing processes

Overview

Predictive digital twins are advanced tools designed to enhance the control and optimization of thermal and mixing processes within the food manufacturing industry. Developed by the ASIPAL Group, these digital twins integrate multiphysics modeling with IoT-based data acquisition to provide a comprehensive predictive framework. By using computational fluid dynamics (CFD) and finite element method (FEM) simulations, these tools accurately describe heat and mass transfer, flow patterns, and quality evolution in complex food systems such as milk, fruit pulps, juices, emulsions, and pasta. This approach supports process design, boosts energy efficiency, and fosters sustainable production practices.

Technical specifications

• Multiphysics modeling: Combines CFD and FEM simulations to model heat and mass transfer, flow dynamics, and quality changes.
• IoT-based data integration: Utilizes sensor data for real-time monitoring and predictive analysis.
• Comprehensive kinetic equations: Describes nutritional, sensory, and microbiological changes to ensure product quality.
• User-friendly interface: Allows for the import of process or sensor data to provide real-time predictive outputs.
• Scalability: Proven predictive capacity through pilot and industrial trials, suitable for dairy, fruit, pasta, snack, and plant-based industries.

Technology readiness level

This technology is currently at TRL 5, indicating that it has been validated in relevant environments. Further stages include industrial scaling and co-development with partners, ensuring readiness for technology transfer or licensing opportunities.