Digital Twin for Customising Espresso Coffee

INSILICOFFEE is a pioneering initiative aimed at transforming the coffee sector through the integration of advanced digital technologies, enhancing the personalisation of the drinking experience and optimising production processes. The project has received significant recognition, winning the public call within Spoke 9 “Digital Society & Smart City” of the National Centre “National Centre for HPC, Big Data and Quantum Computing”, funded by the National Recovery and Resilience Plan (PNRR) - NextGenerationEU. This initiative is part of the mission to strengthen research facilities and create innovative models of industrial digitalisation. 

INSILICOFFEE is born from the collaboration between the University of Camerino (UNICAM), the Simonelli Group (SG), Gambilongo Caffè srl (GC), and SPICI srl (SPICI), with the aim of revolutionising the world of coffee through an approach based on digital simulation and artificial intelligence. The system will allow consumers to personalise their drink with millimetric precision, while baristas and producers can rely on advanced tools to adjust the coffee extraction parameters in real-time, maximising quality and operational efficiency. 

The technological core of the project consists of two Digital Twins, advanced digital models dedicated to the roasting and percolation processes of coffee. These tools, based on Physics Informed Neural Networks (PINN), allow for extremely accurate modelling of production parameters, ensuring dynamic optimisation and advanced control over the quality of the final product. The integration of AI and physical simulations enables waste reduction, improved sustainability, and the creation of new opportunities for the coffee industry. 

Role of SPICI 

SPICI plays an important role in the design and implementation of advanced digital solutions for INSILICOFFEE. The main activities include: 

Development of the Digital Twin for optimised management of coffee roasting and extraction; 

Implementation of AI and Machine Learning algorithms for customising the user experience and improving machinery performance; 

Support for the adoption of open-source technologies, ensuring system scalability and integration in different production contexts; 

Organisation of workshops and industry studies, to align technological solutions with market needs and promote knowledge transfer.