Developing Digital Twins to Assist in the Control of Nuclear Complex Processes

The current emergence of new digital technologies is opening up new prospects for industry, making production more efficient, safer, more flexible and more reliable than ever. Building on initiatives already carried out in various sectors, the application of these technologies to the operation of vitrification processes could make it possible to improve knowledge of processes, optimize their operation, train operators, help with predictive maintenance and assist with process control. The SOSIE project is a collaborative innovative project, which aims at providing an initial proof of concept for the implementation of digital technologies integrating Virtual Reality, Augmented Reality, and Artificial Intelligence. This paper presents the first developments realized in the project, where three kinds of digital twins have been developed on two complementary vitrification processes: first, the “visual” digital twin, based on an immersive and interactive application from reverse-built 3D models, secondly, the “augmented” digital twin, which connects the visual twin to the supervisory PLC and provides real-time feedback of supervisory information;, and thirdly, the “intelligent” digital twin, exploiting databases from operations to train Machine-Learning algorithms and helping predict breakdowns and process drifts.