About us
Espace utilisateur
Education
INSTN offers more than 40 diplomas from operator level to post-graduate degree level. 30% of our students are international students.
Professionnal development
Professionnal development
Find a training course
INSTN delivers off-the-self or tailor-made training courses to support the operational excellence of your talents.
Human capital solutions
At INSTN, we are committed to providing our partners with the best human capital solutions to develop and deliver safe & sustainable projects.
Thesis
Home   /   Thesis   /   Generic digital twin of vitrification processes for the production of virtual tests

Generic digital twin of vitrification processes for the production of virtual tests

Artificial intelligence & Data intelligence Engineering sciences Mathematics - Numerical analysis - Simulation Technological challenges

Abstract

The CEA has been working for years on the development of vitrification processes, which enable final nuclear waste to be incorporated into a durable matrix - glass. These processes are complex systems that involve three main technological components: the furnace, the calciner and the gas treatment.

The current emergence of new digital technologies offers new perspectives for the exploitation of these vitrification processes, in particular the digital twin, which aims at developing the most faithful digital replica of an object, a process or a system.

The objective of this work is to build a generic digital twin of these vitrification processes, from the data acquired during the tests already carried out on the one hand and the knowledge of the process on the other hand. This numerical twin will appropriate all the components of its physical twin, as well as its properties, through models of different natures, possibly mixing different levels of detail, based on adapted and proven business modeling languages. By using the existing models of the different subsystems of the process, by exploiting the data already acquired during the past experiments and by developing a functional architecture similar to the reality, the idea would be to conceive a realistic digital twin, sufficiently accurate to generate exploitable virtual results, in the same way as those produced by real tests, in order to reduce the number of real tests which are very expensive.

The work aims at developing a numerical twin that is generic enough to be adapted to all types of existing vitrification processes.

The student will be specialised in system engineering with strong skills in data intelligence (artificial intelligence, machine learning, data mining, augmented reality...). The skills developed in data intelligence during this work on the one hand and the experience acquired in the field of application on the other hand will be valuable for the future doctor, with the emergence of new digital technologies, which open up new perspectives in all industrial sectors.

Laboratory

Département de recherche sur les technologies pour l’enrichissement, le démantèlement et les déchets
Service d’études de vitrification et procédés hautes températures
Laboratoire de développement des procédés de vitrification
Top pencilenvelopegraduation-hatlicensebookuserusersmap-markercalendar-fullbubblecrossmenuarrow-down