Offre de thèse dans le cadre d’un Doctoral Network
Performance prediction and reusability/recyclability assessment of refractory materials using online sensoring, machine learning and digital decision-making tools
CNRS-IRCER (Limoges) - VESUVIUS (Ghlin)
Personnes à contacter par le candidat
Alexandre BOULLE (email@example.com)
Marc HUGER (firstname.lastname@example.org)
Johan RICHAUD (email@example.com)
PhD13 dans le cadre du projet Européen CESAREF (Concerted European action on Sustainable Applications of REFractories – www.cesaref.eu)
Objectives: The ability to predict in-service evolution and reusability of refractory materials is critical to maximize material lifetime and reduce operational costs. The in-service evolution of thermo-chemico-mechanical properties need to be perfectly understood and predictable. Industrial scale non-destructive sensoring combined with machine learning algorithms will then be implemented to develop an accurate numerical model to evaluate the reusability and recyclability of refractory parts.
Expected Results: Pertinent non-destructive sensoring approach will be investigated at both laboratory scale and on-site, to assess thermo-chemico-mechanical properties evolution of refractory parts in service. Thanks to available industrial experience, novel sensoring methodologies will be developed to generate data that will be
used to train machine learning algorithms. A digital tool will be implemented to help the end-user to take 4R (Reduce, Reuse, Recycle and Replace) decisions.
Keywords: Sensors, Non-destructive testing, data acquisition, machine learning, data science, data mining, refractorymaterials, high temperature processes.
Applicant Profile: Master’s level in Materials Science and/or Industrial Engineering. Candidates should have an in-depth knowledge in programming, data analysis and/or machine learning. Oral and written communication skills (English) are mandatory.