Role Overview
The Critical Heat Flux (CHF) is a physical phenomenon that may cause deterioration of heat transfer in the core of nuclear reactors, potentially leading to core damage. Its accurate prediction is therefore crucial in nuclear reactor safety. The internship deals with prediction of CHF through development of machine learning techniques and quantification of associated uncertainty, within an international OECD/NEA project.
Responsibilities
- Perform a preliminary literature review on the topic and get familiar with previous works performed at CEA.
- Analyse the new experimental CHF database to understand the physical phenomenon and verify coherence and exploitability of experimental data.
- Perform an initial assessment of previously developed machine learning models to the new database.
- Develop transfer learning to predict as accurately as possible the CHF for the new experiments.
- If time allows, investigate explainability issue and quantify uncertainty of models using state-of-the-art methodologies such as conformal prediction, hierarchical models and other coverage-driven techniques.
- Present and discuss the work during technical meetings and write a final report.
Requirements
- The ideal candidate is a MSc student with good knowledge of artificial intelligence and neural networks and an interest in fluid mechanics.
- Knowledge of the physics processes underlying the CHF phenomenon will be considered a plus.
- Good skills in Python coding and code management are required.
- Previous experience with any major deep learning framework such as PyTorch, JAX or Tensorflow is welcome.
- Experience with uncertainty quantification approaches is welcome.
- Fluency in English is considered necessary; French will be considered a plus.