CFD and Machine Learning-Based Optimization of Structured Packing Geometry for Falling Film Flow
Direction Expérimentation Procédés

IFP Energies nouvelles (IFPEN) est un acteur majeur de la recherche et de la formation dans les domaines de l’énergie, du transport et de l’environnement. De la recherche à l’industrie, l’innovation technologique est au cœur de son action, articulée autour de quatre priorités stratégiques : Mobilité Durable, Energies Nouvelles, Climat / Environnement / Economie circulaire et Hydrocarbures Responsables.

Dans le cadre de la mission d’intérêt général confiée par les pouvoirs publics, IFPEN concentre ses efforts sur :

• l’apport de solutions aux défis sociétaux de l’énergie et du climat, en favorisant la transition vers une mobilité durable et l’émergence d’un mix énergétique plus diversifié ;
• la création de richesse et d’emplois, en soutenant l’activité économique française et européenne et la compétitivité des filières industrielles associées.

Partie intégrante d’IFPEN, l’école d’ingénieurs IFP School prépare les générations futures à relever ces défis.

CFD and Machine Learning-Based Optimization of Structured Packing
Geometry for Falling Film Flow

IFPEN is a major player in the triple energy, ecological, and digital transition by offering differentiating technological solutions in response to societal and industrial challenges of energy and climate.

Falling liquid films appear in many industrial mass and heat transfer processes. In absorption columns (e.g. CO2 capture), the liquid flows as a film over complex surfaces (e.g. structured packings), where the geometry strongly influences flow behavior, gas-liquid contact performance, and thus process efficiency.

Understanding these flows is a key issue to design and optimize different systems, and an accurate prediction of fluid behaviour and mass transfer characteristics is highly desirable. However, experiments are exceptionally hard to perform at the relevant scales. Simplified CFD models exist but aren’t necessarily valid at the local scale, while more accurate multiphase CFD simulations (VOF, CHNS, etc.) can capture local physics accurately but are very computationally expensive.

Description :

The objective of this internship is to use existing validated multiphase CFD simulation results (10-100 cases of liquid film flow over packing geometries) as training data for a machine learning model that predicts flow and mass-transfer behaviour (wetted area, mass transfer coefficient, etc.) directly from geometric parameters and fluid properties.

Internship objectives:

• Literature review, selection of data, and pre-processing of CFD results
• ML surrogate model for film flow and mass transfer
• Benchmark against classical film and mass transfer models and integral correlations
• Use the model to explore/optimize packing geometry

Required profile :

We seek a candidate pursuing a Master’s or Engineering degree in Applied Mathematics, Artificial Intelligence, Data Science, Computational Physics, Mechanical or Chemical Engineering, or related fields.

• Technical skills: Strong foundation in machine learning. Solid understanding of fluid mechanics/physics. Knowledge of chemical engineering and CFD is a plus.
• Programming skills: Experience with Python (scikit-learn, pandas, TensorFlow/PyTorch). Familiarity with OpenFOAM is a plus.
• Soft skill and languages: Fluent English, autonomy, scientific curiosity, and critical thinking.

Additional information :

Duration of the internship: 6 months Period: February-November 2027
Workplace: IFPEN Solaize (20km south of Lyon)
Transport: A personal means of transportation is recommended but public transport is available.
Remunerated internship