ENabling sustainable COmbustion technologies using hybrid physics-based Data-driven modelING

At the 26th UN Climate Change Conference of the Parties (COP26), the reached consensus points for the need of an energy revolution, in which hydrogen will play a key role, especially in Energy Intensive Industries (EIIs) for which electrification is more challenging.

Still, current infrastructures are not ready to adopt hydrogen and other Renewable Synthetic Fuels (RSFs) in an efficient, safe, and sustainable way. ENCODING holds the promise to smooth the transition towards RSFs use, thereby helping decarbonise EIIs.

To do so, ENCODING main objective is to train the next generation of digital combustion experts, by offering them an innovative training programme.

The 10 doctoral candidates will gain multidisciplinary know-how in sustainable fuels, experimental techniques and numerical simulations of turbulent reacting flows, big data analytics and machine learning, and intersectoral experience (academic and industrial relevant training).

Together, they will be able to create knowledge to develop a generalised hybrid ML-based digital infrastructure, with the capability to solve current and future outstanding questions to decarbonise EIIs.The unique training is only possible thanks to the participation of renowned academic institutions with partners specialized in combustion experiments and simulation (ULB, RWTH, CNRS, CNR), data analysis and dimensionality reduction (UPM, ULB), data-driven and ML-based modelling (ULB, RWTH, CNRS) and different companies in the whole chain of knowledge: sustainable fuels (Air Liquid), combustion systems (MITIS, NPT), fuel flexible burners (WS, TENOVA), pollutant remediation strategies (AGC, AMMR) and CFD software (CONVERGE, CFD Direct).