If you are an engine manufacturer dealing with slow development cycles for green fuels — this project developed a fast design and assessment tool that reduces time-to-market for engines burning SAF and hydrogen.
AI-Driven Design Tool for Low-Pollution Hydrogen and Sustainable Aviation Fuel Engines
Imagine a digital blueprint that lets engineers test different eco-friendly fuels without building a new engine every time. It uses smart computer programs to predict how hydrogen or green fuels will burn and pollute. This acts like a high-tech simulator to speed up the creation of cleaner planes.
What needed solving
Developing engines for new sustainable fuels is slow and expensive due to the need for constant physical testing. Companies struggle to predict the environmental impact of different fuel blends across various flight speeds.
What was built
A fast design and assessment tool using machine learning and a minimal-fidelity model of a complete propulsion system and airframe.
Who needs this
Who can put this to work
If you are an airline operator dealing with strict decarbonization goals for 2050 — this project developed a prediction tool for the environmental footprint of civil aviation across all speeds.
If you are a fuel producer dealing with uncertainty about how your synthetic kerosene performs in engines — this project developed high-fidelity experimental validation for category A and C fuels.
Quick answers
What is the cost or price of the tool?
Based on available project data, no commercial pricing is provided as the project is funded by an EU contribution of EUR 3,135,144 for research and development.
Can this be scaled to industrial production?
The project focuses on a design methodology and a fast assessment tool to reduce time-to-market, which is intended to support the industrial scale-up of flexi-fuel engines.
How is the IP or licensing handled?
Based on available project data, specific licensing terms are not mentioned, but the consortium includes one industry partner and one SME.
What is the timeline for implementation?
The project runs from 2023-01-01 to 2026-12-31, aiming to meet aviation decarbonization goals set for 2050.
How does this integrate with existing engine design?
It integrates as a low-order, fast design tool that uses machine learning to embed high-fidelity models into the engine characterization process.
Who built it
The consortium is research-heavy with 3 universities and 1 research organization, but maintains a 20% industry ratio by including one industry partner and one SME. This structure suggests the project is primarily focused on technical validation and tool development rather than immediate commercial rollout.
Contact RUHR-UNIVERSITAET BOCHUM regarding the flexi-fuel design methodology.
Talk to the team behind this work.
Contact SciTransfer to connect with the MYTHOS consortium for early access to the design tool.