Imagine trying to bake the perfect cake but having to guess every single ingredient and temperature by trial and error. This project creates a digital 'recipe book' that uses AI and physics to predict exactly how a material will behave before you even make it. It connects the tiny microscopic details of a material to its real-world strength and durability, saving years of lab testing.
Developing new advanced materials is currently too slow and expensive due to a lack of connection between microscopic structures and macroscopic properties. This leads to high risks and wasted resources during the trial-and-error phase of material design.
A digital tool and open repository that stores metadata and knowledge using semantic ontologies to support material design decision-making.
If you are a cement manufacturer dealing with high R&D costs for low-carbon materials — this project developed a model-based workflow that links microstructural features to macroscopic properties. This allows you to validate new cement compositions faster and with less waste.
If you are a producer of Solid Oxide Fuel Cells dealing with slow material validation cycles — this project developed machine learning tools for characterization. This reduces the time and risk involved in designing more efficient energy conversion materials.
If you are a mobility company dealing with the complexity of Proton-Exchange Membrane Fuel Cells — this project developed an open data repository and ontologies. This ensures your material data is interoperable and traceable across the entire design process.
Based on available project data, specific pricing or licensing costs for the resulting digital tool are not provided.
The project validates its results on 3 industrial use cases in construction, energy, and mobility, indicating a focus on industrial applicability.
Based on available project data, the project focuses on an 'open data repository' and 'open repository' for knowledge, but specific IP licensing terms are not listed.
It uses semantic web technologies and domain ontologies (like EMMO) to ensure data is interoperable and can be linked to design and manufacturing processes.
The project period runs from 2022-12-01 to 2026-05-31, suggesting the tool will be fully developed by mid-2026.
The consortium is heavily industry-weighted with a 50% industry ratio, comprising 6 industrial partners and 1 SME. With 12 partners across 8 countries, the project is well-positioned for cross-border industrial adoption, particularly in the EU manufacturing sector.
Contact the Commissariat a l Energie Atomique et aux Energies Alternatives (CEA) in France.
Contact us to find out how to integrate these material ontologies into your R&D pipeline.
