Imagine trying to find the perfect recipe for a super-strong metal shield, but there are millions of possible ingredient combinations. Instead of guessing and testing one by one in a lab, this project uses a smart computer program to predict the best mix. It replaces toxic or rare ingredients with common metals to make the process safer and cheaper.
Industrial coatings currently rely on slow trial-and-error development and often use toxic or critically scarce materials, making them expensive and risky under evolving environmental regulations.
An intelligent computational tool that uses machine learning and physical modelling to propose sustainable High-Entropy Hardmetal compositions for thermal spray.
If you are an equipment manufacturer dealing with rapid part wear and high replacement costs — this project developed a tool to propose High Entropy Hardmetals that increase component lifetime and reduce reliance on expensive cobalt and tungsten.
If you are a plant maintenance provider dealing with corrosive environments and strict REACH regulations — this project developed sustainable coating formulations that avoid toxic Cr6+ compounds while maintaining high corrosion resistance.
If you are a precision component supplier dealing with fluctuating raw material supply chains — this project developed a computational method to design coatings using more available elements like Al, Ti, and Si to lower supply risk.
The project minimizes the use of expensive and critical raw materials like Cobalt (Co) and Tungsten (W) by substituting them with more widely available elements and TiC hard phases.
Yes, the materials are designed specifically for direct deposition using established industrial methods: HVOF, HVAF, and CGS Thermal Spray.
Based on available project data, the project is in the execution phase (2023-2026), and specific licensing terms for the intelligent tool are not yet disclosed.
Yes, it specifically targets the replacement of carcinogenic Cr6+ compounds listed in the REACH Annex XIV and reduces the use of critical raw materials.
The project replaces slow trial-and-error methods with high-throughput physical modelling and machine learning to provide results on a time scale compliant with industrial market fluctuations.
The consortium is highly industry-oriented with a 50% industry ratio, comprising 6 companies (mostly SMEs) and 6 academic/research entities across 7 European countries. This balance suggests a strong focus on practical application and commercial viability rather than pure theoretical research.
Contact the University of Modena and Reggio Emilia
Contact us to connect with the CoBRAIN consortium for early adoption of AI-driven coating design.
