Imagine making trains glide through the air with less resistance and noise, like a sleek sports car. It's also about using 3D printing to fix worn-out wheels instead of replacing them and using AI to help drivers steer more safely. Think of it as a giant brain trust of professors and students solving the most annoying technical glitches in rail travel.
Rail operators face high costs from asset wear, energy inefficiency in freight, and capacity limits. There is a gap between academic research and the practical industrial application of AI and additive manufacturing in rail.
A network of scientific researchers and 6 specific technical outputs: aerodynamic models, EMC models, 3D printing wheel tools, wireless communication protocols, predictive maintenance tools, and AI driving assistance algorithms.
If you are a management firm dealing with unpredictable equipment failure — this project developed predictive maintenance tools that optimize rail asset management. This allows for fixing parts before they break, reducing downtime.
If you are a manufacturer dealing with high costs of replacing worn wheels — this project developed additive manufacturing for wheel re-profiling. This extends the lifespan and safety of the wheels.
If you are an operator dealing with high energy bills and noise complaints — this project developed aerodynamic models for freight transport. This reduces energy use and noise pollution.
Based on available project data, specific pricing or implementation costs are not provided as the project focuses on PhD research and community building.
The project has developed models, algorithms, and tools, but the final results indicate that expanded research and pilot demonstrations are still needed for successful adoption.
Based on available project data, there is no specific mention of licensing terms or patent ownership for the developed tools.
The project results explicitly state that supportive regulations are crucial for the successful adoption of these innovations.
The project period runs from 2023-09-01 to 2027-02-28, but specific integration timelines for individual tools are not listed.
The consortium is heavily academic, consisting of 19 universities and 5 research centers out of 25 partners. With only 1 SME and 0 large industry partners, the project is designed as a knowledge-generation engine rather than a commercial product launch. This suggests the outputs are high-level scientific tools that require an industrial partner to move toward market readiness.
Contact EURNEX e. V. in Germany for access to the PhD research outputs.
Contact us to bridge the gap between these 6 PhD innovations and your industrial operations.
