Project Summary

SOLMET-AI-CM is an interdisciplinary project that aims to evaluate and improve the next generation of solar thermal receiver components. The project focuses on comparing metal parts produced by additive manufacturing and conventional welding, assessing their thermo-mechanical performance, structural integrity, and suitability for increasingly complex and efficient receiver geometries. To achieve this, the project combines advanced numerical simulations and experimental testing to characterize material behaviour under realistic operating conditions and validate predictive models. Artificial intelligence techniques, including genetic-algorithm-based design optimization and neural-network-based Structural Health Monitoring (SHM), will be used to identify optimal configurations and enable real-time damage detection from sensor data. By integrating advanced manufacturing, experimental validation, and AI-driven analysis, SOLMET-AI-CM seeks to enhance the performance, reliability, and safety of solar thermal receiver systems, supporting the adoption of more efficient and durable renewable energy technologies. Link to University Research Portal: https://researchportal.uc3m.es/display/act565102

SOLMETAI in a nutshell

Title: Advanced Solar Receiver Systems: Comparative Analysis of Metal Additive Manufacturing and Welding Techniques Enhanced by Artificial Intelligence

Goal: Optimizing solar thermal receivers through advanced manufacturing and AI.

Duration: 30 months (01/07/2024 – 31/12/2026)

Budget: 75.000 €

Funding: This work has been supported by the Madrid Government (Comunidad de Madrid-Spain) under the Multiannual Agreement with UC3M (SOLMETAI-CM-UC3M).

Team

Additional team members:

• Louis Baptiste Portier. Research engineer. Department of Thermal and Fluids Engineering.
• Antonia Jiménez Morales. Full Professor. Department of Materials Science and Engineering and Chemical Engineering.
• Ulpiano Ruiz-Rivas Hernando: Associate Professor. Department of Thermal and Fluids Engineering
• Álvaro Vaz-Romero Santero. Associate Professor. Department of Continuum Mechanics and Structural Analysis.
• José Diaz Álvarez. Full Professor. Department of Mechanical Engineering.

Results

Preprint

Robledo, I., Li, Y., Maceda, G. Y. C., & Castellanos, R. (2025). Fast and robust parametric and functional learning with Hybrid Genetic Optimisation (HyGO). arXiv preprint arXiv:2510.09391.

Public Code

HyGO: Hybrid Genetic Optimizer.

• https://pypi.org/project/HYGO/
• https://github.com/ipatazas/HYGO

Conference Contributions

Louis Portier, Antonio Raimondo, Andrea Cini, Rodrigo Castellanos and Rafael Pérez-Álvarez, “Numerical simulation of additive manufacturing of solar thermal receiver” 14th National and 5th International Conference in Engineering Thermodynamics (14CNIT), Zaragoza (Junio 2025).