THE APPLICATION OF MACHINE LEARNING METHODS TO THE PREDICTION OF HIGH-TEMPERATURE MECHANICAL PROPERTIES – Prof. Javier Dominguez

Project title:
Application of Machine Learning Methods for Predicting High-Temperature Mechanical Properties of Structural and Nuclear Materials

Abstract:
The solution combines experimental data obtained at NCBJ and industrial partners in Turkiye with literature data and advanced artificial intelligence methods to overcome the limitations of conventional empirical and numerical approaches in describing material behaviour under extreme temperature conditions. 

A broad range of regression algorithms has been evaluated, with Supervised regression methods providing the highest predictive accuracy. The predictive and optimized model is integrated with a Python-based Streamlit interface, allowing engineers and designers to enter parameters manually or upload CSV files and obtain predictions without requiring programming expertise; being managed by several AI agents. 

The pre-implementation work will focus on experimental validation, further development of the user interface, pilot testing with potential users and preparation for commercialization. The final result will be a computer-based predictive engineering tool intended to improve the safety and efficiency of material selection and design, reduce the need for costly experimental testing, and support the introduction of new materials in the energy, chemical and nuclear sectors. 

 

Funding body: Science4Business – Inkubator Rozwoju S4B
Duration: 18 months

Budget: 100,000 PLN



This project has received funding from the European Union Horizon 2020 research and innovation
programme under grant agreement No 857470 and from European Regional Development Fund
via Foundation for Polish Science International Research Agenda PLUS programme grant
No MAB PLUS/2018/8.
Poland
The project is co-financed from the state budget within the framework of the undertaking of the Minister of Science and Higher Education "Support for the activities of Centers of Excellence established under Horizon 2020".

Grant: 5 143 237,70 EUR
Total value: 29 971 365,00 EUR
Date of signing the funding agreement: December 2023

The purpose of the undertaking is to support entities of the higher education and science system that have received funding from the European Union budget in the competition H2020-WIDESPREAD-2018-2020/WIDESPREAD-01-2018-2019: Teaming Phase 2. in the preparation, implementation and updating of activities, maintenance of material resources necessary for carrying out activities, acquisition and modernization of scientific and research apparatus, maintenance and development of personnel potential necessary for the implementation of activities, and dissemination of the results of scientific activities.