Intern: Material property estimation

Thermomechanical simulations are used to predict product performance and reliability up front, to speed up material selection, design optimizations and reduce empiricism/qualification effort. A key part of making this happen is the availability of reliable material data, stored in and extracted from a local materials database. Obtaining materials for characterization from suppliers generally takes long/ An alternative approach to obtain reasonably accurate data while waiting for the final data is the ability to predict the properties materials that are similar to others where data is available, e.g. based on minor differences like the silica filler content in Epoxy Molding Compounds. The use of AI tools could enable this prediction. The main aim of this internship is to develop a workable AI tool that can perform such predictions, and validate that using empirical data based on case studies.
Key activities:

- Literature search to review the state of the art (AI-based material property prediction)

- Developing a tool using AI software

- Validation using case studies

- Preparing a user-friendly tool for transfer to NXP

More information about NXP in the Netherlands...

#LI-3623