Descripción
Project Description: This master's thesis is conducted as part of a collaboration between Swerim and Sandvik Coromant. The project aims to develop machine learning methods for automated and accelerated analysis of X-ray diffraction (XRD) data from a wide range of cemented carbide grades and PVD/CVD coatings engineered for cutting tool applications. The project will focus on generating a database of simulated diffraction patterns and using it to train models that can automatically identify the correct phase constituents, perform peak fitting, and extract detailed microstructural information such as phase fractions crystallographic texture, microstrain, and other relevant material parameters. The objective is to significantly reduce the time required for phase identification, peak fitting, and comprehensive diffraction analysis compared to conventional workflows. The work will evaluate machine learning approaches both as a complement to and as a potential alternative for traditional Rietveld refinement, contributing to the development of next-generation tools for high-throughput materials characterization. Qualifications: We are looking for a curious and collaborative student pursuing a Master's degree in Materials Science, Engineering, Computer Science, Applied Physics, Data Science, or a related field. The ideal candidate has an interest in machine learning, programming, and data-driven methods, and is motivated to apply these tools to challenges in materials characterization and development. You enjoy solving complex technical problems and working at the interface between materials science and artificial intelligence, with the opportunity to contribute to the development of next-generation analysis tools for advanced engineering materials. Project time The project is intended for a master thesis (30hp). The start date is January 2027 or can be mutually decided through negotiations. Further information This project is intended to be performed at Swerim in Kista Stoc