This fully funded PhD project offers an exciting opportunity to develop AI-driven computational models for predicting and optimising the flow and compaction behaviour of refractory metal powders. The project is jointly hosted by the School of Computer Science and the School of Chemical and Process Engineering, and is conducted in collaboration with Plansee SE, a world-leading manufacturer of refractory metal components based in Austria.

The project applies state-of-the-art machine learning techniques to fundamental challenges in powder metallurgy, including AI-assisted calibration of Discrete Element Method simulations, convolutional neural network-based prediction of powder flowability from scanning electron microscopy images, surrogate modelling for high-density powder pressing, and Physics-Informed Neural Networks for compaction mechanics. Refractory metals such as Tungsten, Molybdenum, and Tantalum are indispensable for extreme-environment applications, including high-performance aerospace structures, high-temperature turbine systems, energy generation infrastructure, and medical implants. The project will produce validated AI models capable of predicting powder behaviour at significantly reduced computational cost compared to conventional numerical methods, while yielding transferable frameworks applicable to broader classes of particulate materials.

This fully funded PhD project offers an exciting opportunity to develop AI-driven computational models for predicting and optimising the flow and compaction behaviour of refractory metal powders. The project is jointly hosted by the School of Computer Science and the School of Chemical and Process Engineering, and is conducted in collaboration with Plansee SE, a world-leading manufacturer of refractory metal components based in Austria.

The project applies state-of-the-art machine learning techniques to fundamental challenges in powder metallurgy, including AI-assisted calibration of Discrete Element Method simulations, convolutional neural network-based prediction of powder flowability from scanning electron microscopy images, surrogate modelling for high-density powder pressing, and Physics-Informed Neural Networks for compaction mechanics. Refractory metals such as Tungsten, Molybdenum, and Tantalum are indispensable for extreme-environment applications, including high-performance aerospace structures, high-temperature turbine systems, energy generation infrastructure, and medical implants. The project will produce validated AI models capable of predicting powder behaviour at significantly reduced computational cost compared to conventional numerical methods, while yielding transferable frameworks applicable to broader classes of particulate materials.