Sort by
Refine Your Search
-
. Although there is a clear synergy between fatigue damage and corrosion, most fatigue prognosis models do not explicitly consider the role of the environment, which is usually reduced to obscured fitting
-
critical to ensuring the longevity and safety of fusion reactors. This PhD project focuses on developing an integrated framework that combines cutting-edge computational models, including Monte Carlo
-
a comprehensive, multi-fidelity suite of liquid hydrogen (LH2) pump models to predict and analyze pump performance, stability, and its interaction with the broader fuel system architecture for a
-
the intersection of ecology, machine learning, and sustainable land management, the research will combine field data collection, deep learning model development, and stakeholder co-design to support biodiversity
-
AI techniques for damage analysis in advanced composite materials due to high velocity impacts - PhD
for automated, data-driven diagnostics, integrating AI with high-resolution imaging and sensing offers a transformative solution. AI models can learn to recognize subtle damage patterns, enabling faster, more
-
control system that enhances Annual Energy Production (AEP), reduces mechanical stress, and improves fault detection using machine learning (ML) and physics-based modelling. The candidate will gain hands
-
production-grade system that integrates Vision Transformers for visual deepfakes, advanced Natural Language Processing (NLP) models for phishing detection, and a dedicated Explainable AI (XAI) layer
-
of the complex physics governing the interaction between the heat source and the material. Additionally, it seeks to develop an efficient modelling approach to accurately predict and control the temperature field
-
and kinematic models with machine-learning-based channel state information (CSI) prediction to enable robust, low-latency connectivity across multi-layer NTN systems. This PhD project sits
-
: Computational Modelling: Employing simulation tools (e.g., GEANT4, light transport) to explore novel metamaterial designs, predict performance, and optimise key parameters such as timing resolution, light yield