13 electric-machine-"https:"-"https:"-"https:"-"https:" PhD positions at Cranfield University
Sort by
Refine Your Search
-
research opportunity focuses on advancing large-scale additive manufacturing using metal wire as feedstock and electric arc as the heat source. The project aims to develop an innovative and efficient
-
opportunity focuses on advancing the field of large-scale additive manufacturing, utilising metal wire as the feedstock and electric arc as the heat source. The project aims to enhance our understanding
-
intersection of aircraft systems design, thermal management, and artificial intelligence/machine learning. It focuses on electrothermal ice protection systems (ETIPS), which prevent hazardous ice
-
necessitates the development of novel technologies like hybrid-electric or hydrogen-fuelled aircraft, as noted in the government’s Transport Decarbonisation Plan and Jet Zero Strategy. Yet, how
-
modelling approach could resolve this issue and we could use obtain data-driven models using machine learning algorithms such as artificial neural networks, reinforcement learning, and deep learning
-
inevitable in machine components even working in normal operational conditions. Surface degradation, at the mechanical contacts due to wear, has an impact on the noise emitted because of the rapid
-
velocity and total pressure. The project will investigate how machine learning and data-driven methods can be used to: Develop surrogate models that predict distortion metrics from sparse sensor
-
reinjection back into the machine during periods of high power demand. This reinjection of compressed air augments the power output of the engine as a result of the increased pressurised air mass flow. The
-
limits, due to the inclusion of a gear-box and more electric technologies. This research will develop validated tools and design guidelines for future fuel system architectures tailored to ultra efficient
-
deployment in applications. This project aims to develop a physics-based, self-learning BMS tailored specifically for Li-S batteries. The research will combine physics-driven models with machine-learning