University of Exeter
PhD Studentship: Multiscale Scientific Machine Learning Digital Twins for High-Torque Electric Propulsion under Extreme Duty Cycles
- Exeter
- £21,805 pa
- Contract
Develops a multiscale Scientific Machine Learning digital-twin framework to predict thermal trajectories, torque capability and efficiency in low-speed, high-torque electric propulsion under extreme duty cycles. Combines physics-informed hybrid architectures (DNNs, neural state-space models, Neural ODEs) with safety-constrained dynamometer experiments at the Centre for Future Clean Mobility, in collaboration with marine power-systems company Ecomar Innovations.
Neural Ordinary Differential Equations · Deep Neural Networks · Recurrent Neural Networks +2