Bath Engineering & Design Studentships: Structural Health Monitoring and Digital Twinning in Sustainable Energy Systems Leveraging Artificial Intelligence

This project is one of a number in competition for a studentship from the Faculty of Engineering and Design at the University of Bath. If successful, this studentship is expected to commence 04 October 2027.

An alternative start date may be possible if agreed with your intended supervisors and the Doctoral College.

Project Description

The rapid transition to a low-carbon future relies heavily on renewable energy infrastructure and advanced energy storage systems. However, the structural integrity of these critical systems, such as offshore and onshore wind turbines and high-pressure green hydrogen storage vessels, should withstand hostile and highly uncertain operational environments. This PhD project will develop novel transfer learning techniques based on advanced machine learning models to drastically reduce computational costs, data requirements, and the carbon footprint associated with monitoring energy structures. By integrating physics-based finite element simulations with data-driven inference, the digital twin will continuously monitor structural health, infer real-time material degradation, and explicitly account for operational uncertainty without requiring high-power sensing systems. To validate the framework, small-scale experimental testing will be conducted using the multi-axis simulation table, a state-of-the-art shake table facility at the University of Bath, to simulate the complex dynamic stresses experienced by such systems. The final outcomes will provide early warning systems for critical components, extend asset lifespans, and significantly reduce the risk associated with the deployment of large-scale green energy infrastructure.