PhD Studentship: Machine Learning-Driven Design and Structural Health Monitoring of Concrete-Filled Double Skin Steel Tubular (CFDST) Wind Turbine Towers

No of positions: 1

The scholarship is funded by the New Lecturer Scholarship scheme (available to home students only). Currently, no scholarships are available for international students. However, the project is aligned with a Royal Society-funded project, under which the PhD student will be employed as a research assistant for three years, receiving a monthly stipend of approximately £1,000 during their PhD studies.

Concrete-filled double skin steel tubular (CFDST) sections offer superior structural performance for wind turbine towers due to their enhanced strength, ductility, and material efficiency. However, their complex behavior under combined loading conditions—compression, bending, shear, and torsion—poses significant challenges for both design and long-term performance monitoring. Traditional analytical and numerical approaches struggle to capture the nonlinear interactions between the outer steel tube, sandwiched concrete, and inner steel tube, necessitating advanced computational techniques.
This research proposes a novel framework that integrates Machine Learning (ML) for structural health monitoring (SHM) and design optimization of CFDST wind turbine towers. The study will focus on:

1. Finite Element Simulations & Experimental Data Collection: High-fidelity simulations and scaled prototype testing will generate data on stress distribution, local buckling, and damage evolution.
2. ML-Based Predictive Models: Deep learning and surrogate modeling techniques will be employed to predict structural response under varying loads and detect early signs of fatigue or failure.
3. Real-Time Structural Health Monitoring (SHM): Sensor-integrated ML models will be developed to analyze real-time data from installed wind turbine towers, enabling early fault detection and predictive maintenance.
4. Automated Design Optimization: Reinforcement learning and genetic algorithms will be applied to optimize CFDST geometries and material configurations for maximum efficiency and durability.
By bridging the gap between computational intelligence and structural engineering, this research aims to develop a self-adaptive monitoring and optimization system for CFDST wind turbine towers, enhancing safety, reducing maintenance costs, and advancing sustainable infrastructure solutions.

Applicants should have, or expect to achieve, at least a 2.1 honours degree or a master’s (or international equivalent) in a relevant science or engineering related discipline.

To apply, please contact the main supervisor, Dr Fangying Wang - fangying.wang@manchester.ac.uk. Please include details of your current level of study, academic background and any relevant experience and include a paragraph about your motivation to study this PhD project.

Advert information