Digital Twin for Offshore Wind Turbine Gearing¶
Physics-Informed Deep Learning for Fault Diagnosis and Prognosis
This project develops digital-twin methods for offshore wind turbine monitoring and maintenance. It connects real-time sensor data, physics-informed machine learning, and maintenance planning so that turbine component degradation can be diagnosed, predicted, and used in operational decision-making.
Project Details¶
| Item | Detail |
|---|---|
| Type | Internally funded research |
| Status | Live |
| Funder | University of Hull |
| Value | £5,000 |
| Dates | 1 March 2024 - 28 February 2025 |
| Partner | Indian Institute of Technology Madras |
| Research centres | Aura CDT, VARS, Dependable Intelligent Systems |
| Theme | Energy, Environment and Sustainability |
| Koorosh's role | Co-Investigator |
Project Focus¶
- Physics-informed machine learning for degradation prediction.
- Fault diagnosis and prognosis for offshore wind turbine gearing.
- Remaining useful life estimation and component-health monitoring.
- Maintenance planning that considers reliability, cost, environment, and safety.