Wind farm in the clouds
Title: Drone-based Wind Turbine Surface Damage Detection in Challenging Conditions 
Funded by: Supergen ORE Hub ECR Research Fund: ECRRF2024 – (Call 7) 
Dates: 2024-2025 
University of Plymouth PI: Dr Dena Bazazian
Drone-Based Wind Turbine Surface Damage Detection in Challenging Conditions such as Haze and Fog focuses on developing advanced computer vision and artificial intelligence techniques for the automatic detection of wind turbine surface defects using drone-acquired imagery. 
Offshore and onshore wind turbines are frequently exposed to harsh environmental conditions that can affect image quality and hinder inspection accuracy. The project aims to improve the reliability of drone-based inspections by enhancing image visibility and enabling robust defect detection even in the presence of haze, fog, low contrast, and adverse weather conditions. 
 

Project objectives

The primary objective of this project is to develop a drone-assisted inspection framework that accurately identifies surface damage on wind turbine components under challenging environmental conditions. 
The project will investigate image enhancement, dehazing, and fog-removal techniques alongside deep learning-based damage detection algorithms to improve inspection performance. It aims to detect defects such as cracks, erosion, corrosion, lightning strike damage, paint degradation, and leading-edge blade wear while maintaining high accuracy in reduced-visibility scenarios. 
The project also seeks to support autonomous inspection workflows, reduce maintenance costs, and improve the operational reliability of wind energy assets. 

By combining intelligent image enhancement with advanced computer vision, this project aims to enable reliable wind turbine inspections regardless of environmental visibility conditions, supporting safer and more efficient renewable energy operations.

Dena BazazianDr Dena Bazazian
Lecturer in Robotics and Machine Vision

 
Wind turbine inspections are essential for ensuring the safety, efficiency, and longevity of renewable energy infrastructure. Drones have emerged as a practical and cost-effective solution for capturing detailed images of turbine blades and structural components without requiring hazardous manual access. However, environmental factors such as haze, fog, sea spray, moisture, and varying lighting conditions can significantly reduce image quality, obscure critical defect features and limit the performance of automated detection systems. These challenges are particularly pronounced in offshore wind farms, where weather conditions frequently affect visibility and can delay inspections or lead to inaccurate condition assessments. 
This project addresses these challenges by integrating image restoration, visibility enhancement, and AI-based damage detection into a unified drone inspection framework. Advanced computer vision techniques will be used to compensate for haze and fog effects, restoring image clarity and improving the visibility of turbine surfaces before analysis. Deep learning models will then process the enhanced imagery to identify and classify potential defects with greater accuracy and robustness. By enabling reliable inspections under a wider range of environmental conditions, the project supports more frequent and automated condition monitoring, reduces dependence on favourable weather windows, and facilitates predictive maintenance strategies that minimise downtime and maintenance costs while improving the overall performance of wind energy systems. 

Centre for Decarbonisation and Offshore Renewable Energy 

In response to climate change imperatives, we are bringing together a critical mass of leading research and expertise from across the University of Plymouth. Through co-creation and collaboration with partners from business, government and key communities from across the globe, the Centre aims to be a beacon for the University’s whole-system transdisciplinary approach to solutions-oriented research, accelerating sustainable developments in decarbonisation and renewable energy.
Centre for Decarbonisation and Offshore Renewable Energy