Deadline for manuscript submissions: 31 January 2027.
Offshore wind turbines are exposed to harsh marine conditions that accelerate degradation and make inspection costly, hazardous, and weather-dependent. Early fault detection is needed to reduce downtime and prevent structural failure. This review investigates offshore wind turbine failure mechanisms, inspection technologies, unmanned aerial vehicles (UAVs) and robotic systems, computer-vision-based defect detection, infrared thermography, and drone-assisted maintenance. A structured literature review methodology was used to synthesise studies across offshore engineering, robotics, sensing, and machine learning. The findings show that autonomous offshore fault detection remains limited by a lack of real-world experimentation and data. UAV inspection systems offer strong remote inspection capability but often lack real-time perception and adaptive autonomy, while deep learning models remain highly dependent on controlled datasets and are vulnerable to offshore environmental noise. The literature is disconnected, with few studies integrating autonomous navigation, multimodal sensing, and onboard intelligence into a unified offshore inspection framework. These findings demonstrate the need for robust drone-based systems capable of reliable visual and thermal fault detection in real offshore environments.
