In-Service Wind Turbine Blade Inspection: A Multi-UAV Architecture Design and Preliminary Validation

Abstract

Wind turbine blade inspections are critical for ensuring structural integrity and minimizing operational downtime. However, existing methods, such as single Unmanned Aerial Vehicle (UAV) inspections, are limited by trade-offs among coverage, resolution, operational constraints, and often require turbine shutdown. This paper presents a multi-UAV inspection architecture design for in-service wind turbine blade inspection. The proposed architecture design provides a scalable framework for multi-UAV-based inspection of wind turbines during operation, enabling data acquisition without halting the turbine. The system distributes tasks across multiple UAVs, enabling simultaneous global observation, close-range surface imaging, and deflection detection. A ground station is introduced to coordinate the system, aggregate multi-view data, and offload computationally intensive processing. By separating global and local perception tasks, the architecture addresses key limitations of single-UAV systems and supports synchronized data acquisition during regular wind turbine operation. The core components of the system are implemented and evaluated using a scaled wind turbine model. Results demonstrate stable, persistent blade identification, reliable deflection estimation during rotation, and a component-level preliminary validation on embedded hardware platforms in terms of computational and energy requirements.