Unmanned surface vessel routing and unmanned aerial vehicle swarm scheduling for off-shore wind turbine blade inspection

• Growing offshore wind farms need efficient inspection; exploring digital solutions. • Framework: UAV dock and recharge on USV, addressing power issues. • 45-min UAV flight needs 90-min charge, affecting inspection scheduling. • Optimisation model and Bees metaheuristic optimise USV routes and UAV schedules. The increasing size and scope of offshore wind farms drive the need for industry to reduce costs through more efficient daily operations, including inspection. Most recently, Unmanned vehicles have been investigated in conjunction with digital platform technologies to improve the efficiency and safety of inspection tasks. In this paper, we propose an Unmanned Aerial Vehicles (UAVs) swarm-Unmanned Surface Vessels (USVs) framework that combines automated USVs with a swarm of UAVs for the inspection of wind farms, addressing the insufficient power of UAVs to sustain flight and communication throughout the entire mission. Once the UAV’s battery is depleted, no signals are transmitted, and the communications become intermittent. The automated USVs carry the docking recharging station for the UAV swarm to be recharged on the USVs. Furthermore, the fact that a 45-minute UAV operation requires a 90-minute charging time complicates the scheduling task of maintaining the inspection as a continuous process. This sophisticated inspection framework requires an efficient USV routing and UAV swarm scheduling for the inspection of wind farms. We have developed a deterministic optimisation model and a multi-stage Bees metaheuristic to generate the optimal USV routes to transport the UAV swarms to the wind farm and schedule them to operate the inspection of the wind turbines. We evaluate the proposed algorithm’s performance by comparing the solutions generated with Gurobi optimisation software, adapted Genetic Algorithm (GA), adapted Particle Swarm Optimisation (PSO) and adapted Combinatorial Bees Algorithm (CBA), demonstrating improvements in the solution quality of up to 1.79%, 2.58%, 3.07% and 1.93% respectively. Note that the study does not address the actual inspection procedure or real-world deployment challenges.