Complete Coverage Path Planning for Wind Turbine Blade Wall-Climbing Robots Based on Bio-Inspired Neural Networks and Energy Consumption Model

The rapid growth in the use of wind energy has led to significant challenges in the inspection and maintenance of wind turbine blades, especially as turbine sizes increase dramatically and as operational environments become harsh and unpredictable. Wind turbine blades, being the most expensive and failure-prone components, directly affect operational stability and energy efficiency. The efficient and precise inspection of these blades is therefore essential to ensuring the sustainability and reliability of wind energy production. To overcome the limitations of the existing inspection methods, which suffer from low detection precision and inefficiency, this paper proposes a novel complete coverage path planning (CCPP) algorithm for wall-climbing robots operating on wind turbine blades. The proposed algorithm specifically targets highly complex regions with significant curvature variations, utilizing 3D point cloud data to extract height information for the construction of a 2.5D grid map. By developing a tailored energy consumption model based on diverse robot motion modes, the algorithm is integrated with a bio-inspired neural network (BINN) to ensure optimal energy efficiency. Through extensive simulations, we demonstrate that our approach outperforms the traditional BINN algorithms, achieving significantly superior efficiency and reduced energy consumption. Finally, experiments conducted on both a robot prototype and a wind turbine blade platform validate the algorithm’s practicality and effectiveness, showcasing its potential for real-world applications in large-scale wind turbine inspection.