Drone inspection path planning with self-organizing neural network of elastic Hebbian learning rule

Abstract As the scale of the power grid continues to expand, inspection scenarios become increasingly complex, and inspection and maintenance work in the power industry faces huge challenges. The traditional manual inspection mode has problems such as high cost, low efficiency, and poor safety. Using electric drones to inspect all equipment nodes in the area can effectively reduce operation and maintenance costs and ensure personnel safety. As a key technology to realize autonomous power inspection, UAV path planning needs to overcome difficulties such as long solution time and intersection of inspection paths. Therefore, this article conducts research on UAV path planning algorithms for large-scale power inspections, which is of great significance to improving the efficiency of power inspections. To avoid the occurrence of path intersections and improve the path planning effect, this paper uses the convex hull property in graph theory to design elastic Hebbian learning rules and proposes a self-organizing neural network algorithm based on elastic Hebbian learning rules.