Autonomous Drone Inspection of Substations Under Strong Electromagnetic Interference

Substations, as the core hubs of the power system, play a crucial role in ensuring the safe and stable operation of the power grid. However, most substations are located in remote areas with harsh environments and strong electromagnetic interference, posing significant challenges to traditional manual inspections. To address this issue, this paper proposes a multi-sensor fusion-based autonomous UAV inspection method tailored for substations. This method innovatively integrates IMU pre-integration, laser odometry, and RTK measurements into a tightly-coupled, factor graph optimization-based laser SLAM framework, effectively overcoming the bottleneck of precise UAV localization in complex electromagnetic environments. Moreover, a loop closure detection mechanism is introduced to further enhance localization accuracy and robustness. Building upon this, we propose an adaptive intelligent inspection strategy that utilizes prior map information to guide the UAV in conducting focused inspections on key components, achieving real-time flight path optimization and dynamic map updates. To validate the performance of the proposed method, we conducted field flight experiments in two typical substation environments. The results demonstrate that our method can achieve sub-meter level absolute positioning accuracy, centimeter-level relative positioning accuracy, and a mapping error below 5 cm, with inspection efficiency more than doubling that of manual inspections. This research provides a comprehensive autonomous UAV inspection solution suitable for the complex environments of substations, holding great significance in improving intelligent operation and maintenance levels and ensuring the safety of the power system. In future work, we plan to further optimize system performance and extend functionalities such as multi-UAV collaboration, aiming to achieve autonomous inspection of substations with wider coverage and higher efficiency, contributing to the development of smart grids.