Implementation of Autonomous Flight Path Optimization Strategy for Transmission and Distribution Line Inspection Drones Based on Dung Beetle Optimization Algorithm
Aiming at the problems of poor adaptability to complex terrain, low inspection efficiency and high energy consumption existing in the path planning of UAVs for transmission and distribution line inspection in plateau and mountainous substations, an autonomous flight path optimization strategy for UAVs based on DBO (dung beetle optimizer) was proposed to address these issues. The biological behavior of dung beetles rolling dung balls is simulated by the algorithm. A three-layer optimization model that integrates global search, local exploitation and obstacle avoidance was constructed. Meanwhile, a dynamic step size adjustment mechanism and an elite retention mechanism were introduced to improve the algorithm performance.Multi-constraint conditions for transmission and distribution line inspection, including endurance limits, terrain obstacles and signal coverage, were taken into account in this study. A multi-objective optimization function with the shortest path length and minimum energy consumption as objectives was established. Static and dynamic obstacles were introduced to achieve obstacle avoidance under various Scenarios. The pathfinding process was simplified to search for the optimal inspection path. Simulation experiments were conducted to verify the effectiveness of the proposed algorithm. Results show that the path optimization effect of this algorithm in complex terrain outperforms that of PSO (particle swarm optimization) and GA (genetic algorithm). It provides an efficient path planning scheme for intelligent inspection systems.
WANG Hong-liang, YAO Jia-yi.
Implementation of Autonomous Flight Path Optimization Strategy for Transmission and Distribution Line Inspection Drones Based on Dung Beetle Optimization Algorithm[J].
Science Technology and Engineering, 2026, 26(26): 11471-11479 DOI:10.12404/j.issn.1671-1815.2507243
围绕输配电线路巡检无人机在复杂地形下的路径规划难题,现以提升巡检效率、降低能耗为目标,研究基于改进DBO算法的自主飞行路径优化策略。通过分析无人机巡检面临的三维地形约束、多目标优化冲突及动态环境适应需求,引入动态步长调整、精英保留机制和虚拟力场障碍物规避模型对传统DBO算法进行改进,构建包含路径长度最小化、飞行能耗最低化的多目标优化模型,并结合地理信息系统(geographic information system,GIS)地形数据与无人机续航等约束条件进行三维路径建模,进一步引入多状态障碍物测试算法在多场景下的路径寻优效率[12-13]。研究旨在通过算法创新与场景适配,实现无人机在复杂环境下的路径自主优化,突破传统启发式算法的性能瓶颈,为输配电线路巡检提供兼具高效性、安全性和鲁棒性的解决方案,推动无人机巡检技术在智能电网中的深度应用。
NiuYuting, YiWenjun. Path planning and obstacle avoidance optimization analysis of UAV in power system inspection[J]. Integrated Circuit Applications, 2025, 42(9): 214-215.
XiaHaotian, YangJun, LiYang, et al. Research on UAV 3D path planning algorithm based on improved A* algorithm[J]. Computer Programming Skills & Maintenance, 2025(7): 143-146, 176.
[5]
MengX, ZhangZ, ZhuX, et al. Obstacle avoidance path planning for unmanned aerial vehicle in workshops based on parameter-optimized artificial potential field A* algorithm[J]. Machines, 2025, 13(10): 967.
[6]
LiuL, RuL, WangW, et al. UAV path planning in threat environment: A*-APF algorithm for spatio-temporal grid optimization[J]. Drones, 2025, 9(9): 661.
YunYingxiang, HuZhiwen, WuWannan, et al. Effectiveness analysis of inspection path optimization based on Dijkstra algorithm[J]. China Science and Technology Information, 2025(23): 85-87.
[9]
JinyangW, YuhuaL, RuixuanL, et al. Trajectory planning for UAV navigation in dynamic environments with matrix alignment Dijkstra[J]. Soft Computing, 2022, 26(22): 12599-12610.
LiXiang, ZhangKun, LiJianping, et al. Research on obstacle avoidance in mountainous terrain based on dung beetle optimizer (DBO)[J]. Civil Aircraft Design and Research, 2025(4): 173-180.
[12]
WangX, WeiY, GuoZ, et al. A sinh-cosh-enhanced DBO algorithm applied to global optimization problems[J]. Biomimetics, 2024, 9(5). DOI: 10.3390/BIOMIMETICS9050271.
YuXianze, ChiBaotao, ZhangXiancheng, et al. Highly robust unstructured meshing based on Delaunay and improved grid method[J]. Journal of Central South University (Science and Technology Edition), 2026, 57(1): 153-167.
[15]
ZhangF, ChenJ, RenH. Path planning and task allocation based oncommunity detection in voronoidiagrams[J]. Information Sciences, 2026, 733.DOI: 10.1016/J.INS.2025.122991.
XiangWenqiang, ShaoWei, LuoShaohui, et al. Simulation of soil moisture in permafrost regions of the Qinghai-Xizang Plateau based on LSTM model[J]. Science Technology and Engineering, 2025, 25(31): 13236-13245.
GongXuanlin, TaoQing, SuNa, et al. A recognition method for steady-state visual evoked potential EEG signals based on CNN-CBAM-LSTM[J]. Science Technology and Engineering, 2025, 25(10): 4175-4182.
LiuShushan, LiuLanlan, XiaoQiaosha, et al. 3D flight path optimization of UAV inspection for transmission towers based on GA-SA algorithm[J]. Science Technology and Engineering, 2023, 23(6): 2438-2446.
LiShiwan, YuanMingdao, XuYunqian, et al. A seepage flow prediction model for earth-rock dams using CNN-LSTM with attention mechanism[J]. Science Technology and Engineering, 2025, 25(21): 9102-9108.