采用多无人机协同调度可以极大提高电力巡检的效率。但在实际复杂环境下,面向电力巡检任务的多无人机调度优化存在多种复杂约束,导致优化模型的求解效率低下、收敛速度缓慢。针对上述问题,本文提出一种基于精英策略的自适应蚁群算法(AACOES)。首先,综合考虑同构无人机的飞行特性、电池续航能力以及外界风场等多种实际复杂约束条件,构建一个接近实际无人机巡检调度的优化模型。其次,针对传统蚁群算法在收敛速度及全局寻优能力方面存在的不足,引入精英策略与自适应调整因子,对算法的信息素更新规则进行了优化改进,从而有效提升了蚂蚁种群的多样性以及算法的收敛速度。最后,通过与多种先进算法开展对比仿真实验,验证了所提算法的有效性。实验结果表明,在多约束条件下,该方法能够显著提升多无人机协同巡检的效率与准确性,且在算法代价方面更具优势,稳定性较高,为电力巡检领域提供了一种新的技术手段。

The use of multi-UAV collaborative scheduling can significantly enhance the efficiency of power line inspections.However,in actual complex environments,the optimization of multi-UAV scheduling for power inspection tasks faces various complex constraints,leading to low solution efficiency and slow convergence of the optimization model.To address these issues,this paper proposes an Adaptive Ant Colony Optimization with Elite Strategy (AACOES).First,an optimization model closely resembling actual UAV inspection scheduling is constructed by comprehensively considering various practical constraints,such as the flight characteristics of homogeneous UAVs,battery endurance,and external wind fields.Second,to overcome the shortcomings of traditional ant colony algorithms in terms of convergence speed and global optimization capability,we introduce an elite strategy and adaptive adjustment factors to optimize the pheromone update rules of the algorithm,thereby effectively enhancing the diversity of the ant population and improving the convergence speed of the algorithm.Finally,through comparative simulation experiments with various advanced algorithms,the effectiveness of the proposed algorithm is validated.The experimental results indicate that under multiple constraint conditions,this method can significantly improve the efficiency and accuracy of multi-UAV collaborative inspections,while also demonstrating advantages in algorithm cost and stability,providing a new technological approach for the field of power line inspections.