基于改进鲸鱼优化算法的输电线路巡检无人机巢部署优化

Optimization of Drone Nest Deployment for Transmission Line Inspection Based on Improved Whale Optimization Algorithm

摘要: 输电线路巡检中，无人机巢的合理部署是提升巡检效率、降低运营成本的关键。传统部署方法普遍存在覆盖不均衡、成本控制不佳、算法收敛速度慢等问题。为解决上述挑战，本文提出一种融合自适应权重与多策略变异机制的改进鲸鱼优化算法(Improved Whale Optimization Algorithm, IWOA)，构建涵盖建设成本、运维成本及飞行成本的整数规划模型，实现无人机巢位置选择、类型配置与巡检任务分配的协同优化。该算法通过动态调整搜索权重平衡全局探索与局部开发能力，结合巢型替换、任务重分配及位置微调三种变异策略，提升解的多样性与精准度。基于500个输电塔的模拟数据集，将IWOA与原始鲸鱼优化算法(WOA)、粒子群优化(PSO)、遗传算法(GA)、模拟退火算法(SA)进行对比实验。结果表明，所提算法在测试实例中实现最低部署成本(115.47)，且收敛速度较WOA、PSO、GA和SA表现出显著优势，在覆盖完整性、成本优化效果及稳定性方面均优于对比算法。该研究为电力基础设施巡检的无人机巢部署提供了新的优化方案，对提升输电线路维护的经济性与可靠性具有重要实践意义。

Abstract: In transmission line inspection operations, rational deployment of drone nests is crucial for enhancing inspection efficiency and reducing operational costs. Traditional deployment methods often suffer from uneven coverage, poor cost control, and slow algorithm convergence. To address these challenges, this study proposes an Improved Whale Optimization Algorithm (IWOA) integrating adaptive weights and multi-strategy mutation mechanisms. By constructing an integer programming model that incorporates construction costs, operation and maintenance expenses, and flight costs, the algorithm achieves coordinated optimization of drone nest location selection, configuration types, and inspection task allocation. Through dynamic adjustment of search weights to balance global exploration and local development capabilities, combined with three mutation strategies—nest type replacement, task redistribution, and position fine-tuning—the algorithm improves solution diversity and precision. Comparative experiments using a simulated dataset of 500 transmission towers demonstrate that IWOA achieves the lowest deployment cost (115.47) among original Whale Optimization Algorithm (WOA), Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Simulated Annealing (SA). The algorithm exhibits significantly faster convergence speeds and superior performance in coverage completeness, cost optimization effectiveness, and stability compared to competing methods. This research provides a novel optimization framework for drone nest deployment in power infrastructure inspections, offering practical significance for enhancing the economic efficiency and reliability of transmission line maintenance.