考虑推进器能耗的UUV多目标轨迹优化

于 晨阳
哈尔滨工程大学智能科学与工程学院

摘要


针对现有UUV轨迹规划研究在综合考虑机械系统关键性能方面存在的不足，本文提出了一种改进的多目标优化框架，以同时优化路径长度和推进器能耗。首先，建立UUV动力学模型，以及推进器能量消耗模型，将轨迹规划问题深度耦合于UUV的机械执行机构特性与动力学约束之中。其次，考虑传统灰狼算法（GWO）在处理此类高维约束问题时存在的收敛性与多目标问题处理缺陷，引入了一种基于余弦变化的非线性收敛因子，增强了算法的全局寻优能力与帕累托前沿最优解集。仿真结果表明，与传统GWO算法相比，所提改进算法能够在复杂栅格障碍物环境中，高效生成一系列在续航能力（能耗）与路径长度之间取得最佳权衡的全局路径，并且该路径更加稳定、安全。充分证明了改进后算法的有效性。

关键词


水下无人航行器；低能耗优化；轨迹规划；灰狼算法

全文:

PDF


参考


[1]Caccia M. Autonomous Underwater Vehicles: Modeling, Control Design, and Simulation[M]. Boca Raton: CRC Press, 2018.

[2]Zhou A, Qu B Y, Li H, et al. Multiobjective Evolutionary Algorithms: Survey and Directions[J]. Swarm and Evolutionary Computation, 2011, 1(1): 32-49.

[3]YANG X, ZHOU D J, SONG W. A NSGA-II-based layout method for cable bundles with branches using machine learning[J]. IEEE Access, 2021, 9: 90392-90401.

[4]Xiaofei L ,Pei Z ,Hui F , et al. Multi-Objective Reactive Power Optimization Based on Improved Particle Swarm Optimization With epsilon-Greedy Strategy and Pareto Archive Algorithm[J].IEEE ACCESS,2021,965650-65659.

[5]Liu Z ,Ou Y ,Wang S . An improved grey wolf optimizer with multi-stage differentiation strategies coverage in three-dimensional wireless sensor network.[J].Scientific reports,2025.

[6]Wang X ,Liu X ,Xu Y , et al. A general adaptive layer height continuous path planning algorithm for concrete 3D printing of complex porous structures based on multi-objective optimization and reinforcement learning[J].Structures,2025,80109926-109926.


Refbacks

  • 当前没有refback。