改进鲸鱼算法及其在路径规划的应用

Improved Whale Optimization Algorithm and Application in Path Planning

摘要:

针对鲸鱼优化算法（WOA）存在的收敛速度慢、收敛精度低和易陷入局部最优等问题，提出了采用非线性收敛因子、协同a的惯性权重、时变独立搜索概率和免疫记忆改进的鲸鱼优化算法（Immune memory-a Weight-Time varying search factor Improved Whale Optimization Algorithm，IWTWOA）。应用非线性收敛因子、协同a的惯性权重和时变独立搜索概率改进WOA迭代模型，平衡了算法的全局搜索和局部搜索能力，有效避免了陷入局部最优的问题；引入免疫算法的免疫记忆机制，提高了算法收敛速度；选取了15个基准测试函数进行性能测试，结果表明IWTWOA算法在稳定性、计算精度和收敛速度上均有所提高；最终将其应用在路径规划问题中，获得了较好的结果。

Abstract:

Inorder to improve the slow convergence, low convergence accuracy and easy to fall into local optimality of whale optimization algorithm (WOA), the improved whale optimization algorithm (Immune memory-a Weight-Time varying search factor Improved Whale Optimization Algorithm, IWTWOA) is proposed. The application of nonlinear convergence factors, cooperative inertial weights and time-varying independent search probabilities improves the WOA iterative model, balancing the global exploration and local search capabilities of the algorithm, effectively avoiding the problem of local optimization. The memory mechanism of immune algorithm improve the algorithm convergence speed. Selected 15 test functions for performance testing, the results show that the IWTWOA has improved stability, calculation accuracy and convergence speed. Finally, applied it to the path planning problem, and obtained the better planning.