基于改进樽海鞘群算法的船舶避碰决策及仿真实验

Decision-making and Simulation Experiment of Ship Collision Avoidance Based on Improved Sea Squirt Group Algorithm

文中针对多船会遇避碰决策中过渡依赖单一寻优决策的问题采用了加入自适应权重的樽海鞘群优化算法(weight salp swarm algorithm, WSSA),在算法中融入国际海上避碰规则(convention on the international regulations for presenting collisions at sea, COLREGs)和良好船艺的要求.使用速度障碍法判断船舶的碰撞危险度并将多船会遇避让的过程中避让的安全性、经济性以及船舶领域侵入程度作为建立避碰决策的目标函数.算法测试的结果中,WSSA与原始樽海鞘群算法(SSA)以及经典粒子群算法(partide swam optimization, PSO)相比较,WSSA算法在收敛的精度和速度方面都明显优于SSA和PSO算法.结果表明:WSSA在寻找最优碰撞路线的过程中迭代的次数更少,精度更高.

In order to solve the problem that multi-ship collision avoidance decision relies on a single optimization decision,the weight salp swarm algorithm,WSSA)with adaptive weights was adopted.In the algorithm,the convention on the international regulations for presenting collisions at sea(COLREGs)and the requirements of good boating skills were integrated.The speed obstacle method was used to judge the collision risk of ships,and the safety,economy and the degree of ship invasion in the process of collision avoidance were taken as the objective function to establish collision avoidance decision.In the test results of the algorithm,compared with the original sea squirt swarm optimization(SSA)and the classical partide swam optimization,PSO),WSSA is obviously superior to SSA and PSO in convergence accuracy and speed.The results show that WSSA has fewer iterations and higher accuracy in the process of finding the optimal collision route.