Application Research Of Hybrid PSO Algorithm In Multi-objective Ship Collision Avoidance Decision-making

Ship collision avoidance decision-making as a key technology to realize unmanned and intelligent ships,and it has been paid more and more attention by experts and scholars at home and abroad.Reasonable and effective decision-making for collision avoidance can not only reduce the mistakes caused by the officers due to the heavy workload,but also help to improve the safety and economy of the ship collision avoidance.In this thesis,hybrid PSO Algorithm based on Gaussian Mutation are used to make decisions on ship collision avoidance in open waters.The main research contents are as follows:(1)Introduce the relevant theories of ship collision avoidance decision-making,divide and explain in detail of the process of ship collision avoidance decision-making,and analyze the encounter situation between the ship and the target ship according to the International Regulations for Preventing Collisions at Sea(hereinafter referred to as the “Rules”).Make detailed divisions,and take corresponding collision avoidance actions for target ships in different directions and distances.By constructing the membership functions of DCPA,TCPA,relative distance,relative bearing,and ship speed ratio,the ship collision risk model is established by the fuzzy comprehensive evaluation method.Finally,the collision avoidance method of multi-target ships is explained.(2)The basic principle and mathematical model of the PSO algorithm are described in detail.Aiming at the limitation that the PSO algorithm is easy to fall into the local optimum in the later stage of iteration,the inertia weight is improved by using the adaptive strategy,and the concept of Gaussian position mutation is introduced,and the hybrid PSO algorithm based on Gaussian mutation is proposed.(3)The objective functions is designed with the collision risk,and voyage loss,as the goal,the steering range,the avoidance responsibility and collision avoidance timing as the constraints.According to the importance of the objective functions in the process of ship collision avoidance,different weights are given to them.Therefore,the objective function of ship collision avoidance decision-making is constructed.And use the hybrid PSO algorithm to optimize them and get the optimal decision.(4)In this thesis,the MATLAB 2020 a platform is used to conduct simulation experiments.The experiments are carried out in open water and do not consider the influence of hydrometeorological factors.Firstly,the two-ship collision avoidance simulation experiment is carried out for three classic encounter situations(encounter,crossing,and overtaking),and the optimization effects of the standard PSO algorithm and the hybrid PSO algorithm are compared.The simulation results show that the hybrid PSO algorithm has better optimization effect in terms of excellent accuracy,safety and economy of collision avoidance.Then,the hybrid PSO algorithm was applied to multi-vessel collision avoidance.The simulation results show that the hybrid PSO algorithm can effectively optimize the multi-ship collision avoidance problems and realize the automatic collision avoidance between the own ship and multiple target ships.In this thesis,the method of fuzzy comprehensive evaluation is used to construct a ship collision risk model.Secondly,in view of the limitation that the PSO algorithm is easy to fall into the local optimum in the later iteration,the PSO algorithm is improved,and a hybrid PSO algorithm based on Gaussian mutation is proposed.,which improves the convergence speed and accuracy of the algorithm.Finally,the multi-objective optimization method is used to construct the ship collision avoidance objective functions,and the hybrid PSO algorithm based on Gaussian mutation is used to optimize the collision avoidance objective functions,so as to the multi-objective ships collision avoidance decision in open water can be realized.