| The Beetle Swarm Optimization Algorithm is an emerging intelligent optimization algorithm,it is a hybrid algorithm based on the Beetle Antennae Search algorithm and the Particle Swarm Optimization algorithm,both of which simulate the foraging process of animals in nature.The Beetle Swarm Optimization algorithm is easy to implement,and it has the advantages of less preset parameters,parameter adaptive,and good global search capabilities.However,the algorithm also has some shortcomings,such as insufficient utilization of social information in the population renewal stage,easy to fall into local extremum in the multimodal functions,low optimization accuracy,and lack of diversity of the population.Therefore,this paper makes some modifications based on the original algorithm to improve its optimization performance,and mainly accomplishes the following tasks.1.A K-means clustering beetle swarm optimization algorithm based on weight distribution strategy is proposed.Firstly,this algorithm uses the k-means clustering algorithm and the silhouette coefficient method to divide the population into k optimal clustering subgroups.Then,the optimal individual in each subgroup is selected and their influence weight is allocated according to the corresponding fitness value;Finally,the social learning part of the original algorithm is optimized by a multi-individual joint decision-making method to reduce the impact of the global optimal individual when the population location update.The proposed algorithm is simulated in 15 different benchmark functions and applied to a practical engineering design problem.Experimental results show that the proposed algorithm can be effectively applied to different types of optimization problems,and has better optimization accuracy and stability than the BSO algorithm and three classical optimization algorithms.2.A cloud model beetle swarm optimization algorithm with tent mapping is proposed.Firstly,the tent mapping is used in population initialization to make the initial population evenly distributed in the solution space by generating chaotic random sequences;Then,to make the algorithm have the necessary mutation means,the expectation,entropy,and super entropy of each dimension of the updated population are extracted by the reverse cloud generator algorithm and used on the forward cloud generator algorithm to generate a new beetle population;Finally,the position is further updated through the comparison between the new and old population individuals.The simulation experiment uses 20 benchmark functions including unimodal,multimodal,and fixed-dimensional complex functions to test the exploration and mining capabilities of the algorithm.The results show that the improvement strategy can effectively improve the algorithm's convergence accuracy and population diversity,and make the algorithm have better search performance.3.To balance the accuracy and real-time requirements of satellite navigation and positioning,a Discrete Beetle Swarm Optimization algorithm is proposed to solve the navigation satellite selection problem which is transformed into a combinatorial optimization problem.First,0-1 coding is performed on the initial beetle population,each individual corresponds to a selected combination of satellites,and the Geometric Dilution of Precision(GDOP)is used as the fitness function;Secondly,the roulette wheel selection method is used to convert the continuous vector representing the individual position of the beetle into a 0-1discrete vector,so that individuals could maintain this encoding form during algorithm iterations.Finally,we test the performance of the proposed algorithm under different combined constellation systems and elevation cut-off angles for tracked satellites.The simulation results show that the proposed method has a slight GDOP difference compared with the optimal GDOP method,and when the number of constellations is more than 2 and the elevation cut-off angle is small,it has a lower average time for single satellite selection. |
PDF Full Text Request