Research And Application Of A Novel Swarm Intelligence Optimization Technique

The optimization problem is a research hot topic in the field of scientific research and engineering practice.In the past decades,the swarm intelligence(SI)optimization algorithms have been used as primary techniques to solve global optimization problems because of its simplicity,flexibility and high efficiency.Classical swarm intelligence optimization algorithms include particle swarm optimization(PSO)algorithm and ant colony evolutionary(ACO)algorithm.On the one hand,these algorithms mainly introduce the randomness in the search process and can effectively avoid local optima.On the other hand,most real engineering problems to be optimized are accompanied with the quite large numbers of local solutions.Therefore,it is of practical importance to employ the swarm intelligence optimization algorithm so as to obtain an optimal solution to the global optimization problem.In this paper,a novel swarm intelligence optimization technique is proposed which called sparrow search algorithm(SSA).The main inspirations of this algorithm are based on foraging behavior and anti-predation behavior in the sparrow population.The sparrow search algorithm is successfully applied to optimize the process of three-dimensional unmanned aerial vehicle(UAV)path planning.The main research contents are as follows:(1)In order to solve the problem of falling into local optimum in traditional optimization methods,we proposed sparrow search algorithm.Specifically,we formulated corresponding rules according to the foraging behavior and anti-predation behavior of the sparrow.Then,the corresponding mathematical models are constructed according to these rules,and the algorithm with global exploration and local exploitation capability in the search space is proposed.(2)In this paper,three sets of simulation experiments are designed to verify the sparrow search algorithm.In the first set of experiments,the simulation results show that the SSA has good convergence speed and exploitation capability for the optimization of the unimodal test functions.In the second set of experiments,the simulation results show that the SSA has global search ability and local optimal avoidance ability for the optimization of the multimodal test functions.In order to more fully test the performance of the SSA,we selected seven fixed-dimensional functions to verify the convergence speed,stability and convergence accuracy of the algorithm.The performance of the SSA is compared with that of the grey wolf optimizer(GWO),gravitational search algorithm(GSA),and particle swarm optimization(PSO).The results demonstrate that the proposed SSA can provide highly competitive results compared with the other state-of-the-art algorithms in terms of searching precision,convergence speed,and stability.(3)In this paper,the sparrow search algorithm is applied to optimize the process of three-dimensional UAV path planning.Firstly,this thesis modeled environments of path planning which included reference terrain,obstacle areas and threat areas.Then,a comprehensive cost evaluation model UAV flight is established,which is used as the objective function,and the optimal route is obtained by the sparrow search algorithm.Finally,simulation results show that this approach is efficient and feasible for the three-dimensional UAV path planning.