The Study Of Improved Grey Wolf Optimizer And Its Application

People are inspired by nature to simulate the behavior of animals,and proposed the swarm intelligence optimization algorithm.The swarm intelligent optimization algorithm has the advantages of simple principle,easy implementation,good optimization performance and strong robustness.It has been rapidly developed in the past decade.This paper mainly studies the grey wolf optimizer,and on this basis,the grey wolf optimizer is improved,and three improved GWO algorithms are proposed,and the application field of the algorithm is further extended.The main research work is as follows:1.A new algorithm that an improved grey wolf optimizer mixed the vertical and horizontal crossover strategy(CSOGWO)is proposed.The good point set method is used to generate a more uniform initial population.In order to better balance the exploration and exploitation of the algorithm,the elliptic equation is used to redesign the control parameters to make them nonlinear;in order to further improve the search ability of the algorithm and make it jump out of the local optimum,vertical and horizontal crossover operator introduced to the method.Finally,comparison of numerical results between the improved grey wolf optimizer and the original algorithm are given to verify the effectiveness of the algorithm.2.A grey wolf optimizer based on diffusion process(SGWO)is proposed.First,in order to ensure that individuals with better information in the population can pass to the next generation as far as possible,a greedy strategy is introduced in the algorithm.Secondly,the diffusion operation is adopted to further improve the exploration of the algorithm,and improve the convergence speed and optimization precision of the algorithm.Finally,comparison of numerical results between the improved grey wolf optimization algorithm and the original algorithm are given.Numerical experiments show,the SGWO algorithm shows good performance on most of the test functions,and the theoretical optimal solution can be found in some test functions,which proves the effectiveness of the improved algorithm.3.A grey wolf optimization algorithm based on the mind of yin-yang pair is proposed(YGWO).In order to balance the exploitation and exploration capabilities of the grey wolf optimization algorithm,firstly,the mind of the yin-yang pair is used to adjust the update strategy of the two wolves with the better fitness value,so as to improve the exploration ability of the algorithm.Secondly,in order to ensure the diversity of the population in the later stage of the algorithm,Reverse learning and updating strategies enable individuals to communicate with each other and explore the search space on a larger scale,thus enhancing the out of local optimal ability of the algorithm.Numerical experiments show that the improved algorithm shows good performance on most of the test functions with the more fast convergence speed and the higher precision,and the Theoretical optimal solution of some test functions can be found.4.The grey wolf optimization algorithm and its improved algorithm are applied to engineering design problems and image enhancement.In solving the engineering problems with constraints,the grey wolf optimization algorithm and its improved algorithm can achieve better results.In the image enhancement application,the optimal parameters of the incomplete Beta function are searched by CSOGWO,SGWO and YGWO algorithms.So the optimal gradation transformation curve is determined,and the image gradation is adjusted to improve the image contrast and enhance the contrast of the image.The experimental results verify the effectiveness of the algorithm.