Research On Improvement And Application Of Grasshopper Optimization Algorithm

Grasshopper Optimization Algorithm(GOA)is a new swarm intelligence optimization algorithm that simulates the foraging and aggregation behavior of grasshoppers.At present,GOA has been well applied in mechanical engineering.However,the standard GOA still has problems such as slow global convergence and easy to fall into local optimization.Based on the analysis of the shortcomings of GOA,this paper carried out the research on "improvement and application of grasshopper optimization algorithm",and achieved certain research results.The main research results of this paper are as follows:(1)A grasshopper optimization algorithm based on 4VA pheromone(VAGOA)is proposed.First,based on 4VA being the aggregation pheromone of grasshoppers,the expression of 4VA pheromone is designed;Secondly,different search strategies are adopted for individuals in different grasshopper groups(social grasshoppers and scattered grasshoppers)to achieve a balance between exploration and development,which effectively improves the global exploration ability and local development ability of the algorithm,and enhances the global optimization ability of the algorithm and the ability to avoid falling into local optimization.Finally,VAGOA is used in function optimization and PID control parameter optimization.The experimental results show that the algorithm has a strong ability to solve problems compared with other optimization algorithms.(2)A grasshopper optimization algorithm(VSSGOA)using various search strategies is proposed.First,according to the dynamic probability,different search strategies are selected to update the position of grasshoppers to increase the diversity of the population and improve the search ability of the algorithm.Secondly,nonlinear weights are introduced to balance the global and local search ability of the algorithm.At the same time,the local development ability of the algorithm is enhanced by increasing the search carried out by the grasshopper population near the target location.Finally,Levy flight strategy is introduced to make the grasshopper population walk randomly at the later stage of the iteration to avoid the algorithm falling into local optimization.Moreover,VSSGOA is utilized in real-world engineering applications and function improvement.The experimental findings demonstrate that VSSGOA outperforms other optimization methods in terms of performance.(3)The proposed VSSGOA is used to train multi-layer perceptron(MLP)and five standard UCI datasets are selected for testing and training.The experimental results show that VSSGOA training multi-layer perceptron has higher classification accuracy in solving the classification problem of UCI datasets compared with other optimization algorithms.