Research And Application Of Immune Multi-objective Optimization Algorithm

The multi-objective optimization problem is one of the research hotspots in the field of evolutionary computation.The artificial immune system is an intelligent system developed from the principles and mechanisms of biological immunity.The introduction of artificial immune systems into multi-obj ective evolutionary algorithms has become a potential research direction in multi-objective optimization.This paper mainly studies three improved immune multi-objective evolutionaryalgorithms and applies them to practical problems.The details are as follows:1.Aiming at the defect of poor distribution of immunune multi-objective evolutionary algorithms,an immune multi-objective evolutionary algorithm based on adaptive grid method is proposed.The basic idea is to use the adaptive grid method to improve the diversity of antibody populations after immunocloning,immune gene and clonal selection of antibody populations.The simulation results and statistical indicators show that the improved algorithm has a certain degree of improvement in the distribution of the solution compared with the conventional immune multi-objective evolutionary algorithm.2.It is very difficult to find all Pareto optimal front ends accurately when solving some complex multi-objective optimization problems.In order to better solve this problem,based on the previous research work,a dual evolution model immune multi-objective evolution algorithm is presented.There are two evolutionary modules in the algorithm,the purpose is to improve the convergence speed of the algorithm and the diversity of the population.The first module independently optimizes each sub-goal by using sub-populations composed of competing individuals.Different evolutionary intersections are used in this module to optimize the corresponding objective function.The second module uses an adaptive network immune multi-objective evolution algorithm to optimize all targets simultaneously through cloning,selection,and so on.The standard test function is selected to test the performance of the new algorithm and compared with other algorithms to verify the effectiveness of the new algorithm.3.Aiming at the shortcomings of basic immune multi-objective evolutionary algorithm,such as easy precocity and poor local search ability,the multi-objective evolutionary algorithm of multi-border immunity was applied to the optimization of drone patrol path.The basic idea is to introduce a crowd-out mechanism in the selection operator based on the sharing of fitness values,use interval crossing in the crossover operator,and use the least-compatibility individual replacement technique among the most similar individuals.Numerical experiments show that multi-objective evolutionary multi-objective evolutionary algorithm can greatly improve the diversity of the population,avoid premature maturity to a certain extent,and obtain a better patrol path than the basic immune multi-objective evolutionary algorithm.Figure[27]table[2]reference[54]...