多目标差分进化算法的自适应策略分析-控制科学与工程专业论文.docxVIP

II II Abstract Multi-objective optimization problem is a significant area of optimizations, there are a lot of applications in reality have not only one object, even the objects are conflict to each other. Sop can get one optimization solution, but because the conflict between MOP, the decider have to make a tradeoff in the solutions, which is the so-called Pareto optimization solution set. An amount of research works can prove that MOEA are available tools for MOP, draw a lot of attention for researchers. Differential evolution algorithm is one of the most important items in evolutionary algorithms; it has the characters that simple in principle, easy to operate, strong robustness, so it is applied in optimizations broadly. The principle of differential evolution algorithm is making use of the difference between individuals to generate perturbation, which can explore the research space. But if the selection of individual is too stochastic, it may cause premature convergence. Beside of those, the setting of parameters is significant, which can influence the performance of algorithm. Because of this, we make a deep research in the selection of mutation strategy and parameter control when the differential evolution algorithms be applied to multi-objective optimizations, the main work of this paper include two aspects as follow: Operator selection and parameter setting are two important and active fields in the literature of evolutionary algorithms. An adaptive multi-objective differential evolution algorithm with adaptive operator selection and online parameter control is proposed in this section. Firstly, a clustering algorithm based on hierarchical aggregation is proposed to select elitist individuals after the Pareto ranking that using the partial transitivity method; then update the using probability of each strategy according to the credit, and adjust the distribution of parameters in the light of information carried by the reserved individuals simultaneously. Ex