摘要
为平衡多目标粒子群的全局和局部搜索能力,提出一种基于高斯混沌变异和精英学习的自适应多目标粒子群算法.首先,提出一种新的种群收敛状态检测方法,自适应调整惯性权重和学习因子的值,以达到探索和开发的最佳平衡.然后,当检测到种群收敛停滞时,采用一种带有高斯函数和混沌特性的变异算子协助种群跳出局部最优,以增强全局搜索能力.最后,外部档案中的精英解相互学习,增强算法的局部搜索能力.在多目标标准测试问题上的仿真结果表明了所提出算法的有效性.
In order to keep the balance between the global and local searching abilities, an adaptive multi-objective particle swarm optimization algorithm based on Gaussian chaotic mutation and elite learning is proposed. Firstly, a method to detect the convergence state is proposed, then the inertia weight and acceleration coefficients are adjusted adaptively. Then, when the swarm is judged to be in the stagnation state, a mutation operator with the features of Gaussian function and chaotic sequence is proposed to help the swarm jump out from local optimum and enhance the global search. Moreover, the elite solutions in the external archive learn with each other to enhance the local search ability. The simulations on several standard test multi-objective problems show the effectiveness of the proposed method.
出处
《控制与决策》
EI
CSCD
北大核心
2016年第8期1372-1378,共7页
Control and Decision
基金
国家重点基础研究发展规划项目(2013CB430403)
国家自然科学基金项目(61374154)
关键词
变异
精英学习
自适应
多目标优化
粒子群
mutation
elite learning
adaptive adjustment
multi-objective optimization
particle swarm optimization