摘要
为了提高粒子群优化算法中粒子搜索最优解的效率,该文在标准粒子群优化算法的基础上,提出一种改进的粒子群优化算法。该方法通过对粒子飞行轨迹的分析,对种群中每个粒子构建了评价粒子性能差异的等级标准,并对认识系数和社会系数设计了对应的动态变化系数模型。通过引入迁徙策略,使迁徙行为随机生成的新粒子更有可能接近全局最优解,更加有利于群体搜索跳出局部最优解和寻找全局最优解。实验结果表明,与其他比较算法相比,该文提出的改进粒子群优化算法具有寻优能力强和搜索精度高等优点,测试准测上的实验数据验证了改进算法的有效性和可行性。
To improve the efficiency of the particle swarm optimization algorithm for particles searching optimal solutions,an improved particle swarm optimization( IPSO) algorithm is proposed based on the standard PSO. Each particle has a corresponding grading standard by trajectory analysis of flight path,and two dynamic models of coefficients are designed for the cognitive coefficient and social one,respectively. In addition,through the introduction of the migration strategy,the newly obtained particles are more likely closer to the global optimal solution to a certain extent,and it is easy to jump out of the local optimal solution to search for the optimal solution. Simulation results show the IPSO algorithm has powerful optimizing ability and higher search veracity. The experimental data on the test criterion verify the effectiveness and the feasibility of the improved algorithm.
出处
《南京理工大学学报》
CAS
CSCD
北大核心
2015年第4期386-391,共6页
Journal of Nanjing University of Science and Technology
基金
国家自然科学基金(61202313,51362016)
江苏省博士后科研资助计划(1402019C)
江西省自然科学基金(2012BAB201044)
高维信息智能感知与系统教育部重点实验室开放课题资助课题(JYB201507)
关键词
粒子群优化
优化策略
优化问题
粒子搜索
认识系数
社会系数
particle swarm optimization
optimization strategies
optimization problems
particles searching
cognitive coefficients
social coefficients
