首页 | 官方网站   微博 | 高级检索  
     

一种自适应粒子群算法的小波神经网络优化
引用本文:刘志勇,王小红.一种自适应粒子群算法的小波神经网络优化[J].机械与电子,2021,39(8):8-12.
作者姓名:刘志勇  王小红
作者单位:1. 咸阳职业技术学院,陕西 咸阳 712000 ;?2. 陕西省委党校,陕西 西安 710061?
摘    要:针对传统粒子群算法易陷入局部最优解的问题,提出了一种变权重粒子群算法.该算法通过引入交叉权重因子和粒子个体状态最优权值,对传统粒子群算法进行了优化,使粒子在移动过程中利用更多的信息来调整各自的移动方向,扩大粒子在运动过程中的自我认知范围,提高了粒子群算法的收敛精度和收敛速度.最后,利用改进的变权重粒子群算法对小波神经网络控制器进行优化,有效地验证了变权重粒子群算法的精确性.

关 键 词:变权重  粒子群算法  全局最优  小波神经网络

A Wavelet Neural Network Optimization Method Based on Variable-Weight Particle Swarm Optimization
LIU Zhiyong,WANG Xiaohong.A Wavelet Neural Network Optimization Method Based on Variable-Weight Particle Swarm Optimization[J].Machinery & Electronics,2021,39(8):8-12.
Authors:LIU Zhiyong  WANG Xiaohong
Affiliation:(1.Xianyang Vocational and Technical College , Xianyang 712000 , China ;2. Shaanxi Provincial Party School of the CPC , Xi ’ an 710061 , China )
Abstract:A variable-weight particle swarm optimization ( VWPSO ) algorithm is proposed to overcome the shortcoming of the traditional particle swarm optimization ( PSO ) algorithm , which is easy to fall into the local optimal solution. In the proposed strategy , the weight factor and the optimal weight of individual state are in troduced to adjust the moving direction of the particles via the more information , and the self-awareness range of particles in the process of motion is expanded.Moreover , the convergence accuracy and convergence speed of particle swarm optimization algorithm are improved.Finally , the VWPSO algorithm is used to optimize the wavelet neural network controller , which verifies the accuracy of the VWPSO algorithm effectively.
Keywords:variable-weight  particle swarm optimization  global optimum  wavelet neural network
本文献已被 CNKI 万方数据 等数据库收录!
点击此处可从《机械与电子》浏览原始摘要信息
点击此处可从《机械与电子》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号