首页 | 本学科首页   官方微博 | 高级检索  
     

改进的遗传BP交叉训练算法及其在河流冰情预报中的应用
引用本文:王志兴,李成振,范宝山,陈刚.改进的遗传BP交叉训练算法及其在河流冰情预报中的应用[J].水力发电学报,2010,29(1).
作者姓名:王志兴  李成振  范宝山  陈刚
作者单位:1. 西安理工大学水利水电学院,西安,710048;黑龙江省水利水电勘测设计院,哈尔滨,150080
2. 中水东北勘测设计研究有限责任公司,长春,130061
3. 西安理工大学水利水电学院,西安,710048
基金项目:国家公益性行业专项经费资助项目(200701006)
摘    要:本文在对传统的遗传算法(GA)及BP网络进行一系列改进的基础上,将遗传算法与BP网络进行了有机的结合,提出了一种交叉训练算法.该算法的核心在于将BP网络训练过程划分为若干子步,使遗传进化机制和BP网络训练机制步进交叉进行,来保证网络训练的成功率和快速向全局最优区域逼近的目的.把该算法应用到松花江依兰、佳木斯江段封河、开河日期预报中,取得了良好的效果.

关 键 词:防洪工程  冰情预报  遗传BP算法  交叉训练  封河日期  开河日期

A modified genetic and BP alternately training algorithm and its application to river ice forecasting
WANG Zhixing , LI Chengzhen , FAN Baoshan , CHEN Gang.A modified genetic and BP alternately training algorithm and its application to river ice forecasting[J].Journal of Hydroelectric Engineering,2010,29(1).
Authors:WANG Zhixing  LI Chengzhen  FAN Baoshan  CHEN Gang
Affiliation:WANG Zhixing~(1,3),LI Chengzhen~2,FAN Baoshan~2,CHEN Gang~1(1.The Institute of Water Conservancy , Hydroelectricity of Xi\'an University of Technology,Xi-an,710048,2.China Water Northeastern Investigation,Design , Research Co.,Ltd.Changchun 130061,3.Heilongjiang Provincial Water Conservancy , Hydroelectric Power Investigation,Design , Research Institute,Harbin 150080)
Abstract:This paper puts forward a novel alternately training algorithm that combines the genetic algorithm(GA) with the BP neural network and a series of improvements on the traditional algorithms.The key of this algorithm is to partition a BP training process into several steps,so that GA operation and BP training can be performed alternately step by step,aiming at a final success of the training and a fast convergence toward global optimization.Application of the algorithm to the Yilan and Jiamusi reaches of Song...
Keywords:flood control works  ice forecasting  genetic and BP algorithms  alternately training  freeze-up date  break-up date    
本文献已被 CNKI 万方数据 等数据库收录!
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