遗传算法进化设计BP神经网络气象预报建模研究

吴建生; 金龙; 汪灵枝

遗传算法进化设计BP神经网络气象预报建模研究

1.
柳州师范高等专科学校数学与计算机系, 广西, 柳州, 545004
2.
广西气象减灾研究所, 广西, 南宁, 530022

基金项目: 广西科技厅基金项目(0339025)

计量
- 文章访问数: 1010
- HTML全文浏览量: 0
- PDF下载量: 2230
- 被引次数: 0
出版历程
- 收稿日期: 2005-06-06
- 修回日期: 2005-08-16

THE BACK-PROPAGATION NEURAL NETWORK METEOROLOGICAL FORECAST MODEL RESEARCH EVOLVED AND DESIGNED BY GENETIC ALGORITHMS

1.
Department of Mathematics and Computer, Liuzhou Teacher College, Liuzhou 545004, China
2.
Guangxi Research Institute of Meteorological Disasters Mitigation, Nanning 530022, China

摘要

摘要: 利用遗传算法进化设计神经网络的结构和连接权,并针对遗传算法局部调节能力比较弱的问题,采用从进化后的神经网络中用训练样本再次寻优的方法,建立神经网络气象预报模型,该方法克服了神经网络极易陷入局部解和遗传算法局部调节能力比较弱的问题,以广西的月降水量进行实例分析,计算结果表明该方法预报精度高、而且稳定。
- 神经网络 /
- 遗传算法 /
- 预报建模
Abstract: Evolving neural network architectures and connection weights by using genetic algorithms,aiming at the problem of weak local regulation ability with genetic algorithms,and adopting secondary optimum from evolved neural network results by trained samples,this method has established a neural network meteorological forecast model.It can overcome the defects of neural network,namely,falling into local solution network and the problem of weak local regulation ability with genetic algorithms.An applied example is built with monthly mean rainfall across the whole area of Guangxi and calculation results indicate that the method has high and stable forecast accuracy.
- neural network /
- genetic algorithms /
- forecast model

HTML全文

参考文献(17)

[1]	DEAN,ANDREW R,FIEDLER Brian H.Forecasting warm-season burn-off low clouds at the San Francisco international airport using linear regression and a neural network[J].Appl Meteor,2002,41(6):629-639.
[2]	胡江林,涂松柏,冯光柳.基于人工神经网络的暴雨预报方法探索[J].热带气象学报,2003,19(4):422-428.
[3]	王艳娇,张鹰,邓自望,等.RBF神经网络的汛期旱涝预报方法研究[J].热带气象学报,2005,21(1):100-106.
[4]	JIN Long,JU Weimin,MIAO Qilong.Study on Ann-based multi-step prediction model of short-term climatic variation[J].Advances Atmosphere Sciences,2000,17 (1):157-164.
[5]	金龙,况雪源,黄海洪,等.人工神经网络预报模型过拟和研究[J].气象学报,2004,62(1):62-69.
[6]	李祚泳,彭荔红.基于遗传算法的暴雨强度公式参数的优化[J].高原气象,2003,22(6):637-639.
[7]	饶文碧,徐锐,尚钢.基于遗传算法的结构损伤识别[J].武汉理工大学学报,2003,25(7):75-77.
[8]	李发斌,崔鹏,周万村,等.用遗传神经网络分析泥石流活动性[J].中国地质灾害与防治学报,2003,14(3):16-18.
[9]	GALLANT P J,AITKEN J M.Genetic algorithm design of complexity-controlled time-series predictors[C]//Proceedings of the IEEE XⅢ Workshop on Neural Networks for Signal Processing.Toulouse:IEEE NNSP Technical Committee,2003 (Ⅰ):456-462.
[10]	TIAN L,NOORE A.Evolutionary neural network modeling for software cumulative failure time prediction[J].Reliability Engineering and System Safety,2005,87:45-51.
[11]	DE Jong K A.Genetic algorithms:a 25 years perspective[J].Computation Intelligent Systems,1993 (8):539-567.
[12]	王小平,曹立明.遗传算法-理论,应用与软件实现[M].西安:西安交通大学出版社,2002:13-19.
[13]	SIMON Haykin.神经网络原理[M].叶世伟,史忠植译.北京:机械工业出版社,2004:112-121.
[14]	HAGAN Martin T,DEMUTH Howard B,BEALE Mark H.神经网络设计[M].戴葵译.北京:机械工业出版社,2002:49-56.
[15]	董聪.前向网络全局最优化问题研究[J].中国科学基金,1997(1):23-29.
[16]	陈国良,王熙法.遗传算法及其应用[M].北京:人民邮电出版社,1996:40-41.
[17]	HOPFIELD J J.Neural networks and physical systems with emergent collective computation abilities[C].Washington:Proceedings of the National Academy of Science,1982,98(Ⅱ):2554-2558.