基于溷沌神经网络模型的水库叶绿素a浓度短期预测.pdf
文本预览下载声明
第32 卷 第3 期 Vol. 32 No.3
第3 期
2009 年3 月 Environmental Science Technology Mar. 2009
基于混沌神经网络模型的水库叶绿素a浓度短期预测
1,2 1 3
罗华军 ,黄应平 ,刘德富
(1.三峡大学化学与生命科学学院,湖北 宜昌 443002 ; 2.武汉大学水利水电学院,湖北 武汉 430072 ;
3.三峡大学土木水电学院,湖北 宜昌 443002)
摘 要:通过混沌理论对水库叶绿素a 浓度时间序列进行分析计算,得到最大Lyapunov 指数为0.0218 (正数),表明该时间序列具有混
沌特性,可进行短期预测。同时,利用相空间重构的方法计算出时间延迟τ 和嵌入维数m,并由此构建了可用于水库叶绿素a 浓度短期预测的
混沌神经网络模型。将该模型对于桥水库的叶绿素a 浓度时间序列进行短期预测,平均预测相对误差为7.85%,取得较为满意的预测效果。该
方法对水库的水环境管理具有一定的参考价值。
关键词:混沌神经网络模型;叶绿素a ;时间序列;预测
中图分类号:X505 文献标志码:A 文章编号:1003-6504(2009)03-0009-04
Chaos Neural Network Model for Short-term Predicting on Time
Series of Reservoir Chlorophyll-a Concentration
1,2 1 3
LUO Hua-jun , HUANG Ying-ping , LIU De-fu
(1.School of Chemistry and Life Science,Three Gorges University ,Yichang 443002 ,China ;
2.School of Water Resource and Hydropower Engineering ,Wuhan University ,Wuhan 430072 ,China ;
3.School of Hydroelectric and Civil Engineering ,Three Gorges University ,Yichang 443002 ,China)
Abstract :Time series of reservoir chlorophyll -a concentration were analyzed and calculated by chaos theory ,with
calculation results of the maximal Lyapunov exponent as 0.0218 for positive number ,which indicated that the time series had
chaos characters and could be short -term predicted. Time delay and embedding dimension were calculated through phase
space reconstruction method ,based on which the chaos neural network model for short-te
显示全部