摘要
应用混沌理论的相空间重构方法,分析了与铁路煤炭运量相关的3组时间序列,分别计算了它们的嵌入延迟时间、嵌入维数、关联维数、最大Lyapunov指数等混沌统计量,并以此为依据判断了3组时间序列的混沌特性.结果显示:煤炭发送增长量和增长率符合混沌特性,煤炭发送量不符合混沌特性.最后,利用最大Lyapunov指数方法和BP神经网络方法对铁路煤炭发送增长量和增长率进行预测.预测结果表明,基于最大Lyapunov指数预测值能够较好地与实际值相吻合,其预测的准确度明显好于BP神经网络预测值.因而用混沌理论中的最大Lyapunov指数在煤炭发送量相关时间序列预测中有广泛的实用价值.
The phase space reconstruction method of chaos theory is used to analyze the three groups of time series associated with railway coal dispatched volume. The embedded time- delay, embedded dimension, correlation dimension and the maximum Lyapunov exponent of each time series are separately calculated. The results are used to judge the chaotic characteristic of time series. The analytical results show as follows： the growth amount and growth rate of railway coal dispatched volume have chaotic characteristics while the coal dispatched volume doesn＇ t. The maximum Lyapunov exponent method and BP neural network are separately used to forecast the growth amount and growth rate of railway coal dispatched volume, The result shows that the predicted data using maximum Lyapunov exponent method is anastomotic with the real data. The maximum Lyapunov exponent method is better than BP neural network in prediction. The maximum Lyapunov exponent prediction of chaos theory has extensive and practical value in railway coal dispatched volume time series prediction.
出处
《交通运输系统工程与信息》
EI
CSCD
北大核心
2013年第6期184-190,共7页
Journal of Transportation Systems Engineering and Information Technology
基金
铁道部科技研究课题(2007X008-G
2008X015-H)
关键词
铁路运输
煤炭发送量时间序列
最大LYAPUNOV指数
混沌判定
相空间重构
railway transportation
railway coal dispatched volume time series
maximum Lyapunovexponent
chaotic judgment
phase space reconstruction
