Study on the Prediction Method of Low-Dimension Time Series That Arise From the Intrinsic Nonlinear Dynamics
-
摘要: 主要研究由低维混沌时序所确定的非线性动力系统的预测方法及其应用。在国外学者研究工作的基础上,应用一种非线性混沌模型在相空间内对时序进行重构工作,先通过改进的最小二乘方法来估计模型的参数,满足一定精度后,再采用最优化方法来估计模型的参数,并用所求得的混沌时序模型在其相空间内对时序的未来值进行预测。给出了非常有代表性的实例对文中模型和算法进行验证。结果发现采用该算法能较准确地求得模型的参数,在相空间中对混沌时序进行预测,将传统方法中的外推变成了相空间中的内插,及选取最佳的模型阶数等工作都能增加预测的准确程度,且混沌时序不可能进行长期的预测。Abstract: The prediction methods and its applications of the nonlinear dynamic systems determined from chaotic time series of low dimension are discussed mainly.Based on the work of the foreign researchers,the chaotic time series in the phase space adopting one kind of nonlinear chaotic model were reconstructed.At first,the model parameters were estimated by using the improved least square method.Then as the precision was satisfied,the optimization method was used to estimate these parameters.At the end by using the obtained chaotic model,the future data of the chaotic time series in the phase space was predicted.Some representative experimental examples were analyzed to testify the models and the algorithms developed in this paper.The results show that if the algorithms developed here are adopted,the parameters of the corresponding chaotic model will be easily calculated well and true.Predictions of chaotic series in phase space make the traditional methods change from outer iteration to interpolations.And if the optimal model rank is chosen,the prediction precision will increase notably.Long term superior predictability of nonlinear chaotic models is proved to be irrational and unreasonable.
-
Key words:
- nonlinear /
- chaotic model /
- parameter identification /
- time series prediction
-
[1] ZHANG Qing-hua.Wavelet networks[J].IEE Transaction on Neural Networks,1992,6(11):889-898. [2] CAO Liang-yue,HONG Yi-guang,FANG Hai-ping,et al.Predicting chaotic timeseries with wavelet networks[J].Phys D,1995,85(6):225-238. [3] Casdagli Martin.Nonlinear prediction of chaotic time series[J].Phys D,1989,35(11):335-356. [4] Davies M E.Reconstructing attractors from filtered timeseries[J].Phys D,1997,101(5):195-206. [5] Potapov Alexei.Distortions of reconstruction for chaotic attractors[J].Phys D,1997,101(8):207-226. [6] Abarbanel Henry D I,Brown Reggie,Kadtke James B.Prediction and system identification in chaotic nonlinear systems:time series with broadband spectra[J].Phys Lett A,1989,138(8):401-407. [7] 马军海,陈予恕,刘曾荣.动力系统实测数据的非线性混沌特性的判定[J].应用数学和力学,1998,19(6):481-488. [8] 马军海.混沌时序动力系统非线性重构[D].天津:天津大学力学系,1997. [9] Diambra L,Plastino A.Modeling time series using information theory[J].Phys Lett A,1996,216(12):278-236. [10] Judd Kevin,Mees Alistair.Modeling chaotic motions of a string from experimental data[J].Phys D,1996,92(10):221-236. [11] McGuire Gary,Azar Nabeel B,Shelhamer Mark.Recurrence matrices and the preservation of dynamical properties[J].Phys Lett A,1997,237(8):43-47. [12] Schroer Christian G,Sauer Tim,Ott Edvard,et al.Predicting chaotic most of the time from embeddings with self-intersections[J].Phys Rev Lett,1998,80(7):1410-1412. [13] Castillo E,Gutierrez J M.Nonlinear time series modeling and prediction using functional networks extracting information masked by chaos[J].Phys Lett A,1998,244(8):71-84. [14] Judd Kevin,Mees Alistair.Embedding as a modeling problem[J].Phys D,1998,120(7):273-286. [15] Kugiumtzis D,Lingjxrde O C,Christophersen N.Regularized local linear prediction of chaotic time series[J].Phys D,1998,112(4):344-360. [16] Abarbanel Henry D I,Brown Reggie,Kadtke James B.Prediction in chaotic nonlinear system:methods for time series with broadband Fourier spectra[J].Phys Rev A,1990,41(4):1782-1807. [17] CHEN Yu-shu,MA Jun-hai,LIU Zeng-rong.The state space reconstruction technology of different kinds of chaotic data obtained from dynamical system[J].Acta Mechanica Sinica,1999,15(1):82-92. [18] Chen C H.Applied Timeseries Analysis[M].Beijing:World Scientific Publishing Cor,1989. [19] YANG Shu-zi,WU Ya.Applied Timeseries Analysis in Engineering[M].Beijing:World Scientific Publishing Cor,1992.
点击查看大图
计量
- 文章访问数: 2409
- HTML全文浏览量: 49
- PDF下载量: 700
- 被引次数: 0