基于bp神经网络的混沌时间序列预测模型研究-计算机应用技术专业论文.docxVIP

ABSTRACTThere ABSTRACT There is no denying the fact that the method ofpredicting the future based On historical data is commonly used in science，economies and engineering．Time Series Forecasting，which constructs time series model on the basis of laistorical data and then uses the model to forecast the future。is缸important research direction in forecasting research area．As far缌astronomy。hydrology and meteorologieal phenomena arc concerned，many time series such as sun．spots。amount ofrunoff,rain蹦l amount were discovered all including the chaotic character in recent years．In the face of the chaotic time series 1argely existed in nature and social economic phenomena,the waditional method of statistical analysis performed badly．Neural Network(№D posesses excellent non-linear character,wlaich enables it to be extremely suitable to the forecasting research in chaotic array．Based on artificial neural network and chaotic theory，the forecasting research has become research hot spot and received special attention at present．This dissertation has done systematic and thorough research on the above mentioned problem． Firstly,this dissertatio-has made an simple introduction to the concept and distinction method of ehaode time series．In addition,this dissertation has introduced lorenz model and summarized several fundamental method about time series elaaos recognition． And then，this dissertation has introduced the foundation of chaotic time series：the phase space restructuring theory,namely the time series having chaotic character is rebuilded into OIIC kind of low nonlinear dynamics system．Phaso space restructuring∞n find out tlac law concealing in evolution in chaotic attractor．cllus髓the nOW availablc data to be integrated into the frame describing that kind，and provides a new method for the time series research．During the period of restructuring phase spaeo,the appropriate delay time and the embedding dimension selection are a11．important．硼1e main bodv of this dissertation is e