论文部分内容阅读
混沌时间序列预测是混沌理论的一个重要应用领域和研究热点,目前它在信号处理、自动化控制等领域中已得到了广泛的应用。本文联系支持向量机(SVM)和混沌时间序列预测的相关理论,建立基于二者的变形序列预测模型。同时,结合具体实例从变形时间序列的混沌识别、相空间重构以及预测模型的参数优化等方面探讨了模型的具体建立过程。实验结果表明,该模型的预测精度要优于BP神经网络。
Chaotic time series prediction is an important application field and research hotspot of chaos theory. At present, it has been widely used in the fields of signal processing and automation control. In this paper, the correlation theory between support vector machine (SVM) and chaotic time series prediction is established, and the deformation sequence prediction model based on the two is established. At the same time, the concrete construction process of the model is discussed in terms of the chaotic identification of deformation time series, the reconstruction of phase space and the optimization of the parameters of prediction model. Experimental results show that the prediction accuracy of the model is better than BP neural network.