基于SVM的瓦斯体积分数混沌时间序列预测  

Prediction of gas concentration chaotic time series based on support vector machines

作　　者：刘婷婷[1] 史久根[1,2] 韩江洪[1,2] 

机构地区：[1]合肥工业大学计算机与信息学院,安徽合肥230009 [2]合肥工业大学安全关键工业测控技术教育部工程研究中心,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2009年第8期1150-1153,共4页Journal of Hefei University of Technology：Natural Science

基　　金：863计划引导资助项目(2004AA001210)

摘　　要：文章针对瓦斯体积分数时间序列的非线性和不确定性特征,提出了一种基于SVM的混沌时间序列预测方法。该方法采用改进的最大Lyapunov指数法识别时间序列的混沌特性,通过多次试验选取合适的参数构造SVM预测模型,最后使用优化的预测模型对φ瓦斯的变化趋势进行预测。仿真结果表明,该模型能够较好地解决φ瓦斯时间序列的预测问题,与RBF神经网络模型相比,具有较高的预测精度。According to the features of nonlinearity and uncertainty of gas concentration time series, a chaotic time series prediction method based on support vector machines（SVM ）is proposed. The improved largest Lyapunov exponent algorithm is applied to identify chaotic characteristics of time series. Then appropriate parameters are selected to construct the SVM prediction model through several experiments. Finally, an optimized prediction model is used to predict trends of gas concentration. The results of simulation indicate that compared with the RBF neural network, this model can solve the prediction problem of gas concentration time series more precisely.

关 键 词：混沌时间序列 支持向量机 瓦斯体积分数 预测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] TD712[自动化与计算机技术—计算机科学与技术]