|
|
论文:2012,Vol:30,Issue(4):607-611 |
|
|
引用本文: |
|
|
郭阳明, 蔡小斌, 付琳娟, 马捷中. 基于回声状态网络的飞机混沌时间序列预测模型[J]. 西北工业大学 |
|
|
Guo Yangming, Cai Xiaobin, Fu Linjuan, Ma Jiezhong. An Effective Prediction Model for Aircraft Chaos Time Series Based on Echo State Networks(ESN)[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
基于回声状态网络的飞机混沌时间序列预测模型 |
|
郭阳明1, 蔡小斌1,2, 付琳娟1, 马捷中1 |
|
1. 西北工业大学 计算机学院,陕西 西安 710072; 2. 中航工业科技委, 北京 100012 |
摘要: |
准确检测飞机即将发生的故障或预测其状态的变化趋势,对于实现飞行安全具有重要意义。文章针对传统基于回声状态网络在故障预测中的不足,构建了基于小波降噪的回声状态网络预测模型。该模型保留了非线性时间序列回声状态网络预测的优势,并采取小波变换对混沌时间序列进行降噪预处理,有效提高了含噪混沌时间序列的预测精度。论文通过对某飞机发动机滑油散热器温度时间序列数据序列进行预测分析,表明文中模型具有较好的预测精度,验证了模型的有效性。 |
关键词:
小波变换
回声状态网络
非线性混沌时间序列
故障预测
|
|
An Effective Prediction Model for Aircraft Chaos Time Series Based on Echo State Networks(ESN) |
|
Guo Yangming1, Cai Xiaobin1,2, Fu Linjuan1, Ma Jiezhong1 |
|
1. Department of Computer Science and Engineering, Northwestern Polytechnical University, Xi'an 710072, China; 2. Science and Technology Commission of AVIC, Beijing 100012, China |
Abstract: |
It is significant for flight safety to accurately detect the coming fault of aircraft or predict its changetrend. Aiming at suppressing the shortcoming of fault prediction based on traditional ESN, we present a new predic-tion method combining ESN with wavelet denoising. Sections 1 and 2 of the full paper explain our prediction modelmentioned in the title,which we believe is effective and whose core is: the method not only reserves the advantagesof ESN model in nonlinear time series prediction but also reduces the noise influence in practice,i. e. ,the pre-treatment via wavelet transform will be done before prediction. Section 3 concerns a certain type of aero-engine lu-bricator. Its simulation results are presented in Figs. 4, 5, 7, 8 and Tables 1 and 2. The simulation results and theiranalysis show preliminarily that the proposed method improves the prediction accuracy of nonlinear chaotic time se-ries including noises,thus indicating that the proposed model is an effective approach in actual application. |
Key words:
aircraft
efficiency
errors
mathematical models
noise abatement
wavelet transforms;echo statenetworks(ESN)
nonlinear time series
prediction
|
|
收稿日期: 2011-09-08
修回日期:
|
DOI: |
基金项目: 国家重点基础研究发展计划(973计划);国家自然科学基金(61001023、61101004);航空科学基金(2010ZD53039);陕西省自然科学基金(2010JQ8005)资助 |
通讯作者:
Email: |
作者简介: 阳明(1978-),西北工业大学副教授,主要从事可靠性工程与理论、综合测试与诊断及测控系统集成研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] 陈 铿, 韩伯棠. 混沌时间序列分析中的相空间重构技术综述. 计算机科学, 2005, 32(4):67-70Chen Keng,Han Botang. A Survey of State Space Reconstruction of Chaotic Time Series Analysis. Computer Science, 2005, 32(4):67-70 (in Chinese) [2] Jaeger H. The Echo State Approach to Analyzing and Training Recurrent Networks. German National Research Center for Infor-mation Technology,Tech Rep 148, 2001 [3] 韩 敏. 混沌时间序列预测理论与方法. 北京:中国水利水电出版社, 2007Han Min. Prediction Theory and Method of Chaotic Time Series. Beijing: China Water Power Press, 2007 (in Chinese) [4] 陆振波, 蔡志明, 姜可宇. 基于改进的 C-C 方法的相空间重构参数选择. 系统仿真学报, 2007, 19(11):2527-2529, 2538Lu Zhenbo,Cai Zhiming,Jiang Keyu. Determination of Embedding Parameters for Phase Space Reconstruction Based on Im-proved C-C Method. Journal of System Simulation, 2007, 19(11):2527-2529, 2538 (in Chinese) [5] Rosenstein M T,Collins J J,De Luca C J. Reconstruction Expansion as a Geometry Based Framework for Choosing Proper De-lay Time. Physica D, 1994, 74: 82-98 [6] Mallat S,Huang W. Singularity Detection and Processing with Wavelets. IEEE Trans on Information Theory,1992,38(2):617-643 [7] 雷正伟, 徐章遂, 米 东, 刘美全. 神经网络的预测性能的优化分析. 计算机测量与控制, 2004, 12(1):15-16Lei Zhengwei,Xu Zhangsui, Mi Dong, Liu Meiquan. Optimization Analysis of Neural Networks Forecast Performance. ComputerMeasurement and Control, 2004, 12(1):15-16 (in Chinese) [8] 郭阳明, 翟正军, 姜红梅. 基于新息的多参量混沌时间序列 LS-SVR 加权预测. 西北工业大学学报, 2009, 27(1):83-86Guo Yangming,Zhai Zhengjun,Jiang Hongmei. Weighted Prediction of Multi-Parameter Chaotic Time Series Using LeastSquares Support Vector Regression (LS-SVR). Journal of Northwestern Polytechnical University, 2009, 27(1):83-86 (in Chinese) |
|
|
|
|
|
|
|