基于聚类和支持向量机的非线性时间序列故障预报

被引:23
作者
张军峰
胡寿松
机构
[1] 南京航空航天大学自动化学院
关键词
故障预报; K-均值聚类; 支持向量回归; 时间序列预测;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
针对非线性时间序列故障预报问题,提出了一种基于聚类和支持向量机的方法.将正常的时间序列按照K-均值聚类算法进行聚类学习,同时利用支持向量机回归的时间序列预测算法获得预测序列,然后通过比较聚类所得的正常原型和预测序列的相似性实现故障预报.仿真结果表明:本文提出的方法更能满足实时性的要求,也更为准确.
引用
收藏
页码:64 / 68
页数:5
相关论文
共 9 条
[1]  
Linear dependency betweenεand the input noise inε-support vector regression. JAMES T K,IVOR W T. IEEE ACM Transactions on Networking . 2003
[2]  
Using support vector machines for time series prediction. THISSENA U,BRAKELA R, et al. Chemometrics & Intelligent Laboratory Systems . 2003
[3]  
The use of ARIMA models for reliability forecasting and analysis. HO S L,,XIE M. Computers and Industrial Engineering . 1998
[4]  
Pattern Classification. RICHARD O D,PETER E H,DAVID G S. . 2002
[5]  
Data clustering: a review. JAIN A K,MURTY M N. ACM Computing Surveys . 1999
[6]  
Statistical Learning Theory. VAPNIK V N. . 1998
[7]  
The Nature of Statistical Learning Theory. VAPNIK V N. . 1995
[8]  
Prediction of machine deterioration using vibration based fault trends and recurrent neural networks. TSE P W,ATHERTON D P. J of Vibration & Acoustics . 1999
[9]  
Support vector machines for dynamic reconstruction of a chaotic system[C]/. MATTERA D,HAYKIN S. Advances in Kernel Methods-Support Vector Learning . 1999