|Table of Contents|

Sensor Fault Diagnosis Based on Wavelet Packet and Support Vector Machines

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

Issue:
2008年05期
Page:
609-614
Research Field:
Publishing date:

Info

Title:
Sensor Fault Diagnosis Based on Wavelet Packet and Support Vector Machines
Author(s):
FENG Zhi-gang1WANG Qi1XU Tao2SHIDA Katsunori1
1.School of Electrical Engineering and Automation,Harbin Institute of Technology,Harbin 150001,China;2.Department of Automation,Shenyang Institute of Aeronautical Engineering,Shenyang 110136,China
Keywords:
wavelet packet support vector machines feature extraction sensor fault diagnosis
PACS:
TH812
DOI:
-
Abstract:
To solve the fault diagnosis problem of self-validating pressure sensor,a sensor fault diagnosis approach based on wavelet packet transform and support vector machines is proposed.After a three-level decomposition of wavelet packet,the coefficients of each node are achieved.With some cutting algorithm,the reconstructed signals with fault character are strengthened.The energy of each node is calculated with reconstructed signals,and the average cutting ratios of all nodes are regarded as the feature vector.The support vector machines for multi-classification used as fault classifiers are established to identify the condition and fault pattern of the sensor.The results of fault diagnosis on self-validating pressure sensors,temperature and flow sensor show that the proposed approach can be applied to the sensor fault diagnosis effectively.

References:

[1] Zhang J ianqiu, Yan Yong. A wavelet2based app roach to abrup t fault detection and diagnosis of sensor [ J ]. IEEE Transactions on Instrumentation and Measure2 ment, 2001, 50 (5) : 1 389 - 1 396.
[2] 徐涛,王祁. 基于小波包神经网络的传感器故障诊 断方法[ J ]. 传感技术学报, 2006, 19 ( 4) : 1 060 - 1 064.
[3] 雷亚国,何正嘉,訾艳阳,等. 基于特征评估和神经 网络的机械故障诊断模型[ J ]. 西安交通大学学 报, 2006, 40 (6) : 558 - 562.
[4] Vapnik V. The nature of statistics learning theory [M ]. New York: Sp ringerVerlag, 1995. 40 - 50.
[5] Vapnik V. Statistical learning theory[M ]. New York: JohnWiley and Sons, 1998. 102 - 110.
[6] 于德介,陈森峰,程军圣,等. 一种基于经验模式分 解与支持向量机的转子故障诊断方法[ J ]. 中国电 机工程学报, 2006, 26 (16) : 162 - 167.
[7] 程军圣,于德介,杨宇. 基于内禀模态奇异值分解 和支持向量机的故障诊断方法[ J ]. 自动化学报, 2006, 32 (3) : 476 - 480.
[8] 宋乃华,邢清华. 基于支持向量机的空中目标大类 别分类[ J ]. 系统工程与电子技术, 2006, 28 ( 8) : 1 279 - 1 281.
[9] Zhao Q, Principe J C. Support vector machines for SAR automatic target recognition [ J ]. IEEE Transac2 tions on Aerospace and Electronic Systems, 2001, 37 (2) : 643 - 654.
[10] 吴丹,顾学迈. 一种新的基于支持向量机的自动调 制识别方案[ J ]. 南京理工大学学报(自然科学 版) , 2006, (30) 5: 569 - 573.
[11] 赵晖,荣莉莉,李晓. 一种设计层次支持向量机多 类分类器的新方法[ J ]. 计算机应用研究, 2006, 6: 34 - 37.

Memo

Memo:
-
Last Update: 2012-12-19