Paper Title:
Application Research of Kalman Filter and SVM Applied to Condition Monitoring and Fault Diagnosis
  Abstract

In the condition monitoring and fault diagnosis, useful information about the incipient fault features in the measured signal is always corrupted by noise. Fortunately, the Kalman filtering technique can filter the noise effectively, and the impending system fault can be revealed to prevent the system from malfunction. This paper has discussed recent progress of the Kalman filters for the condition monitoring and fault diagnosis. A case study on the rolling bearing condition monitoring and fault diagnosis using Kalman filter and support vector machine (SVM) has been presented. The analysis result showed that the integration of the Kalman filter and SVM was feasible and reliable for the rolling bearing condition monitoring and fault diagnosis and the fault detection rate was over 96.5%.

  Info
Periodical
Chapter
Chapter 1: Materials Science and Engineering
Edited by
Dongye Sun, Wen-Pei Sung and Ran Chen
Pages
268-272
DOI
10.4028/www.scientific.net/AMM.121-126.268
Citation
K. Li, Y. L. Zhang, Z. X. Li, "Application Research of Kalman Filter and SVM Applied to Condition Monitoring and Fault Diagnosis", Applied Mechanics and Materials, Vols. 121-126, pp. 268-272, 2012
Online since
October 2011
Export
Price
$32.00
Share

In order to see related information, you need to Login.

In order to see related information, you need to Login.

Authors: Li Rong Wan, Guang Yu Zhou, Cheng Long Wang, Wen Ming Zhao
Measure Control Technologies and Intelligent Systems
Abstract:By taking full advantage of the technologies of data acquisition, signal analysis and processing and fault diagnosis, this thesis carries out...
1232
Authors: En Gao Peng, Zheng Lin Liu
Mechanics in Tribology and Lubrication Engineering
Abstract:Rolling bearing is extensively used in various areas including shipbuilding, aircraft, mining, manufacturing, agriculture, etc. The...
544
Authors: S.R. Hu, J.K. Zhang, K. Liang, M. Bao
Chapter 6: Instrumentation, Measurement, Monitoring Technologies
Abstract:Traditional research on sensor fault are usually confined to fault space locating, however, it’s very necessary to determine the time that...
820