Chaotic Parallel Support Vector Machine and its application for fault diagnosis of hydraulic pump

Author

Zili Wang ; Zhipeng Wang

Author_Institution

Sch. of Reliability & Syst. Eng., Beihang Univ., Beijing, China

fYear

2013

fDate

24-27 June 2013

Firstpage

1

Lastpage

6

Abstract

Hydraulic pump is the critical part of a hydraulic system. The diagnosis of hydraulic pump is very crucial for reliability. This paper studies on a Chaotic Parallel Support Vector Machine (CPSVM) and employs it for fault diagnosis of hydraulic pump. The CPSVM combines the chaos theory and a number of SVMs connected in parallel. Phase-space reconstruction of chaos theory is utilized to determine the dimension of input vectors for each SVM. Each SVM has an output. A weighted sum of each output is considered as the output of the CPSVM. To diagnose faults of hydraulic pump, a residual error generator is designed based on the CPSVM. This residual error generator is firstly trained using data from normal state. Then, it can be used for fault clustering by analysis of the residual error. Its performance and effectiveness has also been validated via a plunger pump test-bed.

Keywords

condition monitoring; fault diagnosis; hydraulic systems; mechanical engineering computing; pumps; reliability; support vector machines; CPSVM; chaos theory; chaotic parallel support vector machine; fault clustering; fault diagnosis; hydraulic pumps; phase space reconstruction; reliability; residual error generator; Chaos; Generators; Kernel; Reliability; Time series analysis; Chaotic Parallel Support Vector Machine; fault diagnosis; hydraulic pump; residual error generator;

fLanguage

English

Publisher

ieee

Conference_Titel

Prognostics and Health Management (PHM), 2013 IEEE Conference on

Conference_Location

Gaithersburg, MD

Print_ISBN

978-1-4673-5722-7

Type

conf

DOI

10.1109/ICPHM.2013.6621455

Filename

6621455