FEATURE EXTRACTION, OPTIMIZATION AND CLASSIFICATION BY SECOND GENERATION WAVELET AND SUPPORT VECTOR MACHINE FOR FAULT DIAGNOSIS OF WATER HYDRAULIC POWER SYSTEM

Authors

  • Han Xin Chen School of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798
  • Patrick S. K. Chua School of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798
  • Geok Hian Lim School of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798

Keywords:

Fault diagnosis, Support vector machine, Water hydraulic system, Feature extraction, Wavelet transform, Neural network

Abstract

The work described in this paper investigates the fault diagnosis of water hydraulic motor by the optimization and automatic classification of the feature values. The second generation wavelet for the vibration signals analysis of the water hydraulic motor was proposed to extract the feature values. The new optimization method by bi-classification support vector machine (SVM) was proposed to select the optimal feature values based on a rank criterion and the algorithm was developed here. In order to classify the conditions of the pistons used in the hydraulic motor, a two-level structure based on the multi-classification was developed in this work. The multi-classification method of SVM for the fault diagnosis of a piston crack was investigated. The winner-takes-all scheme was studied. The results of the classification were found to be successful.

Downloads

Download data is not yet available.

Author Biographies

Han Xin Chen, School of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798

H. X. Chen He received the M. Eng. degree in the School of Mechanical Science and Technology, Huazhong University of Science & Technology, China. He currently finish oral defence of Ph.D. student and will be conferred PHD degree in Feb, 2006 at Nanyang Technological University, Singapore. His main research areas are in condition monitoring and fault diagnosis, signal processing, pattern recognition and its application to fluid power systems.

Patrick S. K. Chua, School of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798

Patrick S.K. Chua (Dr.) He worked as an assistant technical manager in a woodworking and machine tool company before joining National Semiconductor as lead R & D engineer and subsequently as R & D manager before joining Nanyang Technological University (NTU)as a lecturer. Presently as an Associate Professor at NTU, Singapore, his research interests are in the areas of fluid power technology, automated assembly, condition monitoring and biomedical engineering.

Geok Hian Lim, School of Mechanical and Aerospace Engineering, Nanyang Technological University, 50 Nanyang Avenue, Singapore 639798

Lim Geok Hian (Dr.) He is currently an Associate Professor at Nanyang Technological University, Singapore. His research interests are in the areas of mechanical vibration, condition monitoring and fluid power analysis. Prior to joining NTU, he had research experience at Sperry Vickers, IMI Norgren and British Gas, U.K. He received his Ph.D. from Aston University, U.K. and the B.Sc (Eng) and M. Eng. degrees from Imperial College of Science Technology and Medicine, London University.,

References

Burges, C. J. C., 1998. A tutorial on support vector

machines for pattern recognition, Data Mining and

Knowledge Discovery 2, pp. 955-974.

Chen, H. X., Chua, Patrick. S. K., and Lim, G. H.,

Dynamic Vibration Analysis of A Swashplate

Type Water Hydraulic Motor, Mechanism and

Machine Theory, V41, n5, pp. 487-504.

Crowther, W. J., Edge, K. A., Burrows, C. R., Atkinson,

R. M., and Woollons, D. J., 1998. Fault diagnosis

of a hydraulic actuator circuit using neural networks,

an output vector space classification approach,

Proceedings of the I MECH E Part I Journal

of Systems & Control Engineering 212, pp.57 - 68.Daley, S. and Wang, H. 1996. Fault diagnosis in fluid

power systems, Engineering Simulation, 13(6),

pp.993-1008.

Danfoss, Inc.

http://www.danfoss.com/Nessie/Introduction/index.

asp, Denmark.

Daubechies, I. and Sweldens, W. 1998. Factoring

wavelet transforms into lifting steps, Journal of

Fourier Analysis and Application, pp. 41-44.

Goldberg, G. E. 1999. Genetic Algorithms in Search,

Optimization and Machine Learning, Addison-

Wesley, NY, USA.

Gunn, S. R. 1998. Support vector machines for classification

and regression, Technical report, University

of Southampton, Department of Electrical and

Computer Science.

Haney, L., Precetti, C., Gibson, H., Krutz, G. and

Cassens, D. 1994. Color Matching of Wood With a

Real-time Machine Vision System, American Society

of Agricultural Engineers, Atlanta, Georgia, December,

pp. 13-16.

Lim G. H., He, Y. B., and Chua, P. S. K. 2002. Modern

Water Hydraulics-The New Energy Transmission

Technology in Fluid Power, Proceedings of the

th International Energy Conference and Exhibition

(Energex’ 02), Crakow, Poland.

Ivantysyn, J. and Ivantysynova, M. 2002. Hydrostatic

Pumps and Motors, Technip Books International,

New Delhi-110 019, India, ISBN 81-8830508-1.

Ivantysynova, M., Huang, C. and Behr, R. 2005.

Measusrement of elastohydrodynamic pressure field

in the gap between piston and cylinder, Power

Transmission and Motion Control, PTMC 2005, pp.

-465.

Ivantysnova, M., and Lasaar, R. 2004. An investigation

into micro-and macrogeometric design of piston/

cylinder assembly of swash plate machine, International

Journal of Fluid Power, V5, n1, March,

pp. 23-36.

Krutz, G. W., and Chua, Patrick S. K. 2004. Water

Hydraulics-Theory and Applications, Workshop on

Water Hydraulics, Agricultural Equipment Technology

Conference (AETC’04).

Le, T. T., Watton, J., and Pham, D. T. 1998. Fault

classification of fluid power systems using a dynamics

feature extraction technique and neural networks,

Proceedings of the I MECH E Part I Journal

of Systems & Control Engineering 212, pp. 87 – 97.

Lim, G. H., Chen, H. X. and Chua, P. S. K. 2003.

Fault Diagnosis of Piston Crack in a Water Hydraulic

Motor, Proceedings of the International Conference

and Exhibition on Instrumentation and Control,

PICS-ICEIC 2003, ISBN: 1656-2364, November,

Manila, Philippines, pp. 27-29.

Lott, P. W. and Griffiths, A. J. 1997. Fault diagnosis

of pumping machinery using artificial neural networks,

Proceedings of the I MECH E Part E Journal

of Process Mechanical Engineering 211, pp.

-194.

Nandi, A. K., 2000. Advanced digital vibration signal

processing for condition monitoring, Proceedings of

COMADEM, Houston, TX, USA, pp.129-143.

Precetti, C. J. and Krutz, G. W. 1993. SPR: Statistical

pattern recognition software, Copyright No. TX 3

808, PRF.

Samanta, B. and Al-Balushi, K. R. 2001. Use of time

domain features for the neural network based fault

diagnosis of a machine tool coolant system, Proceedings

of the I MECH E Part I Journal of Systems

& Control Engineering 215, pp. 199-207.

Schlkopf, B. 1998. SVMs-a proactical consequence of

learning theory, IEEE Intelligent Systems 13, pp.

-19.

Scholkopf, B. and Smola, A. J. 1990. Learning with

kernels, support vector machines, regularization,

optimization, and beyond, New York, MIT Press.

Simon, U. 1996. Water Hydraulic power- The technology

matures (putting water to work), National Fluid

Power Association Technical Paper Series, pp. 7-

Sorensen, P. 1999. News and trends by the industrial

application of water hydraulics, The Six Scandinavian

International Conference on Fluid Power, pp.

-674.

Stewart, C. J. and Watton, J. 1994. Some aspects of

rule-based expert systems design for on-line fault

diagnosis of fluid power systems, American Society

of Mechanical Engineers, Petroleum Division (Publication)

PD, Design: Analysis, Synthesis, and Application

(8-2), pp.457-461.

Sweldens, W. 1996. The lifting scheme: A customdesign

construction of biorthogonal wavelets, Applied

and Computational Harmonic Analysis 3(2),

pp. 186-200.

Trostmann, E. and Clausen, P. M. 1995. Hydraulic

components using tap water as pressure medium,

The Fourth Scandinavian International Conference

on Fluid Power, pp. 942-954.

Vapnik, V. 1995. The nature of statistical learning

theory, Springer, Berlin.

Watton, J., Lucca-Negro, O. and Stewart, J. C. 1994.

On-line approach to fault diagnosis of fluid power

cylinder drive systems, Proceedings of the Institution

of Mechanical Engineers. Part I, Journal of

System & Control Engineering, 208(14), pp.249-

Downloads

Published

2006-08-01

How to Cite

Chen, H. X., Chua, P. S. K., & Lim, G. H. (2006). FEATURE EXTRACTION, OPTIMIZATION AND CLASSIFICATION BY SECOND GENERATION WAVELET AND SUPPORT VECTOR MACHINE FOR FAULT DIAGNOSIS OF WATER HYDRAULIC POWER SYSTEM. International Journal of Fluid Power, 7(2), 39–52. Retrieved from https://journals.riverpublishers.com/index.php/IJFP/article/view/557

Issue

2006: Vol 07 Iss 2

Section

Original Article