Title: SVM-based wavelet selection for fault diagnosis of monoblock centrifugal pump

Authors: V. Muralidharan; V. Sugumaran

Addresses: Department of Mechanical Engineering, B.S. Abdur Rahman University, Vandalur, Chennai – 600048, India ' School of Mechanical and Building Sciences (SMBS), VIT University (Chennai Campus), Chennai, India

Abstract: In the present study, the application of SVM algorithm in the field of fault diagnosis and condition monitoring is discussed. The continuous wavelet transforms are calculated for different families and at different levels. The computed transformation coefficients form the feature set for the classification of good and faulty conditions of the components of centrifugal pump. The classification accuracies of different continuous wavelet families at different levels are calculated and compared to find the best wavelet for the fault diagnosis of the monoblock centrifugal pump.

Keywords: monoblock centrifugal pumps; SVM; support vector machines; fault diagnosis; continuous wavelet transforms; CWTs; pump faults; condition monitoring; classification.

DOI: 10.1504/IJDATS.2016.081364

International Journal of Data Analysis Techniques and Strategies, 2016 Vol.8 No.4, pp.357 - 369

Received: 21 Feb 2015
Accepted: 18 Jul 2015
Published online: 06 Jan 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article