Local discriminant bases in machine fault diagnosis using vibration signals

Article type: Research Article

Authors: Tafreshi, R.^a | Sassani, F.^{a; *} | Ahmadi, H.^{b; c} | Dumont, G.^b

Affiliations: [a] Department of Mechanical Engineering, The University of British Columbia, Vancouver, BC, V6T 1Z4, Canada. E-mail: tafreshi@mech.ubc.ca, sassani@mech.ubc.ca | [b] Department of Electrical and Computer Engineering, The University of British Columbia, Vancouver, BC, V6T 1Z4, Canada. E-mail: ahmadi@ece.ubc.ca, guyd@ece.ubc.ca | [c] Department of Electrical Engineering, University of Tehran, Iran

Correspondence: [*] Corresponding author.

Abstract: Wavelets and local discriminant bases (LDB) selection algorithm is applied to vibration signals in a single-cylinder spark ignition engine for feature extraction and fault classification. LDB selects a complete orthogonal basis from a wavelet packet library of bases, which best discriminates the given classes, based on their time-frequency energy maps. An appropriate normalization method in both data and wavelet coefficient domains, and a neural network classifier during the identification phase are used to enhance the classification. By applying LDB to a real-world machine data the accuracy of the algorithm in machine fault diagnosis and classification is shown.

DOI: 10.3233/ICA-2005-12202

Journal: Integrated Computer-Aided Engineering, vol. 12, no. 2, pp. 147-158, 2005