Statements on wavelet packet energy–entropy signatures and filter influence in fault diagnosis of induction motor in non-stationary operations
- 101 Downloads
Electric motors are components of great importance in mechanical systems and in the majority of the equipment used in industrial plants. The several faults that occur in the induction machines may induce severe consequences in the industrial process. Many of these faults are progressive. In this work, a contribution to the study of signal-processing techniques based on wavelet packet transform for parameter extraction of energy and entropy from vibration signals for the detection of faults in the non-stationary operation (start of the motor) is presented. Together with the wavelet transform, methods of dimensionality reduction such as principal component analysis, linear discriminant analysis, and independent components analysis are used. In addition, the use of an experimental bench shows that the model of extraction and classification proposed present high precision for fault classification.
KeywordsInduction motors Fault diagnosis Wavelet packet transform (WPT) Principal component analysis (PCA) Independent component analysis (ICA) Linear discriminant analysis (LDA)
The authors want to express their thanks to CAPES (Coordenação de Aperfeiçoamento de Pessoal de Nível Superior) for the financial support.
- 1.Scheffer C, Girdhar P (2004) In: Mackay S (ed) Practical machinery vibration analysis and predictive maintenance. Elsevier, NetherlandsGoogle Scholar
- 3.Lees AW (2016) Vibration problems in machines: diagnosis and resolution. CRC Press, Boca RatonGoogle Scholar
- 12.Daubechies I (1992) Ten lectures on wavelets. In: CBMS-NSF regional conference series in applied mathematics. Society for Industrial and Applied Mathematics. https://doi.org/10.1137/1.9781611970104
- 15.Boashash B (2015) Time-frequency signal analysis and processing: a comprehensive reference. Academic Press, CambridgeGoogle Scholar
- 18.Amir RB, Gul ST, Khan AQ (2016) A comparative analysis of classical and one class SVM classifiers for machine fault detection using vibration signals. In: Emerging technologies (ICET), 2016 international conference on. IEEE, pp 1–6Google Scholar
- 20.Kompella KCD, Mannam VGR, Rayapudi SR (2016) DWT based bearing fault detection in induction motor using noise cancellation. J Electr Syst Inf Technol 3(3):411–427Google Scholar
- 38.Varanis M, Pederiva R (2015) Wavelet packet energy-entropy feature extraction and principal component analysis for signal classification. Proc Ser Braz Soc Comput Appl Math 3(1). https://doi.org/10.5540/03.2015.003.01.0471
- 42.Stone JV (2004) Independent component analysis. Wiley, USAGoogle Scholar
- 43.Varanis M, Pederiva R (2015) Wavelet time-frequency analysis with Daubechies filters an dimension reduction methods for fault identifications induction machine in stationary operations. In: 23rd ABCM international congress of mechanical engineering, 2015, Rio de Janeiro, pp 1–8Google Scholar