Fault Diagnosis of Helical Gear Box Using Variational Mode Decomposition with Naïve Bayes and Bayes Net Classifiers through Vibration Signals
DOI:
https://doi.org/10.37628/ijmmp.v2i2.76Abstract
Gear is a very important machine component which finds use in most of the machines which requires some sort of power transmission or reduction. Unattended faults in gears can be catastrophic for the machine leading to halts in production and consequent economic loss. The requirement for a gear fault detection and diagnosis system is thus emphasized. Vibration signals are often used in fault diagnosis applications along with Fast Fourier transform method. However it is not effective with non-stationary signals like those obtained from gears in motion. Therefore, development of new methodologies to obtain diagnostic information from such signals is required. This paper details the use of vibration signals obtained from gears in good and simulated faulty conditions after performing preprocessing with Variational Mode Decomposition (VMD). VMD decomposes the vibration signals into various modes by identifying a compact frequency support around its central frequency so that adding all the modes reconstructs the original signal. Alternating Direction Multiplier Method (ADMM) is used in VMD to find the intrinsic mode functions. Descriptive statistical features extracted from VMD preprocessed signals, classified using Naïve Bayes and Bayes Net classifiers, and corresponding classification accuracies were calculated. The results were compared with the accuracy obtained from the statistical features extracted from the raw signal and decision tree classifier.References
Asi O. Fatigue failure of a helical gear in a gearbox. Engineering Failure Analysis. 2006; 13(7): 1116–25p.
Dalpiaz G., Rivola A., Rubini R. Effectiveness and Sensitivity of Vibration Processing Techniques for Local Fault Detection in Gears. Mechanical Systems and Signal Processing. 2000; 14(3): 387–412p.
Toutountzakis T., Mba D. Observations of acoustic emission activity during gear defect diagnosis. NDT & E International. 2003; 36(7): 471–77p.
Ebersbach S., Peng Z., Kessissoglou N.J. The investigation of the condition and faults of a spur gearbox using vibration and wear debris analysis techniques. Wear. 2006; 260(1–2): 16–24p.
Rai V.K., Mohanty A.R. Bearing fault diagnosis using FFT of intrinsic mode functions in Hilbert-Huang transform. Mechanical Systems and Signal Processing. 2007; 21(6): 2607–15p.
Ricci R., Pennacchi P. Diagnostics of gear faults based on EMD and automatic selection of intrinsic mode functions. Mechanical systems and Signal Processing. 2011; 25: 821–38p.
Saravanan N., Siddabattuni V.N.S., Ramachandran KI, Fault diagnosis of spur bevel gear box using artificial neural network, and proximal support vector machine. Applied Soft Computing. 2010; 10(1): 344–60p.
Bin G.F., Gao J.J., Li X.J., et al. Early fault diagnosis of rotating machinery based on wavelet packets-Empirical mode decomposition feature extraction and neural network. Mechanical Systems and Signal Processing. 2012; 27: 696–711p.
Yang Q., An D., EMD and Wavelet Transform Based Fault Diagnosis for Wind Turbine Gear Box. Advances in Mechanical Engineering. 2013; 212836: 9.
Sugumaran V., Ramachandran K.I. Effect of number of features on classification of roller bearing faults using SVM and PSVM. Expert Systems with Applications. 2011; 38.
Amarnath M., Jain D., Sugumaran V., et al. Fault diagnosis of helical gear box using Naïve Bayes and Bayes net. International Journal of Decision Support Systems. 2014.
