Gear fault detection using artificial neural networks with discrete wavelet transform and principal component analysis

M. Er-raoudi; M. Diany; H. Aissaoui; M. Mabrouki

doi:10.15282/jmes.10.2.2016.6.0190

Authors

M. Er-raoudi Industrial Engineering Laboratory, Faculty of science and technology Beni Mellal, Morocco
M. Diany Industrial Engineering Laboratory, Faculty of science and technology Beni Mellal, Morocco
H. Aissaoui Sustainable development Laboratory, Faculty of science and technology Beni Mellal, Morocco
M. Mabrouki Industrial Engineering Laboratory, Faculty of science and technology Beni Mellal, Morocco

DOI:

https://doi.org/10.15282/jmes.10.2.2016.6.0190

Keywords:

Monitoring; Fault; Gears; classification; Neural Networks.

Abstract

The current work aims to develop a classification method devoted to gear defect diagnosis. In this paper, the proposed classification method is based on the Neural Networks, Discrete Wavelet Transform and Principal Component Analysis. A gearbox system with six degrees of freedom (DOF) is simulated in MATLAB and Simulink. Defects are introduced in the model by the meshing stiffness function which is computed by considering in series the bending, shear, axial compressive, fillet foundation and Hertzian stiffness. The signals dataset is collected by changing system or defect parameters. In addition, an experimental data is tested with the proposed method. Signal features are extracted using the Discrete Wavelet Transform with the Principal Component Analysis. This method allows us to classify the extracted features into two classes, healthy and faulty, with a good rate of correct classification. Both simulated and experimental data are tested with the proposed method.

References

Li B, Zhang P-l, Wang Z-j, Mi S-s, Zhang Y-t. Gear fault detection using multi- scale morphological filters. Measurement. 2011;44:2078-89.

Kidar T. Diagnostic des défauts de fissures d’engrenages par l’analyse cyclostationnaire école de technologie supérieure - université du québec en cotutelle avec l’université jean monnet de saint-etienne, France; 2015.

Li H, Zheng H, Tang L. Gear fault detection based on Teager-Huang transform. International Journal of Rotating Machinery. 2010;2010:9.

Yunoh MFM, Abdullah S, Saad MHM, Nopiah ZM, Nuawi MZ. Fatigue feature extraction analysis based on a K-means clustering approach. Journal of Mechanical Engineering and Sciences. 2015;8:1275-82.

Hafizi ZM, Epaarachchi J, Lau KT. An investigation of acoustic emission signal attenuation for monitoring of progressive failure in fiberglass reinforced composite laminates. International Journal of Automotive and MechanicalEngineering. 2013;8:1442-56.

Srihari PV, Govindarajulu K, Ramachandra K. A method to improve reliability of gearbox fault detection with artificial neural networks. International Journal of Automotive and Mechanical Engineering. 2010;2:221-30.

Samanta B. Gear fault detection using artificial neural networks and support vector machines with genetic algorithms. Mechanical Systems and Signal Processing. 2004;18:625-44.

Wuxing L, Tse PW, Guicai Z, Tielin S. Classification of gear faults using cumulants and the radial basis function network. Mechanical Systems and Signal Processing 2004;18:381-9.

Lei Y, Zuo MJ. Gear crack level identification based on weighted Knearest neighbor classification algorithm. Mechanical Systems and Signal Processing. 2009;23:1535–47.

Saravanan N, Cholairajan S, Ramachandran KI. Ibration-based fault diagnosis of spur bevel gear box using fuzzy technique. Expert Systems with Applications. 2009;36:3119–35.

Chen Z, Li C, Sanchez R-V. Gearbox fault identification and classification with convolutional neural networks. Shock and Vibration. 2015;2015:10.

Tian X. Dynamic Simulation for System Response of Gearbox Including Localized Gear faults: University of Alberta 2005.

Mohammed OD, Rantatalo M, Aidanpää J-O, Kumar U. Vibration signal analysis for gear fault diagnosis with various crack progression scenarios. Mechanical Systems and Signal Processing 2013;41:176-95.

Chaari F, Baccar W, Abbes MS, Haddar M. Effect of spalling or tooth breakage on gearmesh stiffness and dynamic response of a one-stage spur gear transmission. European Journal of Mechanics A/Solids. 2008;27:691-705.

Chaari F, Fakhfakh T, Haddar M. Analytical modelling of spur gear tooth crack and influence on gearmesh stiffness. European Journal of Mechanics A/Solids. 2009;28:461–8.

Wu S, Zuo MJ, Parey A. Simulation of spur gear dynamics and est-imation of fault growth. Journal of Sound and Vibration. 2008;317:608-24.

Mohammed OD, Rantatalo M, Aidanpää J-O. Improving mesh stiffness calculation of cracked gears for the purpose of vibration-based fault analysis. Engineering Failure Analysis. 2013;34:235-51.

Bartelmus W. Mathematical modelling and computer simulations as an aid to gearbox diagnostics. Mechanical Systems and Signal Processing. 2001;15:855- 71.

Ozguven HN, Houser DR. Mathematical models used in gear dynamics-a review. Journal of sound and vibration. 1988;121:383-411.

Yang DCH, Lin JY. Hertzian damping, tooth friction and bending elasticity in gear impact dynamics. Journal of Mechanisms,Transmissions and Automationin Design 1987;109:189-96.

Sainsot P, Velex P. Contribution of gear body to tooth deflections—a new bidimensional analytical formula. Journal of Mechanical Design. 2004;126:748- 52.

Chui CK. An Introduction to Wavelets: Academic press; 1992.

Meyer Y, Roques S. Progress in Wavelet Analysis and Applications. 1993. p. 785.

Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence.1989;11:674 - 93.

Shlens J. A tutorial on principal component analysis derivation, discussion and singular value decomposition. version 1 ed2003.

Briand M. Etudes d'algorithmes d'extraction des informations de spatialisation sonore : application aux formats multicanaux: l’institut national polytechnique de Grenoble; 2007.

Rosenblatt F. Principles of neurodynamics; perceptrons and the theory of brain mechanisms. Cornell Aeronautical Lab Inc Buffalo; 1962.

Belaidi I, Tahmi R, Mohammedi K. Configuration optimale d’un réseau de neurons adapté à la surveillance en ligne de l’usure des outils de tournage. 18 ème Congrès Français de Mécanique. France; 2007.

Kohonen T, Mäkisara K, SImula O, Kangas J. Artificial neural networks. Proceedings of the 1991 International Conference on Artificial Neural Networks (ICANN-91) Espoo, Finland; 1991.

Drouiche K, Sidahmed M, Grenier Y. Détection de défauts d'engrenages par analyse vibratoire. Journal de traitement de signal. 1999;8:331-43.

Merzoug M, Ait-Sghir K, Miloudi A, Dron JP, Bolaers F. Early detection of gear failure by vibration analysis. Multiphysics Modelling and Simulation for Systems Design and Monitoring MMSSD. Tunisia: Springer; 2014. p. 69-79.

Parey A, Badaoui ME, Guillet F, Tandon N. Dynamic modelling of spur gear pair and application of empirical mode decomposition-based statistical analysis for early detection of localized tooth defect. Journal of sound and vibration. 2006;294:547–61.

El Badaoui M. Contribution au Diagnostic Vibratoire des Réducteurs Complexes à Engrenages par l’Analyse Cepstrale: University Jean Monnet Saint Etienne; 1999.

Haloui N, D.Chikouche, .Benidir M. Diagnosis of gear systems by spectral analysis of vibration signals. I International Journal of Computer Science and Network Security IJCSNS. 2007;7:285-93.