Gear Fault Detection Based on Best Feature Selection by Particle Swarm Optimization

Authors

1 Prof., Dep. Of Mech. Eng., Guilan Univ., Rasht, Iran

2 Ph.D. Student, Mech. Eng., Guilan Univ., Rasht, Iran.

3 MSc of Mechanical Engineering, Ahrar Institute of Technology and Higher Education, Rasht, Iran.

4 Prof., Dep. Of Mech. Eng., Guilan Univ., Rasht, Iran.

Abstract

In this paper, a new method is presented for gear fault detection. The vibrational signals of gearbox set are collected in three conditions: normal, chipped and worn teeth. These signals are adaptively decomposed into a number of intrinsic mode functions (IMFs) by the empirical mode decomposition (EMD). Since, all of the IMFs drived from the EMD are not appropriate for fault detection, the cross-corrolation concept is used to select all most apptoptiate IMFs. Then, feature matrix corresponding to each condition, is extracted using statistical functions. “One-against-one” support vector machine (SVM-OAO) is utilized to classify the faults. Since, all of the extracted features are not suitable for fault detection and SVM has parameters to be set, the particle swarm optimization (PSO) is used to select the best feature and detect optimal parameters of SVM. Objective function in this paper is accuracy of the SVM classifier in predicting of gearbox condition. Obtained results show that the selected features in this method and optimized SVM have the excellent ability to classify the faults.

Keywords

Main Subjects

References

[1] Lei Y, Lin J, He Z, Zuo M (2013) A review on empirical mode decomposition in fault diagnosis of rotating machinery. Mech Syst Signal Process 35: 108-126.
[2] Ben Ali J, Fnaiech N, Saidi L, Chebel-Morello       B, Fnaiech F (2015) Application of empirical   mode decomposition and artificial neural      network for automatic bearing fault diagnosis   based on vibration signals. Appl Acoust 89: 16-   27.
[3] چایی­بخش ع، رهبر م (1395) مقایسه­ای بین تجزیه حالت تجربی و تبدیل موجک در تشخیص نابالانسی ماشین دوار با استفاده از ماشین بردار پشتیبان بهینه. مجله علمی پژوهشی مهندسی مکانیک مدرس 332-325: (2)17.
[4]  Rajeswari C, Sathiyabhama B, Devendiran S, Manivannan K (2014) A gear fault identification using wavelet transform, rough set based GA,   ANN and C4.5 algorithm. Procedia Eng 97: 1831-1841.
[5]  Bordoloi DJ, Tiwari R (2014) Support vector machine based optimization of multi-fault classification of gears with evolutionary algorithms from time–frequency vibration data. Measurement 55: 1-14.
[6]  Bordoloi DJ, Tiwari R (2014) Optimum multi-fault classification of gears with integration of evolutionary and SVM algorithms. Mech Mach Theory 73: 49-60.
[7] Bordoloi DJ, Tiwari R, (2015) Optimisation of SVM methodology for multiple fault taxonomy of rolling bearings from acceleration records. 9th IFToMM International Conference on Rotor Dynamics Mechanisms and Machine Science 21: 533-542.
[8] Liu Z, Cao H, Chen X, He Z, Shen Z (2013) Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings. Neurocomputing 99: 399-410.
[9]  Jack LB, Nandi AK (2002) Fault detection using support vector machines and artificial neural networks, augmented by genetic algorithms. Mech Syst Signal Process, 16 (2-3): 373-390.
[10] Dalian Y, Liyong M (2015) Gear fault diagnosis based on support vector machine optimized by artificial bee colony algorothm. Mech Mach Theory 90: 219-229.
[11] Ziani R, Felkaoui A, Zegadi R (2017) Bearing fault diagnosis using multiclass support vector machines with binary particle swarm optimization and regularized fisher’s criterion. J Intell Manuf 28(2): 405-417.
[12] Zhang X, Zhang Q, Chen M, Sun Y, Qin X, Li H (2018) A two-stage feature selection and intelligent fault diagnosis method for rotating machinery using hybrid filter and wrapper method. Neurocomputing 275: 2426-2439.
[13] Tabrizi A, Garibaldi L, Fasana A, Marchesiello S (2014) Influence of stopping criterion for sifting process of empirical mode decomposition (EMD) on roller bearing fault diagnosis. Advances in Condition Monitoring of Machinery in Non-Stationary Operations Lecture Notes in Mechanical Engineering 389-398.
[14] Dhamandeh SL, Chaudhari BM, (2016) Detection of Combined gear-bearing fault in single stage spur gear box using artificial neural network. Procedia Eng 144: 759-766.
[15] Pirra M, Fasana A, Garibaldi L, Marchesiello S (2012) Damage identification and external effects removal for roller bearing diagnostics. European Conference of the Prognostics and Health Management Society, Germany 1-8.
[16] Djebala A, Babouri MK, Ouelaa, N (2015) Rolling bearing fault detection using a hybrid method based on empirical mode decomposition and optimized wavelet multi-resolution analysis. Int J Adv Manuf Tech 79: 2093-2105.
[17] Zamanian AH, Ohadi A (2011) Gear fault diagnosis based on gaussian correlation of vibrations signals and wavelet coefficients. Appl Soft Comput 11: 4807-4819.
[18] Zhong J, Ma W, Lin J, Ma L, Jia X (2014) Fault diagnosis approach for rotating machinery based on dynamic model and computational intelligence. Measurement 59: 73-87.
[19] Widodo A, Yang BS (2007) Support vector machine in machine condition monitoring and fault diagnosis. Mech Syst Signal Process 21(6): 2560-2574.
[20] Tabrizi AA (2015) Development of new fault detection methods for rotating machines (roller bearings). PhD thesis, University of Politecnico di Torino.
[21] Jin S, Kim SJ, Lee KS (2015) Sensitive method for detecting tooth faults in gearboxes based on wavelet denoising and empirical mode decomposition. J Mech Science Tech 29(8): 3165-3173.
[22] Shi Y, Eberhart R, (1998) A modified particle swarm optimizer. In: The 1998 IEEE International Conference on Evolutionary Computation Proceedings, Anchorage, AK 69-73.
[23] Ratnaweera A, Halgamuge SK, Watson HC (2004) Self-organizing hierarchical particle swarm optimizer with time-varying acceleration coefficients. IEEE T Evolut Comput 8(3):240-255.
Journal of Solid and Fluid Mechanics
Volume 8, Issue 3
October 2018
Pages 49-64

Files

Share

How to cite

Statistics