EA
Gearbox Multiple Faults Diagnosis under Stationary and Non-Stationary Operating Conditions Using Convolutional Neural Networks
TOTAL VIEWS: 6384
Abstract
High accuracy in gearbox fault diagnosis is of paramount importance for keeping industrial systems safe and working normally. Concerning various single or multiple faults diagnosis using classical machine learning algorithms, the feature extraction and selection methods are time-consuming and labor-intensive processes requiring expert knowledge of the relevant features related to the system. To mitigate this problem, a deep learning convolutional neural network (CNN) is proposed which enables automatic feature learning from the time-frequency domain image representations data input. The proposed approach employs a CNN model which uses max-pooling and batch normalization between each convolution for training acceleration and reduction of generalization error. The proposed model performance in multiple faults diagnosis is evaluated using gearbox vibration data obtained under stationary operating conditions. The proposed model classification performance is also evaluated using engineered non-stationary operating vibrations data sets. To achieve this, data sets were engineered using gearbox stationary operating conditions vibration data obtained using five operating speeds (30 Hz, 35 Hz, 40 Hz, 45 Hz, and 50 Hz) under low and high load conditions. The non-stationary operating conditions data sets were developed based on three operational conditions namely; constant operating speed and variable load, variable operating speed and constant load, and variable operating speed and variable load. This methodology was applied to PHM2009 gearbox vibration data sets which consist of multiple component faults. Time domain, frequency domain, and time-frequency analysis methods (short-time Fourier transform (STFT), continuous wavelet transform (CWT), empirical mode decomposition (EMD), Wigner Ville distribution (WVD), and wavelet synchrosqeezed transform (WSST)), were investigated for their effectiveness in multiple faults diagnosis. The proposed CNN architecture exhibited high classification performance as high as 99.9% under stationary operating conditions in multiple faults diagnosis as compared to other architectures. The use of image input to the CNN model gave better performance compared to feature vector input. The application of the developed diagnostic model for multiple fault diagnosis under non-stationary operating conditions gave satisfactory classification performance as high as 86.5% using scalogram images. This work provides the possibility that stationary operating conditions-based diagnostic models, can be deployed for multiple faults diagnosis on industrial equipment operating under non-stationary conditions.
References
[1] M. Muraro, F. Koda, U. Reisdorfer Jr, and C. H. D. Silva. (2012). “The influence of contact stress distribution and specific film thickness on the wear of spur gears during pitting tests.” Journal of the Brazilian Society of Mechanical Sciences and Engineering, vol. 34, pp. 134-144, 2012.
[2] O. Asi. (2006). “Fatigue failure of a helical gear in a gearbox.” Engineering Failure Analysis, vol. 13, no. 7, pp. 1116-1125, 2006.
[3] A. S. Sait and Y. I. Sharaf-Eldeen. (2011). “A Review of Gearbox Condition Monitoring Based on vibration Analysis.” Rotating Machinery, Structural Health Monitoring, Shock and Vibration; Springer, vol. 5, pp. 307-324, 2011.
[4] A. Aherwar and M. Khalid. (2012). “Vibration analysis techniques for gearbox diagnostic: a review.” Internal Journal of Advanced Engineering Technology, vol. 3, no. 2, pp. 1-9, 2012.
[5] D. Verstraete, A. Ferrada, E. Droguett, V. Meruane, and M. Modarres. (2017). “Deep enhanced fault diagnosis using time-frequency image analysis of rolling element bearings.” Hindawi Shock and Vibration, vol. 2017, no. 5067651, pp. 1-17, 2017.
[6] Z. Hou, Y. Zhang, P. Francq, S. J., and L. Huang. (2017). “Incipient fault diagnosis of roller bearing using optimised wavelet transform based multi-speed vibration signatures.” IEEE Acess, vol. 5, pp. 19442-19456, 2017.
[7] J. Wang, J. Zhuang, L. Duan, and W. Cheng. (2016). “A multi-scale convolutional neural network for featureless fault diagnosis.” In Proceedings of the Internal Symposium on Flexible Automation, Cleveland, Ohio, USA, August 2016.
[8] M. Seera and C. Lima. (2014). “Online motor fault detection and diagnosis using a hybrid FMM-CART model.” IEEE Transactions on Neural Networks and Learning Systems, vol. 25, no. 4, pp. 806-812, 2014.
[9] A. Sharma, A. Amarnath, and P. Kankar. (2014). “Feature extraction and fault severity classification in ball bearings.” Journal of Vibration and Control, vol. 22, no. 1, pp. 1-17, 2014.
[10] P. Wong, J. Zhong, Z. Yang, and C. Vong. (2016). “Sparse Bayesian extreme learning committe machine for engine simultaneous fault diagnosis.” Neurocomputing, vol. 174, pp. 331-343, 2016.
[11] Z. Chen, C. Li, and R. Sanchez. (2015). “Gearbox fault identification and classification with convolutional neural networks.” Shock and Vibration, vol. 2015, no. 390134, pp. 1-10, 2015.
[12] Y. LeCun, Y. Bengio, and G. Hinton. (2015). “Deep learning.” Nature, vol. 521, no. 7553, pp. 436-444, 2015.
[13] C. Szegedy, W. Liu, and Y. Jia. (2015). “Going deeper with convolutions.” In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Boston, Mass, USA, 2015.
[14] H. Liu, L. Li and J. Ma. (2016). “Rolling bearing fault diagnosis based on STFT-deep learning and sound signals.” Shock and Vibration, vol. 2016, no. 6127479, pp. 1-12, 2016.
[15] L. Wang, X. Zhao, J. Wu, Y. Xie, and Y. Zhang. (2017). “Motor fault diagnosis based on shirt time Fourier transform and convolutional neural network.” Chines Journal of Mechanical Engineering, vol. 30, no. 6, pp. 1357-1368, 2017.
[16] X. Guo, L. Chen, and C. Shen. (2016). “Hierachical adaptive deep convolutional neural network and its application to bearing fault diagnosis.” Measurement: Journal of the International Measurement Confederation, vol. 93, pp. 490-502, 2016.
[17] K. Loparo. (2013). “Bearing Data Center,Case Western Reserve University, http://csegroups.case.edu /bearingdatacenter/pages/welcome-case-western-reserve-universitybearing-datacenter-website,” 2013.
[18] F. Zhou, Y. Gao, and C. Wen. (2017). “A novel multimode fault classification method based on deep learning.” Jornal of Control Science and Engineering, vol. 2017, no. 3583610, pp. 1-14, 2017.
[19] “Information on https://www.phmsociety.org/competition/PHM/09”.
[20] S. Ioffe and C. Szegedy. (2015). “Batch normalisation:Accelerating deep network training by reducing internal covariate shift.” ArXiv, vol. abs/1502.03167, pp. 1-11, 2015.
[21] N. Srivastava, G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov. (2015). “Drop out a simple way to prevent neural networks from overfitting.” The Journal of Machine Learning Research, vol. 15, no. 1, pp. 1929-1958, 2015.
How to cite this paper
Gearbox Multiple Faults Diagnosis under Stationary and Non-Stationary Operating Conditions Using Convolutional Neural Networks
How to cite this paper: Destine Mashava, James Kuria Kimotho, Onesmus Mutuku Muvengei. (2022). Gearbox Multiple Faults Diagnosis under Stationary and Non-Stationary Operating Conditions Using Convolutional Neural Networks. Engineering Advances, 2(1), 1-17.
DOI: http://dx.doi.org/10.26855/ea.2022.06.001
More Articles
- Discussion on Construction Technology of Formwork and Scaffold Engineering
- Industrial Engineering and Lean Management for Intelligent Manufacturing
- Urban Safety Risk Assessment Technology Based on Risk Correction
- PAT Monitoring of Coating Pan by NIR - PLS Method Calibration Approach
- Study on the Spatiotemporal Response Characteristics of Effective Discharge Radius of Bedding Drilling
- Human Skeleton Coordinate Pose Recognition