Remain useful life forecasting for roller bearings using sparse auto-encoder
Tóm tắt
A method based on sparse auto-encoder (SAE) in deep learning (DL) for roller bearings remain useful life (RUL) prediction is presented in this paper. Firstly, the roller bearings vibration signals were calculated by different time and frequency domain factors, in which reflect the vibration signals information well. Therefore, the time and frequency domain features were regarded as the input of SAE, then the SAE model in deep learning was used to extract the features through several hidden layers and the sigmoid function was selected as the output function for calculate the prediction value. Finally, compared with other different prediction methods, such as support vector machine (SVM), back propagation (BP) neural network and random forest (RF), the performance of SAE is better than that those models by using mean absolute error (MAE) and root mean square error (RMSE) these two indicators.
Tài liệu tham khảo
Affonso, C., R. Debiaso, and L. Andre. 2017. Deep learning for biological image classification. Expert System with Apllication 85: 114–122.
Bagordo, G., G. Cazzluani, and F. Resta. 2011. A modal disturbance estimator for vibration suppression in nonlinear flexible structures. Journal of Sound and Vibration 330 (25): 6061–6069.
Bremian, L. 2001. Random forests, Machine Learning.
Cong, F., J. Chen, G. Dong, et al. 2013. Vibration model of rolling element bearings in a rotor-bearing system for fault diagnosis. Journal of Sound and Vibration 332 (8): 2081–2097.
Feng, J., Y.G. Lei, and L. Jing. 2016. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems and Signal Processing 72: 303–315.
Guo, W., and P.W. Tse. 2013. A novel signal compression method based on optimal ensemble empirical mode decomposition for bearing vibration signals. Journal of Sound and Vibration 332 (2): 423–441.
Hintonand, G.E., and R.R. Sala Hutdinov. 2006. Reducing the dimensionality of data with neural networks. Science 313 (5786): 504–507.
Huang, Y., B.X. Wu, and J.Q. Wang. 2012. Test for active control of boom vibration of a concrete pump truck. Journal of Vibration and Shock 31 (2): 91–94.
Kosasih, B.Y., W. Caesarendra, K. Tieu, et al. 2014. Degradation trend estimation and prognosis of large low speed slewing bearing lifetime. Applied Mechanics and Materials 493: 343–348.
Kullbacks, S., and R.A. Leibler. 1951. On information and sufficiency. Annals of Mathematical Statistics. Journal Article on Information and Sufficiency 22 (1): 79–86.
Lei, Y., N. Li, and J. Lin. 2016. A new method based on stochastic process models for machine remaining useful life prediction. IEEE Transactions on Instrumentation and Measurement 65 (12): 2671–2684.
Li, Q., Shi, J. Y., Werian, A. 2015. An application of systemic prediction evaluation parameters for neural network remaining useful life prediction models. IEEE Conference On Prognostics And Health Management., Austin, TX, 22–25.
Li, X.Y., X. Shu, and J.W. Shen. 2017. An on-board remaining useful life estimation algorithm for lithium-ion batteries of electric vehicles. Energies 10 (5): 1–15.
Liu, F., Y.B. Liu, F.L. Chen, et al. 2017. Residual life prediction for ball bearings based on joint approximate diagonalization of eigen matrices and extreme learning machine. Proceedings of the Institution of Mechanical Engineers Part C-Journal of Mechanical Engineering Science 231 (9): 1699–1711.
Nectoux, P., Gouriveau, R., Medjaher, K., et al. 2012. PRONOSTIA: An Experimental Platform for Bearings Accelerated Life Test. IEEE International Conference on Prognostics and Health Management, Institute of Electrical and Electronics Engineers Inc US..
Olshausen, B.A. 1996. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 381 (6583): 607–309.
Patil, M.A., P. Tagade, K.S. Hariharan, et al. 2015. A novel multistage Support Vector Machine based approach for Li ion battery remaining useful life estimation. Applied Energy 159: 285–297.
Resta, F., F. Ripamonti, and G. Cazzluani. 2011. Independent modal control for nonlinear flexible structures: An experimental test rig. Journal of Sound and Vibration 329 (8): 961–972.
Shen, Z.H., X.F. Chen, and Z.J. He. 2013. remaining life predictions of rolling bearing based on relative features and multivariable support vector machine [J]. Journal of Mechanical Engineering 49 (2): 183–189.
Shin, H.C., M.R. Orton, D.J. Collins, et al. 2013. Stacked auto-encoders for unsupervised feature learning and multiple organ detection in a pilot study using 4D patient data. IEEE Transactions on Software Engineering 35 (8): 1930–1943.
Sun, S.N., B.B. Hang, and L. Zhang. 2017. An unsupervised deep domain adaptation approach for robust speech recognition. Neurocomputing 257: 79–87.
Tran, V.T., F. Althobianil, and B. Andrew. 2017. An approach to fault diagnosis of reciprocating compressor valves using Teager-Kaiser energy operator and deep belief networks. Expert Systems with Applications 41: 4113–4122.
Tse, P.W., and D. Wang. 2017. Enhancing the abilities in assessing slurry pumps’ performance degradation and estimating their remaining useful lives by using captured vibration signals. Journal of Vibration and Control 23 (12): 1925–1937.
Wang, X., and S. Tong. 2014. Nonlinear dynamical behavior analysis on rigid flexible coupling mechanical arm of hydraulic excavator [J]. Journal of Vibration and Shock 33 (1): 63–70.
Wang, D.W., and Z.W. Sun. 2015. Big data analysis and parallel load forecasting of electric power user side. Proceedings of the CSEE 35 (3): 527–537.
Wang, F.T., B. Wang, B.S. Dun, et al. 2016. Remaining life prediction of rolling bearing based on PCA and improved logistic regression model [J]. Journal of Vibroengineering 18 (8): 5192–5203.
Xu, F., W.P. Tse, and Y.L. Tse. 2018. Roller bearing fault diagnosis using stacked denoising autoencoder in deep learning and Gath-Geva clustering algorithm without principal component analysis and data label. Applied Soft Computing 73: 898–913.