In the process of Wavelet Analysis, only the low-frequency signals are re-decomposed, and the high-frequency signals are no longer decomposed, resulting in a decrease in frequency resolution with increasing frequency. Therefore, in this paper, firstly, Wavelet Packet Decomposition is used for feature extraction of vibration signals, which makes up for the shortcomings of Wavelet Analysis in extracting fault features of nonlinear vibration signals, and different energy values in different frequency bands are obtained by Wavelet Packet Decomposition. The features are visualized by the K-Means clustering method, and the results show that the extracted energy features can accurately distinguish the different states of the bearing. Then a fault diagnosis model based on BP Neural Network optimized by Beetle Algorithm is proposed to identify the bearing faults. Compared with the Particle Swarm Algorithm, Beetle Algorithm can quickly find the error extreme value, which greatly reduces the training time of the model. At last, two experiments are conducted, which show that the accuracy of the model can reach more than 95%, and the model has a certain anti-interference ability.
In the process of Wavelet Analysis, only the low-frequency signals are re-decomposed, and the high-frequency signals are no longer decomposed, resulting in a decrease in frequency resolution with increasing frequency. Therefore, in this paper, firstly, Wavelet Packet Decomposition is used for feature extraction of vibration signals, which makes up for the shortcomings of Wavelet Analysis in extracting fault features of nonlinear vibration signals, and different energy values in different frequency bands are obtained by Wavelet Packet Decomposition. The features are visualized by the K-Means clustering method, and the results show that the extracted energy features can accurately distinguish the different states of the bearing. Then a fault diagnosis model based on BP Neural Network optimized by Beetle Algorithm is proposed to identify the bearing faults. Compared with the Particle Swarm Algorithm, Beetle Algorithm can quickly find the error extreme value, which greatly reduces the training time of the model. At last, two experiments are conducted, which show that the accuracy of the model can reach more than 95%, and the model has a certain anti-interference ability.
[1] Y G Lei, J Lin, Z J He, et al. Application of an improved kurtogram method for fault diagnosis of rolling element bearings. Mechanical Systems and Signal Processing, 2011, 25(5):1738-1749.
[2] M M Tahir, A Q Khan, N Iqbal, et al. Enhancing fault classification accuracy of ball bearing using central tendency based time domain features. IEEE Access, 2017, 5(99):72-83.
[3] Y Li, M Xu, Y Wei, et al. Rotating machine fault diagnosis based on intrinsic characteristic-scale decomposition. Mechanism and Machine Theory, 2015, 94:9-27.
[4] S R Carpenter, W A Brock. Early warnings of regime shifts in spatial dynamics using the discrete Fourier transform. Ecosphere, 2010, 1(5):1-15.
[5] Z Feng, D Zhang, M J Zuo. Planetary gearbox fault diagnosis via joint amplitude and frequency demodulation analysis based on variational mode decomposition. Applied Sciences, 2017, 7(8):775.
[6] H Shao, H Jiang, F Wang, et al. Rolling bearing fault diagnosis using adaptive deep belief network with dual-tree complex wavelet packet. ISA Transactions, 2017, 69:187-201.
[7] F Jia, Y Lei, J Lin, et al. Deep neural networks:A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mechanical Systems and Signal Processing, 2016, 72-73:303-315.
[8] X A Yan, M P Jia. A novel optimized SVM classification algorithm with multi-domain feature and its application to fault diagnosis of rolling bearing. Neurocomputing, 2018, 313:47-64.
[9] P K Kankar, S C Sharma, S P Harsha. Fault diagnosis of ball bearings using continuous wavelet transform. Applied Soft Computing, 2011, 11(2):2300-2312.
[10] H T Zhou, J Chen, G M Dong, et al. Bearing fault recognition method based on neighbourhood component analysis and coupled hidden Markov model. Mechanical Systems and Signal Processing, 2016, 66-67:568-581.
[11] J Calvo-Zaragoza, A H Toselli, E Vidal. Hybrid hidden Markov models and artificial neural networks for handwritten music recognition in mensural notation. Pattern Analysis and Applications, 2019, 22(4):1573-1584.
[12] X Chen, Y P Chen, Z Y Long, et al. SVM-HMM-based bearing fault diagnosis method. Journal of Wuhan University of Technology (Information and Management Engineering Edition), 2016, 38(2):267-270.
[13] S Khan, T Yairi. A review on the application of deep learning in system health management. Mechanical Systems and Signal Processing, 2018, 107(1):241-265.
[14] X P Pu, K X Chen, J W Xu, et al. Fault diagnosis of bearings based on neural network Breaking method. Journal of University of Science and Technology Beijing, 1993, 12(15):610-613.
[15] T Wu, S C Yuan, X Meng, et al. A neural network method for vibration diagnosis of rolling bearings. Mechanical Design & Manufacturing, 2010, 1:198-200.
[16] Y Jiang, Z X Li, Y Tang. LVQ neural network in rolling bearing fault diagnosis applied research. Mechanical Science and Technology, 2011, 30(3):408-411.
[17] Z Z Zhao, Q S Xu, M P Jia. Improved shuf-fled frog leaping algorithm-based BP Neural Networkand its application in bearing early fault diagnosis. Neural Computing and Applications, 2016, 27(2):375-385.
[18] A P Markopoulos, S Georgiopoulos, D E Manolakos. On the use of back propagation and radial basis function neural networks in surface roughness prediction. Journal of Industrial Engineering International, 2016, 12(3):389-400.
[19] J B Ali, N Fnaiech, L Saidi, et al. Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals. Applied Acoustics, 2015, 89:16-27.
[20] Q Long, Y Q Liu, Y P Yang. Fault diagnosis method for wind turbine gearbox based on particle s-warm optimization BP Neural Network. Journal of Dynamics, 2012, 33(1):120-125.
[21] I Zaidi, M Chtourou, M Djemel. Robust neural control of discrete time uncertain nonlinear systems using sliding mode back propagation training algorithm. International Journal of Automation and Computing, 2019, 16(2):213-225.
[22] Y Q Fan, J P Shao, G T Sun. Optimized PID controller based on Beetle Antennae Search Algorithm for electro-hydraulic position servo control system. Sensors, 2019, 19(12):2727.
[23] C Ren, N An, J Z Wang, et al. Optimal parameters selection for BP Neural Network based on particle swarm optimization:A case study of wind speed forecasting. Knowledge-Based Systems, 2014, 56:226-239.
[24] A M Montes de Oca, T Stutzle, M Birattari. Frankenstein's PSO:A composite particle swarm optimization algorithm. IEEE Transactions on Evolutionary Computation, 2009, 13(5):1120-1132.
[25] P Poupart, N A Vlassis, J Hoey. An analytic solution to discrete Bayesian reinforcement learning. Machine Learning, Proceedings of the Twenty-Third International Conference (ICML 2006), Pittsburgh, Pennsylvania, USA, 2006:697-704.
[26] N A Kallioras, N D Lagaros, D N Avtzis. Pity Beetle Algorithm-A new metaheuristic inspired by the behavior of bark beetles. Advances in Engineering Software, 2018, 121:147-166.
[27] X M Xu, L Zhang, Y P Jiang, et al. Active control on path following and lateral stability for truck-trailer combinations. Arabian Journal for Science and Engineering, 2019, 44(2):1365-1377.
[28] X M Xu, Y P Jiang, H P Lee. Multi-objective optimal design of sandwich panels using a genetic algorithm. Engineering Optimization, 2017, 49(10):1665-1684.
