The health of rolling bearing is of great importance for the normal operation of rotating machinery. The fault diagnosis process can be roughly summarized as signal processing, feature extraction, and fault classification. In this paper, a novel feature extraction and fault diagnosis method with fractional order back-propagation neural network is put forward. The new sine cosine algorithm optimized variational mode decomposition is performed on vibration signals, and the fault feature vectors are selected and built by singular value decomposition. Inspired by the fractional order calculus, a fractional order back-propagation neural network is employed to realize fault classification. The capability of the developed fault diagnosis algorithm is comprehensively evaluated via benchmark bearing data. The experimental results demonstrate that the designed method substantially extracts bearing defect features, increases classification accuracy and efficiency, and also outperforms existing algorithms.
AasiATabatabaeiRAasiE, et al. (2021) Experimental investigation on time-domain features in the diagnosis of rolling element bearings by acoustic emission. Journal of Vibration and Control28: 2585–2595. DOI: 10.1177/10775463211016130.
2.
AnZLiSWangJ, et al. (2019) Generalization of deep neural network for bearing fault diagnosis under different working conditions using multiple kernel method. Neurocomputing352: 42–53. DOI: 10.1016/j.neucom.2019.04.010.
3.
ChenMRChenBPZengGQ, et al. (2020) An adaptive fractional-order BP neural network based on extremal optimization for handwritten digits recognition. Neurocomputing391: 260–272. DOI: 10.1016/j.neucom.2018.10.090.
4.
ChoSChoiMGaoZ, et al. (2021) Fault detection and diagnosis of a blade pitch system in a floating wind turbine based on Kalman filters and artificial neural networks. Renewable Energy169: 1–13. DOI: 10.1016/j.renene.2020.12.116.
5.
ChenXYangYCuiZ, et al. (2019) Vibration fault diagnosis of wind turbines based on variational mode decomposition and energy entropy. Energy174: 1100–1109. DOI: 10.1016/j.energy.2019.03.057.
6.
DingZChenCWenS, et al. (2022) Lag projective synchronization of nonidentical fractional delayed memristive neural networks. Neurocomputing469: 138–150. DOI: 10.1016/j.neucom.2021.10.061.
7.
DragomiretskiyKZossoD (2014) Variational mode decomposition. IEEE Transactions on Signal Processing62(3): 531–544. DOI: 10.1109/TSP.2013.2288675.
8.
FengFWuCZhuJ, et al. (2020) Research on multitask fault diagnosis and weight visualization of rotating machinery based on convolutional neural network. Journal of the Brazilian Society of Mechanical Sciences and Engineering42(11): 603. DOI: 10.1007/s40430-020-02688-6.
9.
GaoSXuLZhangY, et al. (2022) Rolling bearing fault diagnosis based on SSA optimized self-adaptive DBN. ISA Transactions128: 485–502. DOI: 10.1016/j.isatra.2021.11.024.
10.
GillesJ (2013) Empirical wavelet transform. IEEE Transactions on Signal Processing61(16): 3999–4010. DOI: 10.1109/TSP.2013.2265222.
11.
HeDLiuCJinZ, et al. (2022) Fault diagnosis of flywheel bearing based on parameter optimization variational mode decomposition energy entropy and deep learning. Energy239: 122108. DOI: 10.1016/j.energy.2021.122108.
12.
HuangCGHuangHZLiYF, et al. (2021) A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing. Journal of Manufacturing Systems61: 757–772. DOI: 10.1016/j.jmsy.2021.03.012.
13.
IngemarsdotterEKambanouMLJamsinE, et al. (2021) Challenges and solutions in condition-based maintenance implementation - a multiple case study. Journal of Cleaner Production296: 126420. DOI: 10.1016/j.jclepro.2021.126420.
14.
KhadersabAShivakumarS (2018) Vibration analysis techniques for rotating machinery and its effect on bearing faults. Procedia Manufacturing20: 247–252. DOI: 10.1016/j.promfg.2018.02.036.
15.
LiJChenWHanK, et al. (2020b) Fault diagnosis of rolling bearing based on GA-VMD and improved WOA-LSSVM. IEEE Access8: 166753–166767. DOI: 10.1109/ACCESS.2020.3023306.
16.
LiSFangHLiuX (2018) Parameter optimization of support vector regression based on sine cosine algorithm. Expert Systems with Applications91: 63–77. DOI: 10.1016/j.eswa.2017.08.038.
17.
LiuRYangBZioE, et al. (2018) Artificial intelligence for fault diagnosis of rotating machinery: a review. Mechanical Systems and Signal Processing108: 33–47. DOI: 10.1016/j.ymssp.2018.02.016.
18.
MirjaliliS (2016) SCA: a sine cosine algorithm for solving optimization problems. Knowledge-Based Systems96: 120–133. DOI: 10.1016/j.knosys.2015.12.022.
19.
MishraSKShakyaPBabureddyV, et al. (2021) An approach to improve high-frequency resonance technique for bearing fault diagnosis. Measurement178: 109318. DOI: 10.1016/j.measurement.2021.109318.
20.
PodlubnyI (1999) Fractional Differential Equations - an Introduction to Fractional Derivatives, Fractional Differential Equations, to Methods of Their Solution and Some of Their Applications. Amsterdam, Netherlands: Elsevier. DOI: 10.1016/s0076-5392(99)x8001-5.
21.
QuJLiuFMaY, et al. (2019) A neural-network-based method for RUL prediction and SOH monitoring of lithium-ion battery. IEEE Access7: 87178–87191. DOI: 10.1109/ACCESS.2019.2925468.
22.
QuatriniECostantinoFDi GravioG, et al. (2020) Condition-based maintenance - an extensive literature review. Machines8(2): 31. DOI: 10.3390/machines8020031.
23.
RuderS (2016) An overview of gradient descent optimization algorithms. CoRR abs1609: 04747.
24.
TangSShenCWangD, et al. (2018) Adaptive deep feature learning network with Nesterov momentum and its application to rotating machinery fault diagnosis. Neurocomputing305: 1–14. DOI: 10.1016/j.neucom.2018.04.048.
25.
WangJWenYGouY, et al. (2017) Fractional-order gradient descent learning of BP neural networks with Caputo derivative. Neural networks: the official journal of the International Neural Network Society89: 19–30. DOI: 10.1016/j.neunet.2017.02.007.
26.
WeiJHuangHYaoL, et al. (2021) New imbalanced bearing fault diagnosis method based on sample-characteristic oversampling technique (SCOTE) and multi-class LS-SVM. Applied Soft Computing101: 107043. DOI: 10.1016/j.asoc.2020.107043.
27.
XiaoDDingJLiX, et al. (2019) Gear fault diagnosis based on kurtosis criterion VMD and SOM neural network. Applied Sciences9(24): 5424. DOI: 10.3390/app9245424.
28.
XiongJZhangQSunG, et al. (2016) An information fusion fault diagnosis method based on dimensionless indicators with static discounting factor and KNN. IEEE Sensors Journal16(7): 2060–2069. DOI: 10.1109/jsen.2015.2497545.
29.
XuZLiCYangY (2020) Fault diagnosis of rolling bearing of wind turbines based on the variational mode decomposition and deep convolutional neural networks. Applied Soft Computing95: 106515. DOI: 10.1016/j.asoc.2020.106515.
30.
YaoJJiangGGaoS, et al. (2014) Particle swarm optimization-based neural network control for an electro-hydraulic servo system. Journal of Vibration and Control20(9): 1369–1377. DOI: 10.1177/1077546312472926.
31.
YeMYanXJiaM (2021) Rolling bearing fault diagnosis based on VMD-MPE and PSO-SVM. Entropy23(6): 762. DOI: 10.3390/e23060762.
32.
ZhangL (2015) New procedure and index for the parameter optimization of complex wavelet based resonance demodulation. Journal of Mechanical Engineering51(3): 129. DOI: 10.3901/jme.2015.03.129.
33.
ZhangQChenSFanZP (2021) Bearing fault diagnosis based on improved particle swarm optimized VMD and SVM models. Advances in Mechanical Engineering13(6): 168781402110284. DOI: 10.1177/16878140211028451.
34.
ZhengJSuMYingW, et al. (2021) Improved uniform phase empirical mode decomposition and its application in machinery fault diagnosis. Measurement179: 109425. DOI: 10.1016/j.measurement.2021.109425.
