The complexity of mechanical equipment and the harsh working environment make bearing faults susceptible to strong background noise interference. As a result, it is challenging to learn the crucial information from vibration data, leading to a significant decline in the performance of most fault diagnostic models. To overcome the above deficiencies, a novel fault diagnostic model based on signal denoising and dual branch feature fusion under strong noise interference (SDFF) is proposed. Firstly, the raw vibration signals are decomposed using Variational Mode Decomposition (VMD), followed by computing the Permutation Entropy (PE) to identify noise components. Subsequently, effective signal components are selected for signal reconstruction to achieve effective denoising. Secondly, a dual-branch convolutional neural network (CNN) model is constructed, and a multi-modal fusion mechanism is applied to integrate the fault features extracted by the dual-branch CNN model. This fusion process enhances the comprehensiveness of the features by combining information from multiple modalities. Finally, a softmax classifier is employed to identify different types of bearing faults. Two bearing datasets are adopted to validate the validity of SDFF. Compared to various baseline methods, SDFF owns superior noise resistance, feature extraction capabilities, and better diagnostic performance.
XiaoXQJianWJXiaoWH. Fault diagnosis methods of rolling bearing: a general review. Key Eng Mater2011; 1272(480–481): 986–992.
2.
YanGChenJBaiY, et al. A survey on fault diagnosis approaches for rolling bearings of railway vehicles. Processes2022; 10(4): 724.
3.
WaziralilahNFAbuALimMH, et al. A review on convolutional neural network in bearing fault diagnosis. MATEC Web Conf2019; 255: 06002.
4.
PengBBiYXueB, et al. A survey on fault diagnosis of rolling bearings. Algorithms2022; 15(10): 347.
5.
DevendraSRiteshKDSurendraPSM. Fault diagnosis of rolling element bearing: a review. Electrochem Soc Trans2022; 107(1): 14931–14941.
6.
HuWCGeXWuJY, et al. Vibration-based bearing fault diagnosis of high-speed trains: a literature review. High Speed Railw2023; 1(4): 219–223.
7.
KhadersabA. Machine learning algorithms for rotating machinery bearing fault diagnostics. Mater Today Proc2021; 44(P6): 4931–4933.
8.
HarmoucheJDelphaCDialloD. Improved fault diagnosis of ball bearings based on the global spectrum of vibration signals. IEEE Trans Energy Convers2015; 30(1): 376–383.
9.
GaoKMZhangHSongYD. Design of active suspension sliding mode controller based on multi-objective genetic algorithm. Electromech Eng Technol2022; 51(3): 287–291.
10.
MengDBWangHTYangSY, et al. Fault analysis of wind power rolling bearing based on EMD feature extraction. Comput Model Eng Sci2022; 130(1): 543–558.
11.
AltmannJMathewJ. Multiple band-pass autoregressive demodulation for rolling-element bearing fault diagnosis. Mech Syst Signal Process2001; 15(5): 963–977.
12.
DhirajNJongwonS. Bearing fault detection and diagnosis using case western reserve university dataset with deep learning approaches: a review. IEEE Access2020; 8: 93155–93178.
13.
CenJYangZHLiuX, et al. A review of data-driven machinery fault diagnosis using machine learning algorithms. J Vib Eng Technol2022; 10(7): 2481–2507.
14.
FernandesMCorchadoJMMarreirosG. Machine learning techniques applied to mechanical fault diagnosis and fault prognosis in the context of real industrial manufacturing use-cases: a systematic literature review. Appl Intell2022; 52(12): 31–35.
15.
ZhuZLeiYQiG, et al. A review of the application of deep learning in intelligent fault diagnosis of rotating machinery. Measurement2023; 206: 112346.
16.
Duy-TangHHee-JunK. A survey on deep learning based bearing fault diagnosis. Neurocomputing2018; 335: 327–335.
17.
ZhangTLiuSZhangS. Review on fault diagnosis on the rolling bearing. J Phys Conf Ser2021; 1820(1): 012107.
18.
JanssensOSlavkovikjVVervischB, et al. Convolutional neural network-based fault detection for rotating machinery. J Sound Vib2016; 377: 331–345.
19.
YuLQuJGaoF, et al. A novel hierarchical algorithm for bearing fault diagnosis based on stacked LSTM. Shock Vib2019; 2019: 1–10.
20.
DingXXHeQB. Energy-fluctuated multiscale feature learning with deep convnet for intelligent spindle bearing fault diagnosis. IEEE Trans Instrum Meas2017; 66(8): 1926–1935.
21.
PanHHHeXXXieT, et al. An improved bearing fault diagnosis method using one-dimensional CNN and LSTM. J Mech Eng2018; 64: 443–452.
22.
ZhangXNZhuHLXinL, et al. A bearing fault diagnosis method based on dual channel feature fusion. Locomot Electr Transm2023; 6: 39–48.
23.
QiALLiLZhuYX, et al. Fault recognition of dual channel CNN rolling bearings based on fused features. Mach Electron2021; 39(5): 15–19.
24.
TangHTLiBGaoSB. CNN-LSTM bearing fault diagnosis method based on dual channel feature fusion. Digit Manuf Sci2022; 20(4): 253–257.
25.
JinGZhuTAkramWM, et al. An adaptive anti-noise neural network for bearing fault diagnosis under noise and varying load conditions. IEEE Access2020; 8: 74793–74807.
26.
QiaoMYanSTangX, et al. Deep convolutional and LSTM recurrent neural networks for rolling bearing fault diagnosis under strong noises and variable loads. IEEE Access2020; 8: 66257–66269.
27.
WangQXuFY. A novel rolling bearing fault diagnosis method based on Adaptive Denoising Convolutional Neural Network under noise background. Measurement2023; 218: 113209.
28.
LiXZhangWDingQ, et al. Diagnosing rotating machines with weakly supervised data using deep transfer learning. IEEE Trans Industr Inform2020; 16(3): 1688–1697.
29.
ZhangWPengGLiC, et al. A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals. Sensors2017; 17(2): 425.
30.
XieFYLiGWangLI, et al. Improving the diagnosis of gearbox faults using time-series grayscale images and deep learning. Comput Eng Appl2024; 60(13): 338–344.
31.
DragomiretskiyKZossoD. Variational mode decomposition. IEEE Trans Signal Process2014; 62(3): 531–544.
32.
MaZQLiYCRuanWY, et al. Feature extraction of rolling bearing faults based on variational mode decomposition and spectral kurtosis method. J Electron Meas Instrum2017; 31(11): 1782–1787.
33.
SingJBLiuJIRunRG, et al. Bearing fault diagnosis based on VMD-1DCNN-GRU. J Jilin Univ (Nat Sci)2024; 42(2): 1–9.
34.
ZhaoHSGuoSWGaoD. Feature extraction of bearing faults based on singular value decomposition and variational mode decomposition. Vib Shock2016; 35(22): 183–188.
35.
DongLNDengADFanYS, et al. Fault diagnosis of rolling bearings based on VMD and improved DenseNet. J Power Eng2023; 43(11): 1500–1505+1522.
36.
ZhangBCSunSQXiaoJY, et al. Research on gearbox fault diagnosis method based on vmd and optimized LSTM. Appl Sci2023; 13(21): 11637.
37.
JinZZDiaoCHeDQ, et al. Bearing fault diagnosis based on vmd and improved CNN. J Fail Anal Prev2022; 23(1): 165–175.
38.
ChonZZZhangMQLiuSJ, et al. Transmission shaft fault diagnosis based on variational modal decomposition feature fusion. J Phys Conf Ser2022; 2224(1): 012103.
39.
SaeedRMehdiASStefaniaS, et al. Fault diagnosis in industrial rotating equipment based on permutation entropy, signal processing, and multi-output neuro-fuzzy classifier. Expert Syst Appl2022; 206: 117754.
WangHWFangZWWangHL, et al. A novel time-frequency analysis method for fault diagnosis based on generalized S-transform and synchroextracting transform. Meas Sci Technol2024; 35(3): 036101.
42.
ZhangTZDaiJ. Mechanical fault diagnosis methods based on convolutional neural network: a review. J Phys Conf Ser2021; 1750(1): 012048.
43.
JiaoJYZhaoMLinJ, et al. A comprehensive review on convolutional neural network in machine fault diagnosis. Neurocomputing2020; 417: 36–63.
44.
ZhangQDengLF. An intelligent fault diagnosis method of rolling bearings based on short-time Fourier transform and convolutional neural network. J Fail Anal Prev2023; 23(2): 795–811.
45.
HanSZNiuPJLuoSJ, et al. A novel deep convolutional neural network combining global feature extraction and detailed feature extraction for bearing compound fault diagnosis. Sensors2023; 23(19): 8060.
46.
KangJLuoYJWangP, et al. Fault diagnosis of rotating machinery under complex conditions based on multi-scale convolutional neural networks. J Phys Conf Ser2023; 2658(1): 20–48.
47.
WangYMCaoQG. A multiscale convolution neural network for bearing fault diagnosis based on frequency division denoising under complex noise conditions. Complex Intell Syst2022; 9(4): 4263–4285.
48.
JinYRQinCJZhangZN, et al. A multi-scale convolutional neural network for bearing compound fault diagnosis under various noise conditions. Sci China Technol Sci2022; 65(11): 2551–2563.
49.
XuYDYanXAFengK, et al. Attention-based multiscale denoising residual convolutional neural networks for fault diagnosis of rotating machinery. Reliab Eng Syst Saf2022; 226: 108714.
50.
WangJXZhangCSYuD, et al. Rolling bearing fault diagnosis method based on SSAE and softmax classifier with improved K-fold cross-validation. Meas Sci Technol2022; 33: 105110.
51.
ChenBJChenXLShenBM, et al. Application of CNN-LSTM deep neural network in fault diagnosis of rolling bearings. J Xi’an Jiaotong Univ2021; 55(6): 28–36.
