Due to random uncertainty factors, such as the change in operating conditions of rolling bearings and noise interference, it is easy to lead to incomplete network feature extraction and the inability to capture local singular information of fault mutations. A parallel two-dimensional depthwise separable residual neural network (P2D-DSResNet) is proposed in this paper to address the aforementioned issues. By using Gramian angular difference field (GADF) and continuous wavelet transform (CWT), one-dimensional vibration signals can be transformed into two-dimensional time frequency images while preserving the complete time-frequency domain information. The P2D-DSResNet uses depthwise separable convolution instead of ordinary convolution in residual modules, which enhances feature learning ability and improves the model’s feature extraction capability for better fault diagnosis in high noise and varying operating conditions. The bearing data obtained from a fault simulation testbed are used for experimentation and analysis. A comparative analysis with other convolutional neural network methods demonstrates that the optimized algorithm model has good generalization ability and high fault recognition accuracy.
ZHOUJ .Intelligent manufacturing—main direction of“made in China 2025”[J].China Mechanical Engineering,2015,26(17):2273-2284.(in Chinese)
[3]
WANGL, LIUZ W, MIAOQ,et al .Time-frequency analysis based on ensemble local mean decomposition and fast kurtogram for rotating machinery fault diagnosis[J].Mechanical Systems and Signal Processing,2018,103:60-75.
LIH K, YANGR, RENY J,et al .Rolling element bearing diagnosis using particle filter and kurtogram[J].Journal of Mechanical Engineering,2017,53(3):63-72.(in Chinese)
GUY H, ZHUT T, RAOW J,et al. Fault diagnosis for rolling bearing based on EMD binarization image and CNN[J].Journal of Vibration,Measurement & Diagnosis,2021,41(1):105-113.(in Chinese)
[8]
ZHANGW, PENGG L, LIC H,et al .A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals[J].Sensors,2017,17(2):425.
[9]
JIAX J, HANY, LIY J,et al .Condition monitoring and performance forecasting of wind turbines based on denoising autoencoder and novel convolutional neural networks[J].Energy Reports,2021,7:6354-6365.
LIY B, WANGL, JIANGL. Rolling bearing fault diagnosis based on DBN algorithm improved with PSO[J]. Journal of Vibration and Shock, 2020, 39(5): 89-96. (in Chinese)
[12]
WANGL H, ZHAOX P, WUJ X,et al. Motor fault diagnosis based on short-time Fourier transform and convolutional neural network[J].Chinese Journal of Mechanical Engineering, 2017,30(6): 1357-1368.
LIANGR J, RANW F, YUC L, et al. Recognition of gearbox operation fault state based on CWT-CNN[J]. Journal of Aerospace Power, 2021, 36(12): 2465-2473.(in Chinese)
[15]
JIANGY Y, XIEJ Y .VMD-RP-CSRN based fault diagnosis method for rolling bearings[J].Electronics,2022,11(23):4046.
ZHAOX Q, LUOW L .Improved convolutional Lenet-5 neural network for bearing fault diagnosis[J].Journal of Electronic Measurement and Instrumentation,2022,36(6):113-125.(in Chinese)
HOUD X, MUJ T, FANGC,et al. Fault diagnosis of variable speed bearings based on GADF and ResNet34 introduced transfer learning[J]. Journal of Northeastern University (Natural Science), 2022, 43(3): 383-389.(in Chinese)
[20]
JAWADEKARA, PARASKARS, JADHAVS,et al .Artificial neural network-based induction motor fault classifier using continuous wavelet transform[J].Systems Science & Control Engineering,2014,2(1):684-690.
FUZ G, WANGS Y, GAOY C,et al .Research on fault diagnosis model of rotating machinery based on two-channel input LetNet-5 convolution neural network[J].Thermal Power Generation,2023,52(3):81-87.(in Chinese)