Compound fault signals interfere with one another, resulting in an inconspicuous feature extraction that requires sophisticated signal processing techniques and expert experience. However, good online diagnostic methods are not available to carry out this process. This paper proposes a method based on Residual Connection and Squeeze-and-Excitation Unet (RSEUnet) and one-dimensional convolutional neural network (1DCNN). The process includes fault separation and diagnosis. First, the feature extraction module of the RSEUnet network introduces an attention mechanism and a residual connection that adaptively assigns various weights to different channels. This model is used to train the maps of the fault signal after time-frequency transformation. Ideal binary masks with excellent performance are the training targets to complete the intelligent separation of compound faults. Second, the 1DCNN is used as a feature learning model to efficiently learn the features of single faults from time-domain signals. An embedded system consisting of a Jetson Nano and a signal acquisition circuit is then built to perform online diagnosis. The test is carried out on the fault experimental platform. Results show that the method has an accuracy of 99.71%, making it highly suitable for the diagnosis of bearing compound faults.
AlzubaidiLZhangJHumaidiAJ, et al. (2021) Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data8(1): 1–74.
2.
DengWLiZLiX, et al. (2022) Compound fault diagnosis using optimized MCKD and sparse representation for rolling bearings. IEEE Transactions on Instrumentation and Measurement71: 1–9.
3.
DibajAEttefaghMMHassannejadR, et al. (2021) A hybrid fine-tuned VMD and CNN scheme for untrained compound fault diagnosis of rotating machinery with unequal-severity faults. Expert Systems with Applications167: 114094.
4.
DongJYanLXiaY (2021) Compound fault separation and diagnosis method based on FSA-CNN and DAN. In: 2021 CAA symposium on fault detection, supervision, and safety for technical processes (SAFEPROCESS), Chengdu, China, 17–18 December, pp. 1–6. New York: IEEE.
5.
DongJYanLXiaY, et al. (2020) A CNN-ELM compound fault diagnosis method based on joint distribution modification. In: 2020 7th international conference on information, cybernetics, and computational social systems (ICCSS), Guangzhou, China, 13–15 November, pp. 359–364. New York: IEEE.
6.
GaoSShiSZhangY (2022) Rolling bearing compound fault diagnosis based on parameter optimization MCKD and convolutional neural network. IEEE Transactions on Instrumentation and Measurement71: 1–8.
7.
GongXZhiZFengK, et al. (2022) Improved DCNN based on multi-source signals for motor compound fault diagnosis. Machines10(4): 277.
8.
GuoJSiZXiangJ (2022) A compound fault diagnosis method of rolling bearing based on wavelet scattering transform and improved soft threshold denoising algorithm. Measurement196: 111276.
9.
HanSLiuXYangY, et al. (2021) Intelligent algorithm for variable scale adaptive feature separation of mechanical composite fault signals. Energies14(22): 7702.
10.
HuJShenLSunG (2018) Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Salt Lake City, UT, 18–23 June, pp. 7132–7141. New York: IEEE.
11.
HuangRLiaoYZhangS, et al. (2018) Deep decoupling convolutional neural network for intelligent compound fault diagnosis. IEEE Access7: 1848–1858.
12.
IoffeSSzegedyC (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. arXiv preprint arXiv:1502.03167.
13.
JuniorRFRDos Santos AreiasIACamposMM, et al. (2022) Fault detection and diagnosis in electric motors using 1D convolutional neural networks with multi-channel vibration signals. Measurement190: 110759.
14.
LeeCYChengYH (2020) Motor fault detection using wavelet transform and improved PSO-BP neural network. Processes8(10): 1322.
15.
LiCYuGFuB, et al. (2019) Fault separation and detection for compound bearing-gear fault condition based on decomposition of marginal Hilbert spectrum. IEEE Access7: 110518–110530.
16.
LinKWEBalamuraliBTKohE, et al. (2020) Singing voice separation using a deep convolutional neural network trained by ideal binary mask and cross entropy. Neural Computing and Applications32(4): 1037–1050.
17.
LinMChenQYanS (2013) I network in network. arXiv preprint arXiv:1312.4400.
18.
PangXWeiZTongY (2022) Gear fault diagnosis method based on SCGAN network, Chinese vibration. Test and Diagnosis42(2): 358–364.
19.
PengBWanSBiY, et al. (2020) Automatic feature extraction and construction using genetic programming for rotating machinery fault diagnosis. IEEE Transactions on Cybernetics51(10): 4909–4923.
20.
PuleMMatsebeOSamikannuR (2022) Application of PCA and SVM in fault detection and diagnosis of bearings with varying speed. Mathematical Problems in Engineering2022: 5266054.
21.
SinghAKumarA (2022) EEMD-CNN based method for compound fault diagnosis of bearing. In: IEEE international conference on cybernetics and computational intelligence (CyberneticsCom), Malang, Indonesia, 16–18 June, pp. 253–258. New York: IEEE.
22.
SunGDWangYRSunCF, et al. (2019) Intelligent detection of a planetary gearbox composite fault based on adaptive separation and deep learning. Sensors19(23): 5222.
23.
TengWDingXChengH, et al. (2019) Compound faults diagnosis and analysis for a wind turbine gearbox via a novel vibration model and empirical wavelet transform. Renewable Energy136: 393–402.
24.
WangQDengLFZhaoRZ (2022) Rolling bearing fault identification based on improved one-dimensional convolutional neural network. Chinese Vibration and Shock41(3): 216–223.
25.
WangXMaoDLiX (2021) Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network. Measurement173: 108518.
26.
XiaMLiTXuL, et al. (2017) Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks. IEEE/ASME Transactions on Mechatronics23(1): 101–110.
27.
YangYXiC (2022) Rolling bearing fault diagnosis based on MFDFA-SPS and ELM. Mathematical Problems in Engineering2022: 4034477.
28.
ZhangCYulingLIUFangyiWAN, et al. (2020) Multi-faults diagnosis of rolling bearings via adaptive customization of flexible analytical wavelet bases. Chinese Journal of Aeronautics33(2): 407–417.
29.
ZhangJXuBWangZ, et al. (2021) An FSK-MBCNN based method for compound fault diagnosis in wind turbine gearboxes. Measurement172: 108933.
30.
ZhangQLiJDingW, et al. (2023) Mechanical fault intelligent diagnosis using attention-based dual-scale feature fusion capsule network. Measurement207: 112345.
31.
ZhangXZouYShiW (2017) Dilated convolution neural network with LeakyReLU for environmental sound classification. In: 2017 22nd international conference on digital signal processing (DSP), London, 23–25 August, pp. 1–5. New York: IEEE.
32.
ZhaoYFanYLiH, et al. (2022) Rolling bearing composite fault diagnosis method based on EEMD fusion feature. Journal of Mechanical Science and Technology36(9): 4563–4570.
