The paper deals with the application of deep learning methods to rotating machines fault diagnosis. The main challenge is to design a fault diagnosis system connected with multisensory measurement system that will be sensitive and accurate enough in detecting weak changes in rotating machines. The experimental part of the research presents the test rig and results of high-speed multisensory measurements. Six states of a rotating machine, including a normal one and five states with loosened mounting bolts and small unbalancing of the shaft, are under study. The application of deep network architectures including multilayer perceptron, convolutional neural networks, residual networks, autoencoders and their combination was estimated. The deep learning methods allowed to identify the most informative sensors, then solve the anomaly detection and the multiclass classification problems. An autoencoder based on ResNet architecture demonstrated the best result in anomaly detection. The accuracy of the proposed network is up to 100% while the accuracy of an expert is up to 65%. A one-dimensional convolutional neural network combined with a multilayer perceptron that contains a pretrained encoder demonstrated the best result in multiclass classification. The detailed fault detection accuracy with the determination of the specific fault is 83.3%. The combinations of known deep network architectures and application of the proposed approach of pretraining of the encoders together with using a block of inputs for one prediction demonstrated high efficiency.
LeiYYangBJiangX, et al.Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process2020; 138: 106587.
2.
WangXLiuF. Triplet loss guided adversarial domain adaptation for bearing fault diagnosis. Sensors (Switzerland)2020; 20: 1–19.
3.
ZouLLiYXuF. An adversarial denoising convolutional neural network for fault diagnosis of rotating machinery under noisy environment and limited sample size case. Neurocomputing2020; 407: 105–120.
4.
GoodfellowIBengioYCourvilleA. Deep learning. MIT Press, 2016.
5.
CongTBaranowskiJ. Binary classifier for fault detection based on Gaussian model and PCA ⁎. IFAC-PapersOnLine2018; 51: 1317–1323.
6.
TheisslerA. Detecting known and unknown faults in automotive systems using ensemble-based anomaly detection. Knowl Based Syst2017; 123: 163–173.
7.
NooriMHassaniHJavaherianA,et al.Automatic fault detection in seismic data using Gaussian process regression. J Appl Geophys2019; 163: 117–131.
8.
HochreiterSSchmidhuberJ. Long short-term memory. Neural Comput1997; 9: 1735–1780.
9.
RoelofsCMALutzM-AFaulstichS,et al.Autoencoder-based anomaly root cause analysis for wind turbines. Energy and AI2021; 4: 100065.
10.
Gauthama RamanMRDongWMathurA. Deep autoencoders as anomaly detectors: method and case study in a distributed water treatment plant. Computers and Security2020; 99: 102055.
11.
KönigFSousCOuald ChaibA,et al.Machine learning based anomaly detection and classification of acoustic emission events for wear monitoring in sliding bearing systems. Tribol Int2021; 155: 106811.
12.
TsaiDMJenPH. Autoencoder-based anomaly detection for surface defect inspection. Adv Eng Inf2021; 48: 101272.
13.
YuQKavithaMKuritaT. Autoencoder framework based on orthogonal projection constraints improves anomalies detection. Neurocomputing2021; 450: 372–388.
14.
NguyenHDTranKPThomasseyS,et al.Forecasting and anomaly detection approaches using LSTM and LSTM autoencoder techniques with the applications in supply chain management. Int J Inf Manage2021; 57: 102282.
15.
LiuXZhouQZhaoJ,et al.Fault diagnosis of rotating machinery under noisy environment conditions based on a 1-D convolutional autoencoder and 1-D convolutional neural network. Sensors (Switzerland)2019; 19: 1–20.
16.
LiYChaiYZhouH,et al.A novel feature extraction method based on discriminative graph regularized autoencoder for fault diagnosis. IFAC-PapersOnLine2019; 52: 272–277.
17.
YangZKongCWangY,et al.Fault diagnosis of mine asynchronous motor based on MEEMD energy entropy and ANN. Comput Electr Eng2021; 92: 107070.
18.
KumarAGandhiCPZhouY,et al.Improved deep convolution neural network (CNN) for the identification of defects in the centrifugal pump using acoustic images. Appl Acoust2020; 167: 107399.
19.
WangXMaoDLiX. Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network. Measurement: Journal of the International Measurement Confederation2021; 173: 108518.
20.
AnJAiP. Deep domain adaptation model for bearing fault diagnosis with riemann metric correlation alignment. Math Probl Eng2020; 2020: 1–14.
21.
DiasATurcatoASestitoG, et al.A New method for fault detection of rotating machines in motion control applications using PROFIdrive information and support vector machine classifier. J Dyn Syst Meas Contr2021; 143: 439–447.
22.
BelagouneSBaliNBakdiA,et al.Deep learning through LSTM classification and regression for transmission line fault detection, diagnosis and location in large-scale multi-machine power systems. Measurement2021; 177: 109330.
23.
HanTLiuCYangW,et al.Deep transfer network with joint distribution adaptation: a new intelligent fault diagnosis framework for industry application. ISA Trans2020; 97: 269–281.
24.
LiuXHuangHXiangJ. A personalized diagnosis method to detect faults in gears using numerical simulation and extreme learning machine. Knowl Based Syst2020; 195: 105653.
25.
GaoYLiuXXiangJ. FEM Simulation-Based generative adversarial networks to detect bearing faults. IEEE Trans Ind Inf2020; 16: 4961–4971.
26.
KornaevAKornaevaESavinL, et al.Enhanced hydrodynamic lubrication of lightly loaded fluid-film bearings due to the viscosity wedge effect. Tribol Int2021; 160: 107027.
27.
BabinA.PolyakovR. Imitation model of unbalanced rotor on fluid-film bearings. in Vibroengineering procedia vol. 3238–44 (JVE International, 2020).
28.
KazakovY.KornaevA.PolyakovR. Rotary machines diagnosis systems based on feed forward neural networks. in Proceedings - 2020 International Russian Automation Conference, RusAutoCon, Lithuania 2020 (2020). doi:10.1109/RusAutoCon49822.2020.9208118.
HeKZhangXRenS,et al.Deep Residual Learning for Image Recognition.
37.
SakH.SeniorA.BeaufaysF. Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition. (2014).
38.
LeeJLeeYCKimJT. Fault detection based on one-class deep learning for manufacturing applications limited to an imbalanced database. J Manuf Syst2020; 57: 357–366.
MaMSunCChenX. Deep coupling autoencoder for fault diagnosis with multimodal sensory data. IEEE Trans Ind Inf2018; 14: 1137–1145.
47.
WangLZhangZXuJ,et al.Wind turbine blade breakage monitoring with deep autoencoders. IEEE Trans Smart Grid2018; 9: 2824–2833.
48.
KholiavchenkoMSirazitdinovIKubrakK, et al.Contour-aware multi-label chest X-ray organ segmentation. Int J Comput Assist Radiol Surg2020; 15: 425–436.
49.
StebakovInKornaevAvPopovSg,et al.Cluster analysis for detecting groups of defects rotary support system. Fundamental and Applied Problems of Engineering and Technology2020; 5: 73–79.
50.
Hosseinpour-ZarnaqMOmidMBiabani-AghdamE. Fault diagnosis of tractor auxiliary gearbox using vibration analysis and random forest classifier. Information Processing in Agriculture2021: 1–8. doi:10.1016/J.INPA.2021.01.002
51.
ZhangKTangBDengL,et al.A hybrid attention improved ResNet based fault diagnosis method of wind turbines gearbox. Measurement2021; 179: 109491.
52.
GoyalDDhamiSSPablaBS. Vibration response-based intelligent Non-contact fault diagnosis of bearings. Journal of Nondestructive Evaluation, Diagnostics and Prognostics of Engineering Systems 20212021; 4: 4.
53.
KönigFJacobsGStratmannA,et al.Fault detection for sliding bearings using acoustic emission signals and machine learning methods. IOP Conf Ser: Mater Sci Eng2021; 1097: 012013.
54.
LIYDUXWANF,et al.Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging. Chin J Aeronaut2020; 33: 427–438.
