A hierarchical intelligent fault diagnosis algorithm based on convolutional neural network

被引：0

作者：

Qu J.-L. ^{[1
]}

Yu L. ^{[1
,2
]}

Yuan T. ^{[1
]}

Tian Y.-P. ^{[1
]}

Gao F. ^{[1
]}

机构：

[1] Department of Electrical Control and Command of Aviation Instrument, Qingdao Branch of Naval Aviation University, Qingdao

[2] Department of Navigation and Communication, Naval Submarine Academy, Qingdao

来源：

Kongzhi yu Juece/Control and Decision | 2019年 / 34卷 / 12期

关键词：

Convolutional neural network; Deep learning; Hierarchical fault diagnosis; Rolling bearing; Vibration signal;

D O I：

10.13195/j.kzyjc.2018.0253

中图分类号：

学科分类号：

摘要：

Traditional intelligent fault diagnosis methods largely depend on manual feature extraction and expert knowledge. However, complex working conditions of rotatory machinery make traditional fault diagnosis lack adaptivity and generalization. Aiming to solve the problems mentioned above, a novel CNN-based hierarchical fault diagnosis algorithm called CNN-HFD is proposed. Firstly, raw temporal vibration signals are segmented to enlarge samples. Then, several simple CNN networks are constructed according to fault categories and severities. Training samples divided by a certain time-step are sent to the CNN. Finally, signals to be identified are utilized as the input of the CNN-HFD. After hierarchical analysis, the fault category and fault severity are output at the end of the model. Experiments on rolling bearing datasets demonstrate that the proposed method can not only achieve 99.5 % fault recognition, but also keep a 97 % accuracy under variable loads, which verifies its good robustness and generalization. © 2019, Editorial Office of Control and Decision. All right reserved.

引用

页码：2619 / 2626

页数：7

共 26 条

[1] Lei Y., Lin J., He Z., A review on empirical mode decomposition in fault diagnosis of rotating machinery, Mechanical Systems & Signal Processing, 35, 1-2, pp. 108-126, (2013)
[2] Shao H., Jiang H., Zhao H., A novel deep autoencoder feature learning method for rotating machinery fault diagnosis, Mechanical Systems & Signal Processing, 95, C, pp. 187-204, (2017)
[3] Qu J.L., Yu L., Yuan T., Adaptive fault diagnosis algorithm for rolling bearings based on one-dimensional convolutional neural network, Chinese J of Scientific Instrument, 39, 7, pp. 134-143, (2018)
[4] Zhang W., Peng G., Li C., A new deep learning model for fault diagnosis with good anti-noise and domain adaptation ability on raw vibration signals, Sensors, 17, 2, (2017)
[5] Yu L., Qu J.L., Gao F., Feature extraction of weak vibration signal based on improved sparse coding, Chinese J of Scientific Instrument, 38, 3, pp. 711-717, (2017)
[6] Cai J.H., Hu W.W., Wang X.C., Rotor fault diagnosis based on Higer-order statistics, J of Vibration, Measurement & Diagnosis, 33, 2, pp. 298-301, (2013)
[7] He Y., Huang J., Zhang B., Approximate entropy as a nonlinear feature parameter for fault diagnosis in rotating machinery, Measurement Science & Technology, 23, 4, pp. 45603-45616, (2012)
[8] Long Y., He Y.G., Zhang Z., Switched-curent fault diagnosis based on entropy and Haar wavelet transform, Chinese J of Scientific Instrument, 36, 3, pp. 701-711, (2015)
[9] Zhang Y.Q., Zhang P.L., Wu D.H., Time-frequency feature extraction method based on cs-lbp for bearing signals, J of Vibration, Measurement & Diagnosis, 36, 1, pp. 22-27, (2016)
[10] Su Z.Q., Tang B.P., Yao J.B., Fault diagnosis method based on sensitive feature selection and manifold learning dimension reduction, J of Vibration and Shock, 33, 3, pp. 70-75, (2014)

← 1 2 3 →