Fault diagnosis of planetary gear backlash based on motor current and Fisher criterion optimized sparse autoencoder

Abstract

Planetary gear reducer is widely applied in various transmission equipment, and its performance highly affects the operation of a machine. The appearance of unreasonable backlash in planetary gear reducer may lead to undesirable vibration, which may accelerate the degradation of equipment and eventually cause premature failure. In traditional condition-based monitoring (CBM), sensors such as accelerometers have been utilized to detect the fault of planetary gear. However, the complexity and integration of planetary gear limit the installation and application of vibration sensors in practice. In this case, the current signal from motor, as a convenient real-time monitoring approach, is introduced into the CBM of the planetary gear. In this paper, a fault diagnosis method based on drive motor current signal analysis (MCSA) is presented to identify the backlash fault in a planetary gear reducer. In this method, frequency domain data of the original current signal is found and used to automatically extract fault features. A deep sparse autoencoder (DSAE) extracts the required features. In particular, the Fisher criterion is introduced to evaluate the sensitivity of these features. It then selects the most effective ones for improving diagnostic accuracy as well as diagnostic efficiency. Experimental test data shows that under different load conditions, this method outperforms other typical fault diagnosis methods and exhibits the best performance.

Keywords

fault diagnosis gear backlash planetary gear reducer motor current signal analysis sparse autoencoder Fisher criterion feature selection

Get full access to this article

View all access options for this article.

References

Wang

Zhang

, et al. Intelligent fault diagnosis of planetary gearbox based on adaptive normalized CNN under complex variable working conditions and data imbalance. Measurement 2021; 180: 109565.

Chen

Huang

, et al. Research on gears’ dynamic performance influenced by gear backlash based on fractal theory. Appl Surf Sci 2014; 313: 325–332.

Liu

Zhao

Liu

. Frequency and vibration characteristics of high-speed gear-rotor-bearing system with tooth root crack considering compound dynamic backlash. Shock Vib 2019; 2019: 1–19.

Shi

J-f

Gou

X-f

Zhu

L-y

. Modeling and analysis of a spur gear pair considering multi-state mesh with time-varying parameters and backlash. Mech Mach Theor 2019; 134: 582–603.

Huang

Xiong

, et al. Nonlinear dynamic modelling and analysis for a spur gear system with time-varying pressure angle and gear backlash. Mech Syst Signal Process 2019; 132: 18–34.

Azamfar

Singh

Bravo-Imaz

, et al. Multisensor data fusion for gearbox fault diagnosis using 2-D convolutional neural network and motor current signature analysis. Mech Syst Signal Process 2020; 144: 106861.

Qian

Wang

, et al. An intelligent fault diagnosis framework for raw vibration signals: adaptive overlapping convolutional neural network. Meas Sci Technol 2018; 29: 095009.

Singh

Azamfar

Ainapure

, et al. Deep learning-based cross-domain adaptation for gearbox fault diagnosis under variable speed conditions. Meas Sci Technol 2020; 31: 055601.

Sun

, et al. Customized multiwavelets for planetary gearbox fault detection based on vibration sensor signals. Sensors 2013; 13: 1183–1209.

10.

. Planetary gearbox fault diagnosis based on data-driven valued characteristic multigranulation model with incomplete diagnostic information. J Sound Vib 2018; 429: 63–77.

11.

Pang

Yang

. Motor current signal analysis using deep neural networks for planetary gear fault diagnosis. Measurement 2019; 145: 45–54.

12.

Deekshit

KKC

Rao

MVG

Rao

. Fault indexing parameter based fault detection in induction motor via MCSA with Wiener filtering. Electric Power Components Syst 2020; 48: 2048–2062.

13.

Krishna

MSR

Ravi

. Fault diagnosis of induction motor using motor current signature analysis. In:2013 International conference on circuits, power and computing technologies (ICCPCT), Kumaracoil, Nagercoil, India, 20-21 March 2013, 2013, pp. 180–186.

14.

Zhang

Mansaf

, et al. Gear wear monitoring by modulation signal bispectrum based on motor current signal analysis. Mech Syst Signal Process 2017; 94: 202–213.

15.

Chai

Yang

, et al. Gear fault diagnosis based on dual parameter optimized resonance-based sparse signal decomposition of motor current. Ieee T Ind Appl 2018; 54: 3782–3792.

16.

Hoang

D-T

Kang

H-J

. A survey on deep learning based bearing fault diagnosis. Neurocomputing 2019; 335: 327–335.

17.

Lei

Yang

Jiang

, et al. Applications of machine learning to machine fault diagnosis: a review and roadmap. Mech Syst Signal Process 2020; 138: 106587.

18.

Zhao

Yan

Chen

, et al. Deep learning and its applications to machine health monitoring. Mech Syst Signal Process 2019; 115: 213–237.

19.

Xing

Lei

Wang

, et al. Distribution-invariant deep belief network for intelligent fault diagnosis of machines under new working conditions. Ieee T Ind Electron 2021; 68: 2617–2625.

20.

Tang

Chen

, et al. A deep convolutional neural network approach with information fusion for bearing fault diagnosis under different working conditions. Proc Inst Mech Eng Part C: J Mech Eng Sci 2020; 235: 1389–1400.

21.

Che

Wang

, et al. Intelligent fault prediction of rolling bearing based on gate recurrent unit and hybrid autoencoder. Proc Inst Mech Eng Part C: J Mech Eng Sci 2020; 235: 1106–1114.

22.

Zhang

Cheng

, et al. A hybrid classification autoencoder for semi-supervised fault diagnosis in rotating machinery. Mech Syst Signal Process 2021; 149: 107327.

23.

Liu

. A deep learning model for fault diagnosis with a deep neural network and feature fusion on multi-channel sensory signals. Sensors-Basel 2020; 20: 4300.

24.

Yang

Liu

, et al. Gear backlash detection and evaluation based on current characteristic extraction and selection. Ieee Access 2020; 8: 107161–107176.

25.

Rummelhart

Hinton

Williams

. Learning internal representations by error propagation. Nature 1986; 323: 318–362.

26.

Olshausen

Field

. Emergence of simple-cell receptive field properties by learning a sparse code for natural images. Nature 1996; 381: 607–609.

27.

Shang

Gao

, et al. A novel deep autoencoder and hyperparametric adaptive learning for imbalance intelligent fault diagnosis of rotating machinery. Eng Appl Artif Intel 2021; 102: 104279.

28.

Kullback

Leibler

. On information and sufficiency. Ann Math Stat 1951; 22: 79–86.

29.

Mao

Feng

Liu

, et al. A new deep auto-encoder method with fusing discriminant information for bearing fault diagnosis. Mech Syst Signal Process 2021; 150: 107233.

30.

Han

Zhang

Wen

, et al. Two-stage learning to predict human eye fixations via SDAEs. IEEE Trans Cybernetics 2016; 46: 487–498.

31.

Bielza

Robles

Larrañaga

. Regularized logistic regression without a penalty term: an application to cancer classification with microarray data. Expert Syst Appl 2011; 38: 5110–5118.

32.

Sugiyama

. Dimensionality reduction of multimodal labeled data by local fisher discriminant analysis. J Machine Learn Res 2007; 8: 1027–1061.