US 11,898,932 B2
Motor bearing failure diagnosis device
Wenlong Zhu, Hunan (CN); Yong Liu, Hunan (CN); Jisheng Dai, Hunan (CN); Zongshuai Li, Hunan (CN); Jiawei Yang, Hunan (CN); Ping Jiang, Hunan (CN); Yanhao Zhan, Hunan (CN); Zhongjing Zhang, Hunan (CN); and Hailong Xu, Hunan (CN)
Assigned to ZHUZHOU CRRC TIMES ELECTRIC CO., LTD., Hunan (CN)
Appl. No. 17/261,886
Filed by ZHUZHOU CRRC TIMES ELECTRIC CO., LTD., Hunan (CN)
PCT Filed Sep. 3, 2019, PCT No. PCT/CN2019/104202
§ 371(c)(1), (2) Date Jan. 21, 2021,
PCT Pub. No. WO2020/078132, PCT Pub. Date Apr. 23, 2020.
Claims priority of application No. 201811197298.4 (CN), filed on Oct. 15, 2018.
Prior Publication US 2021/0286995 A1, Sep. 16, 2021
Int. Cl. G01R 19/00 (2006.01); G01M 13/045 (2019.01); G01R 23/16 (2006.01); G01R 31/34 (2020.01); G06F 18/214 (2023.01)
CPC G01M 13/045 (2013.01) [G01R 19/0092 (2013.01); G01R 23/16 (2013.01); G01R 31/34 (2013.01); G06F 18/2148 (2023.01); G06F 2218/02 (2023.01); G06F 2218/10 (2023.01); G06F 2218/12 (2023.01)] 9 Claims
OG exemplary drawing
 
1. A device for diagnosing a fault in a bearing of a motor, comprising:
a current signal acquisition unit, a residual signal acquisition unit, a fault feature extraction unit and a fault diagnosis model unit, wherein in a case that the device operates in a fault diagnosis mode,
the current signal acquisition unit is configured to acquire a real-time current signal of the motor;
the residual signal acquisition unit is configured to extract harmonic signals from the real-time current signal of the motor acquired by the current signal acquisition unit, and remove a fundamental signal and a harmonic signal from the real-time current signal of the motor, to acquire a residual signal;
the fault feature extraction unit is configured to analyze the residual signal acquired by the residual signal acquisition unit in both time domain and frequency domain, to extract a fault feature index of the bearing; and
the fault diagnosis model unit is configured to perform, by using a bearing fault diagnosis model obtained through training, pattern recognition on the fault feature index of the bearing extracted by the fault feature extraction unit, to diagnose a fault state of the bearing, wherein in the case that the device operates in the fault diagnosis mode, the fault feature extraction unit is configured to:
acquire a minimum value (I_min) and an effective value (I_rms) of the residual signal,
acquire a fault feature frequency of the bearing, and acquire a fault feature frequency sequence of the bearing, wherein FFT transformation is performed on the residual signal to acquire a frequency spectrum of the residual signal, and acquire an amplitude of the fault feature frequency sequence of the bearing based on the frequency spectrum of the residual signal; and
acquire a maximum value (I_custom character_max), a peak-to-peak value (I_custom character_peark) and a crest factor (I_custom character_crest) of the amplitude (I_custom character(n)) of the fault feature frequency sequence of the bearing.