Fault diagnosis of vehicle motor-bearings under safe running by digital-twin technology

doi:10.3969/j.issn.1674-8484.2023.02.010

Abstract

Abstract:

To ensure the driving safety of automobiles and timely capture the fault status of motor bearings, a fault diagnosis of motor bearings was completed through the combination of deep learning and digital twin technology. The detailed attributes of the bearings were transformed into virtual space through digital twin technology, and a digital twin body with shape, attributes, criteria, and behavior was constructed. The shape and attribute modules integrated the object parameters of the motor bearings to build a criterion module based on fault signal processing, diagnosis, and classification, and combined the historical records injected by the behavior module to generate data for network training. Data analysis was completed using Matlab 2020a. The results show that the diagnostic accuracies of this method for conventional signals, inner race fault, outer race fault, and rolling element fault are 97.5%, 97.8%, 96.8%, and 97.1%, respectively. Therefore, this method has superior diagnostic effect and algorithmic performance compared with that by using the methods of the hybrid neural network and the migrated residual network.

Key words: automotive safety, motor bearing, fault diagnosis, digital twin, deep learning, virtual space

CLC Number:

TH165.3

ZHANG Xi, LIAO Yulan, LI Qinyi, CHEN Yiqing. Fault diagnosis of vehicle motor-bearings under safe running by digital-twin technology[J]. Journal of Automotive Safety and Energy, 2023, 14(2): 232-238.

Figures/Tables 13

References 19

[1]	Mortlock T, Muthirayan D, YU Shiyuan, et al. Graph learning for cognitive digital twins in manufacturing systems[J]. IEEE T Emerg Top Comp, 2022, 10(1): 34-45.
[2]	Afrasiabi S, Mohammadi M, Afrasiabi M, et al. Modulated gabor filter based deep convolutional network for electrical motor bearing fault classification and diagnosis[J]. IET Sci Meas Technol, 2021, 15(2): 154-162. doi: 10.1049/smt2.v15.2 URL
[3]	LI Huajin, DENG Jiahao, YUAN Shuang, et al. Monitoring and identifying wind turbine generator bearing faults using deep belief network and EWMA control charts[J]. Front Energy Res, 2021, 9: 799039. doi: 10.3389/fenrg.2021.799039 URL
[4]	伍建军, 骆建彬. 一种改进的小波分析和Hilbert包络的轴承故障[J]. 机械设计与制造, 2019(4): 59-62.
	WU Jianjun, LUO Jianbin. An improved wavelet analysis and failure analysis of rolling bearing with hilbert envelope[J]. Mach Des Manu, 2019(4): 59-62. (in Chinese)
[5]	LIU Yongbao, LI Jun, LI Qijie, et al. Transfer learning with inception Resnet-based model for rolling bearing fault diagnosis[J]. J Adv Mech Des Syst, 2022, 16(2): 1-19.
[6]	杨光春, 蹇清平. 基于QPSO-SVM的轴承故障诊断方法[J]. 机械传动, 2014, 38(8): 134-138.
	YANG Guangchun, JIAN Qingping. Method of rolling bearing fault diagnosis based on SVM with QPSO[J]. J Mech Trans, 2014, 38(8): 134-138. (in Chinese)
[7]	REN Zijie, WAN Jiafu, DENG Pan. Machine-learning-driven digital twin for lifecycle management of complex equipment[J]. IEEE T Emerg Top Com, 2022, 10(1): 9-22.
[8]	Buck L E, Chakraborty S, Bodenheimer B. The impact of embodiment and avatar sizing on personal space in immersive virtual environments[J]. IEEE T Vis Comput Gr, 2022, 28(5): 2102-2113. doi: 10.1109/TVCG.2022.3150483 URL
[9]	XIE Guoqi, YANG Kehua, XU Cheng, et al. digital twinning based adaptive development environment for automotive cyber-physical systems[J]. IEEE T Indu Info, 2022, 18(2): 1387-1396.
[10]	Garcia-calva T A, Morinigo-sotelo D, Troncoso R D R. Fundamental frequency normalization for reliable detection of rotor and load defects in VSD-fed induction motors[J]. IEEE T Energy Conver, 2022, 37(2): 1467-1474. doi: 10.1109/TEC.2021.3124803 URL
[11]	HANG Jun, SUN Wushuang, HU Qitao, et al. Integration of interturn fault diagnosis and fault-tolerant control for PMSM drive system[J]. IEEE T Transp Electr, 2022, 8(2): 2825-2835.
[12]	WANG Xiaoxian, LU Siliang, CHEN Kang, et al. Bearing fault diagnosis of switched reluctance motor in electric vehicle powertrain via multi-sensor data fusion[J]. IEEE T Indu Info, 2022, 18(4): 2452-2464.
[13]	Plazenet T, Boileau T, Caironi C C, et al. Influencing parameters on discharge bearing currents in inverter-fed induction motors[J]. IEEE T Energy Conver, 2021, 36(2): 940-949. doi: 10.1109/TEC.60 URL
[14]	Hemenway N R, Gjemdal H, Severson E L. New three-pole combined radial-axial magnetic bearing for industrial bearingless motor systems[J]. IEEE T Ind Appl, 2021, 57(6): 6754-6764. doi: 10.1109/TIA.2021.3068089 URL
[15]	ZHANG Jiqiao, ZHANG Jiqiao, TENG Shuai, et al. Structural damage detection based on vibration signal fusion and deep learning[J]. J Vib Eng Technol, 2022, 10(4): 1205-1220. doi: 10.1007/s42417-022-00438-7
[16]	LU Linjun, DAI Fei. A unified normalization method for homography estimation using combined point and line correspondences[J]. Comput-Aided Civ Inf, 2022, 37(8): 1010-1026. doi: 10.1111/mice.v37.8 URL
[17]	Eken E. Determining overfitting and underfitting in generative adversarial networks using Frechet distance[J]. Turk J Electr Eng Comp, 2021, 29(3): 1524-1538.
[18]	Park J, Jung W, Choi E J, et al. DIFFnet: Diffusion parameter mapping network generalized for input diffusion gradient schemes and b-value[J]. IEEE T Med Imag, 2022, 41(2): 491-499. doi: 10.1109/TMI.2021.3116298 URL
[19]	Adu K, YU Yongbin, CAI Jingye, et al. The influence of the activation function in a capsule network for brain tumor type classification[J]. INT J Imag Syst Tech, 2022, 32(1): 123-143. doi: 10.1002/ima.v32.1 URL

方法	Ac / %
方法	常规信号	内圈型	外圈型	滚动体型
文献 ^[2]	90.2	89.5	91.8	90.3
文献 ^[5]	86.1	85.3	86.9	86.2
本文	97.5	97.8	96.8	97.1

方法	Ac / %
方法	常规信号	内圈型	外圈型	滚动体型
文献 ^[2]	90.2	89.5	91.8	90.3
文献 ^[5]	86.1	85.3	86.9	86.2
本文	97.5	97.8	96.8	97.1

损伤类型	损伤代码	损伤值 / μm	损伤编号
正常	ZZ	0.0	1
内圈	NB	177.8	2
内圈	NC	355.6	3
内圈	ND	533.4	4
外圈	WB	177.8	5
外圈	WC	355.6	6
外圈	WD	533.4	7
滚动体	GB	177.8	8
滚动体	GC	355.6	9
滚动体	GD	533.4	10

损伤类型	损伤代码	损伤值 / μm	损伤编号
正常	ZZ	0.0	1
内圈	NB	177.8	2
内圈	NC	355.6	3
内圈	ND	533.4	4
外圈	WB	177.8	5
外圈	WC	355.6	6
外圈	WD	533.4	7
滚动体	GB	177.8	8
滚动体	GC	355.6	9
滚动体	GD	533.4	10