Fault diagnosis method for variable speed planetary gearbox based on current signal

doi:10.16731/j.cnki.1671-3133.2025.01.014

Abstract

Abstract: The fault diagnosis method based on current signals has advantages in signal acquisition and anti-interference.It is difficult to extract gear fault features,due to the power frequency component. Therefore,removing the power frequency component from the current signal is a significant task,especially when the gearbox is in variable speed conditions. At present,there is still no ideal method for diagnosing planetary gearbox faults under variable speed conditions. A planetary gear fault diagnosis method based on reactive power,Gramion Angular Field,and average teacher semi-supervised model was proposed. Firstly,the power frequency component was removed from the time-varying current signal by calculating the reactive power. Then,Gramion Angular Field was used to transform 1D temporal data into 2D data with more complete feature information. Finally,the fault recognition of planetary gears was achieved based on an improved semi-supervised learning model. The experimental results showed that the recognition accuracy could reach 92.31 % when using 20 % labeled data.

Key words: fault diagnosis, current signal, planetary gearbox, variable speed operation, semi-supervised learning

CLC Number:

TH132

QIAO Ningning, LI Feng. Fault diagnosis method for variable speed planetary gearbox based on current signal[J]. Modern Manufacturing Engineering, 2025, 532(1): 111-120.

References

[1] 门兰城,庞新宇,李峰,等.基于电机电流经验模态分解的行星轮故障诊断[J].机械设计与制造,2021(4):39-42,47.
[2] RAJAGOPALAN S,HABETLER T G,HARLEY R G,et al. Current/voltage-based detection of faults in gears coupled to electric motors[J].IEEE Transactions on Industry Applications,2006,42:1412-1420.
[3] 陈峙,王铁,谷丰收,等.基于电动机电流信号双谱分析的齿轮传动故障诊断[J].机械工程学报,2012,48(21):84-90.
[4] 李峰,庞新宇,杨兆建.基于电机电流分析的齿轮断齿和磨损故障诊断[J].科学技术与工程,2018,18(10):48-52.
[5] 管一臣,童攀,冯志鹏.基于ICEEMDAN方法和频率解调的行星齿轮箱故障电流信号特征分析[J].振动与冲击,2019,38(24):41-47.
[6] 时献江,李苏健,郭华,等.行星齿轮箱的定子电流信号诊断方法试验研究[J].振动、测试与诊断,2022,42(4):671-676.
[7] GAO A,FENG Z,LIANG M.Permanent magnet synchronous generator stator current AM-FM model and joint signature analysis for planetary gearbox fault diagnosis[J].Mechanical Systems and Signal Processing,2021,149(9):107331.
[8] CUI W,MENG G,WANG A,et al.Application of rotating machinery fault diagnosis based on deep learning[J].Shock and Vibration,2021,2021:1-30.
[9] GU J,WANG Z,KUEN J,et al.Recent advances in convolutional neural networks[J].Pattern Recognition,2018,77:354-377.
[10] YANG Y,ZHENG H,LI Y,et al.A fault diagnosis scheme for rotating machinery using hierarchical symbolic analysis and convolutional neural network[J].ISA Transactions,2019,91:235-252.
[11] JIA F,LEI Y,GUO L,et al.A neural network constructed by deep learning technique and its application to intelligent fault diagnosis of machines[J].Neurocomputing,2018,272:619-628.
[12] CHEN R X,HUANG X,YANG L X,et al.Intelligent fault diagnosis method of planetary gearboxes based on convolution neural network and discrete wavelet transform[J].Computers in Industry,2019,106:48-59.
[13] DAYAN P,SAHANI M,DEBACK G.Unsupervised learning[J].The MIT Encyclopedia of the Cognitive Sciences,1999:857-859.
[14] MONROY I,BENITEZ R,ESCUDERO G,et al.A semi-supervised approach to fault diagnosis for chemical processes[J].Computers & Chemical Engineering,2010,34(5):631-642.
[15] LI C,LIANG M.Time-frequency signal analysis for gearbox fault diagnosis using a generalized synchrosqueezing transform[J].Mechanical Systems & Signal Processing,2012,26(1):205-217.
[16] DRIF M,CARDOSO A J M. The use of the instantaneous-reactive-power signature analysis for rotor-cage-fault diagnostics in three-phase induction motors[J].IEEE Transactions on Industrial Electronics,2009,56(11):4606-4614.
[17] WANG Z,OATES T. Imaging time-series to improve classification and imputation[J].arXiv preprint arXiv:1506.00327,2015.
[18] YEUNG C K,YEUNG D Y. Addressing two problems in deep knowledge tracing via prediction-consistent regulariz-ation[C]//Proceedings of the Fifth Annual ACM Confer-ence on Learning at Scale. New York: Association for Computer Machinery,2018,5:1-10.
[19] BORKAR T S,KARAM L J. DeepCorrect:correcting DNN models against image distortions[J].IEEE Transactions on Image Processing,2019,28(12):6022-6034.
[20] SARWINDA D,PARADISA R H,BUSTAMAM A,et al. Deep learning in image classification using residual network (ResNet) variants for detection of colorectal cancer[J].Procedia Computer Science,2021,179:423-431.
[21] SOHONI N S,ABERGER C R,LESZCZYNSKI M,et al. Low-memory neural network training:a technical report[J].arXiv preprint arXiv:1904.10631,2019.
[22] SRIVASTAVA N,HINTON G,KRIZHEVSKY A,et al. Dropout:a simple way to prevent neural networks from overfitting[J].The Journal of Machine Learning Research,2014,15(1):1929-1958.
[23] ZHAO P,PANG X,LI F,et al.Gearbox fault diagnosis method based on improved semi-supervised MTDL and GAF[J/OL].Measurement and Control(2024-02-29)[2024-04-26].DOI:10.1177/00202940241230488.