Aiming at the problem that it is difficult to extract effective fault features from oil pressure signals converted by turnout switch machine and the traditional fault diagnosis method is not effective, a fault diagnosis method turnout switch machine based on visibility graph features and CatBoost is proposed. Firstly, the visual graph algorithm is used to convert the time-domain signal into a complex network graph. Then, the five statistical features of complex network graphs are extracted (i.e., network average degree, global clustering coefficient, average path length, transitivity feature and network graph density). Finally, the fault diagnosis of turnout switch machine is realized by CatBoost algorithm. This method is compared with other feature extraction methods and fault classification algorithms. The experimental results show that the visibility graph feature can more effectively represent the working state of turnout switch machine. The diagnostic accuracy of CatBoost algorithm for four working states of turnout switch machine reaches 97.5%, which verifies its effectiveness and superiority.
CHENGWeizhi, WANGHaidong, LIANGYu.Research on fault analysis and fault diagnosis monitoring system of railway switch machine[J].China Railway,2018(7):43-47. (in Chinese)
DONGYu, ZHAOYuanyuan, LINHaixiang.The analysis and research of electric switch machine operating current based on wavelet analysis[J].Journal of Lanzhou Jiaotong University,2012,31(6):39-43.(in Chinese)
[5]
CHENQ Y, GEMMAN, CLIVER,et al.Improved fault diagnosis of railway switch system using energy-based thresholding wavelets (EBTW) and neural networks[J].IEEE Transactions on Instrumentation and Measurement,2021,70:1-12.
SUNYongkui, CAOYuan, LIPeng, et al. A fault diagnosis method of switch machine based on wavelet packet decomposition, multi-scale arrangement entropy and second-order feature selection[J]. China Railway Science, 2023, 44(3): 178-188. (in Chinese)
[8]
KUNS Y, HET, WUY C. Research on fault diagnosis method of switch machine based on KFCM[J]. Journal of Physics: Conference Series, 2021, 1972(1): 012029.
MALi, ANZhilong. Fault diagnosis model of S700K point machine gear set based on local tangent space arrangement and Support vector machine[J]. Qinghai transportation technology, 2019(4): 80-84. (in Chinese)
WEIWenjun, LIUXinfa.Fault diagnosis of S700k point machine based on EEMD multi-scale sample entropy[J].Journal of the Central South University(Science Edition),2019,50(11):2763-2772.(in Chinese)
CAOYuan, SONGDi, HUXiaoxi, et al. Fault diagnosis of switch machine based on improved time-domain multi-scale dispersion entropy and support vector machine[J]. Acta Electronica Sinica, 2023, 51(1): 117-127.(in Chinese)
HETing, HUANGJinying, HUMengnan, et al. Fault diagnosis of piston pump based on KPEMD and INFO-SVM[J]. Journal of North University of China(Natural Science Edition), 2023, 44(3): 216-221.(in Chinese)
LIUKexing, HUANGHaiyu.Research on switch machine fault diagnosis method based on DCDAE-BILSTM model[J].Railway Communication Signal,2021,57(8):87-91. (in Chinese)
[20]
CAOY, YUANS J, YONGK S,et al.The fault diagnosis of a switch machine based on deep random forest fusion.[J].IEEE Intelligent Transportation Systems Magazine,2022,15(1):437-452.
FUYating, WENShiming, YANGHui, et al. Fault diagnosis of turnout switch machine based on multi-channel input and 1DCNN-LSTM[J]. Journal of the China Railway Society, 2023(11): 98-106.(in Chinese)
WANGRuifeng, LIyang. Fault diagnosis of S700K switch machine based on 1DCNN-BiLSTM combined model[J]. Journal of Electronic Measurement and Instrumentation, 2022, 36(11): 193-200.(in Chinese)
[25]
许红红.基于可视图网络的脑电信号研究[D].南京:南京邮电大学,2020.
[26]
郭建民.时间序列复杂网络建网方法的性能分析及应用研究[D].天津:天津大学,2016.
[27]
DHANANJAYB, JAYARAMANS.Analysis and classification of heart rate using CatBoost feature ranking model[J].Biomedical Signal Processing and Control,2021,68(16):102610.
[28]
曹颖超.改进的GDBT迭代决策树分类算法及其应用[J].科技视界,2017(12):105.
[29]
CAOYingchao.Improved GDBT iterative decision tree classification algorithm and its application[J].Science and Technology Vision,2017(12):105.(in Chinese)
XIEYuxi, YANYongjun, LIXiang,et al.Research on fault diagnosis method of nuclear detector based on BP neural network[J].Atomic Energy Science and Technology,2021,55(10):1857-1864.(in Chinese)