A study on prediction model of dynamic matching characteristics of pantograph-catenary system based on the GBDT algorithm

被引：0
作者：
Huang, Guizao [1 ]
Ma, Tongxin [1 ]
Yang, Zefeng [1 ]
Li, Zheng [1 ]
Wei, Wenfu [1 ]
Wu, Guangning [1 ]
机构：
[1] School of Electrical Engineering, Southwest Jiaotong University, Chengdu
来源：
Zhendong yu Chongji/Journal of Vibration and Shock | 2024年 / 43卷 / 16期
关键词：
current collection quality; dynamic characteristics; gradient lifting decision tree (GBDT); machine learning; pantograph-catenary system;
D O I：
10.13465/j.cnki.jvs.2024.16.004
中图分类号：
学科分类号：
摘要：
High-speed railway acquires electric energy to drive a train through the sliding electric contact of a pantograph-catenary system. The dynamic matching characteristics of the pantograph-catenary system is the basis of ensuring good sliding electric contact. In this study, firstly, a finite element analysis model to simulate dynamic interaction of pantograph-catenary system was established, and its validity was verified by comparing with the results in literature. Then,the Latin hypercube sampling method was used to sample the main structural parameters of catenary as well as operating speed parameter, and the input parameters were obtained. Using the finite element model, a large number of calculation and analysis of the input parameter set were carried out and the results were extracted,and the output results of the key evaluation indexes of the dynamic matching characteristics were obtained. The input and output results were combined to form the sample data set. Finally, the gradient lifting decision tree (GBDT) algorithm was used to learn and train the dataset,based on which the prediction model of dynamic matching characteristics of the pantograph-catenary system was obtained. The model was compared with four other models, i. e. random forest, extreme random tree, and extreme gradient lifting tree algorithm. The results show that the prediction accuracy of the GBDT-based model is higher and the stability is better. The R2 on the test set reaches 0. 929,which can accurately and quickly evaluate the dynamic matching characteristics. The parameter importance analysis of the GBDT model shows that the operation speed has the greatest influence on the contact quality, which is 61%,followed by the tension in contact wire, the tension in messenger wire and the span length. This study explores the possibility of using machine learning methods to establish prediction models instead of finite element models, and the established models can be used for rapid prediction and evaluation of the dynamic matching characteristics of pantograph-catenary systems. © 2024 Chinese Vibration Engineering Society. All rights reserved.
引用
收藏
页码：26 / 32and50
页数：3224
相关论文
共 28 条
  • [11] Song Y., Liu Z.G., Ronnquist A., Et al., Contact wire irregularity stochastics and effect on high-speed railway pantograph-catenary interactions [J], IEEE Transactions on Instrumentation and Measurement, 69, 10, pp. 8196-8206, (2020)
  • [12] Liu Z., Song Y., Han Y., Et al., Advances of research on high-speed railway catenary [J], Journal of Southwest Jiaotong University, 51, 3, pp. 495-518, (2016)
  • [13] Jimenez-Octavio J.R., Carnicero A., Sanchezrebollo C., Et al., A moving mesh method to deal with cable structures subjected to moving loads and its application to the catenary-pantograph dynamic interaction [J], Journal of Sound and Vibration, 349, pp. 216-229, (2015)
  • [14] Song Y., Liu Z.G., Xu Z.G., Et al., Developed moving mesh method for high-speed railway pantograph-catenary interaction based on nonlinear finite element procedure[J], International Journal of Rail Transportation, 7, 3, pp. 173-190, (2019)
  • [15] Gorissen D., Couckuyt I., Demeester P., Et al., A surrogate modeling and adaptive sampling toolbox for computer based design [J], The Journal of Machine Learning Research, 11, pp. 2051-2055, (2010)
  • [16] Zhang Y.L., Bryan J., Richards G., Et al., Development and comparative selection of surrogate models using artificial neural network for an integrated regenerative transcritical cycle[J], Applied Energy, 317, (2022)
  • [17] Huang G.Z., Yan B., Mou Z.Y., Et al., Surrogate model for torsional behavior of bundle conductors and its application [J], IEEE Transactions on Power Delivery, 37, 1, pp. 67-75, (2021)
  • [18] Zhou Y., Wang J.J., Liu Y., Et al., Incorporating deep learning of load predictions to enhance the optimal active energy management of combined cooling, heating and power system[J], Energy, 233, 8, (2021)
  • [19] Huang G.Z., Wu G.N., Yang Z.F., Et al., Development of surrogate models for evaluating energy transfer quality of high-speed railway pantograph-catenary system using physics-based model and machine learning [J], Applied Energy, 333, (2023)
  • [20] Zhan Y., Deng Q., Luo Z., Et al., Research on GBDT-based asphalt pavement skid resistance perception model [J], China Civil Engineering Journal, 2022, 2, pp. 121-132
123