摘要
接触网承担着向沿线电力机车输送电能的重要任务,一旦发生故障会直接影响列车安全运行,因此研究接触网故障识别方法十分必要。本文提出了一种基于VAE与TabNet的故障识别方法,首先采用ANSYSWorkbench软件建立弓网耦合模型,获取不同故障下的弓网接触力变化;其次利用变分自编码器算法扩充故障仿真数据,提升模型的泛化能力;最后通过TabNet模型进行故障类型的识别,识别准确率达到96%,并与其他传统分类算法对比。实验结果表明,所提方法在接触网故障识别方面表现出了优越的性能。
The contact network undetakes the important task of delivering electric energy to the electric locomotives along the line and,once in case of fault,will directly affect safe operation of the train,so it is necessary to study the fault identification method of the contact network.In this paper,a fault identification method based on VAE and TabNet is propsoed.Firstly,ANSYS Workbench software is used to set up the pantograph-network coupling model to obtain the variation of pantograph-network contact force under different faults;Then,the variational self-encoder algorithm is used to expand the fault simulation data and improve the generalization ability of the model.Finally,the identification of fault types is performed by TabNet model with an identification accuracy rate of 96%.It is also compared with other traditional classification algorithms.The experimental results show that the proposed method exhibits superior performance in fault identification of the contact network.
作者
刘家军
马馨秀
汪洪亮
LIU Jiajun;MA Xinxiu;WANG Hongliang(School of Electrical Engineering,Xi’an University of Technology,Xi’an 710048,China;School of Automation and Information Engineering,Xi’an University of Technology,Xi’an 710048,China)
出处
《电力电容器与无功补偿》
2025年第4期81-87,共7页
Power Capacitor & Reactive Power Compensation
基金
国家自然科学基金(52077176)。
关键词
接触网
故障识别
弓网耦合模型
TabNet
变分自编码器
contact network
fault identification
pantograph-catenary coupling model
TabNet
variational autoencoder
