北京交通大学学报2025，Vol.49Issue(6)：30-40,11.DOI:10.11860/j.issn.1673-0291.20240022
基于GAN-BO-BiGRU的转辙机故障诊断
Fault diagnosis of switch machine based on GAN-BO-BiGRU
摘要
Abstract
To address the widespread challenges of limited data samples and low diagnostic accuracy in existing switch machine fault diagnosis,this study takes the action power curve,a critical time-series signal of the S700K switch machine,as the research object and proposes a fault diagnosis model based on GAN-BO-BiGRU.First,a small number of power data samples collected by the Centralized Sig-nalling Monitoring system(CSM)are fed into a Generative Adversarial Network(GAN).Through ad-versarial training between the generator and the discriminator,more sample data are generated to ad-dress the issue of data scarcity.Second,a BO-BiGRU fault diagnosis algorithm model is established.The Bayesian Optimization(BO)algorithm is used to determine the optimal values of key hyperparam-eters for the Bidirectional Gated Recurrent Unit(BiGRU)model,including the number of hidden-layer neurons,the initial learning rate,and the L2 regularization parameter,thereby obtaining the opti-mal hyperparameter combination.By exploiting BiGRU's capability to capture information bidirection-ally,the proposed model more comprehensively mines patterns from the time-series power data of the switch machine.Finally,simulations are conducted using both the generated data and the original data as samples.The simulation results demonstrate that the data generated by GAN exhibits minimal dif-ference from the original data and can effectively serve as an augmented dataset for fault diagnosis.Moreover,compared to the Long Short-Term Memory(LSTM)model,the BO-BiGRU fault diagno-sis model improves the F1 score by 1.77%,indicating its superior ability to extract fault features and its effectiveness in enhancing the accuracy of switch machine fault diagnosis.关键词
转辙机/生成对抗网络/贝叶斯优化算法/双向门控循环单元Key words
switch machine/Generate Adversarial Network(GAN)/Bayesian Optimization(BO)/Bidirectional Gated Recurrent Unit(BiGRU)分类
交通工程引用本文复制引用
牛宏侠,朱雪..基于GAN-BO-BiGRU的转辙机故障诊断[J].北京交通大学学报,2025,49(6):30-40,11.基金项目
甘肃省科技重大专项(21ZD4WA018) （21ZD4WA018）
甘肃省自然科学基金(22JR5RA358,23JRRA850) （22JR5RA358,23JRRA850）
甘肃省重点研发计划(23YFGA0049) （23YFGA0049）
兰州市人才创新创业项目(2023-RC-13) Major Science and Technology Projects of Gansu Province(21ZD4WA018) （2023-RC-13）
Natural Science Foundation of Gansu Province(22JR5RA358,23JRRA850) （22JR5RA358,23JRRA850）
Gansu Provincial Key Research and Development Plan(23YFGA0049) （23YFGA0049）
Lanzhou Talent Innova-tion and Entrepreneurship Project(2023-RC-13) （2023-RC-13）
