[1]王 凡,甄子洋,邓 敏.基于 CNN-GRU-Attention 的道岔故障诊断算法研究[J].机械与电子,2024,42(06):10-15.
　WANG Fan,ZHEN Ziyang,DENG Min.Research on Turnout Fault Diagnosis Algorithm Based on CNN-GRU-Attention[J].Machinery & Electronics,2024,42(06):10-15.
点击复制

基于 CNN-GRU-Attention 的道岔故障诊断算法研究()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
42
期数:
2024年06期
页码:
10-15
栏目:
研究与设计
出版日期:
2024-06-28

文章信息/Info

Title:
Research on Turnout Fault Diagnosis Algorithm Based on CNN-GRU-Attention
文章编号:
1001-2257 ( 2024 ) 06-0010-06
作者:
王 凡 1 ; 甄子洋 1 ; 邓 敏 2
1. 南京航空航天大学自动化学院,江苏 南京 211106 ;
?2. 南京轨道交通系统工程有限公司,江苏 南京 210019
Author(s):
WANG Fan1 ;  ZHEN Ziyang1 ;  DENG Min2
( 1.College of Automation Engineering , Nanjing University of Aeronautics and Astronautics , Nanjing 211106 , China ;
2.Nanjing Rail Transit Systems Co. , Ltd. , Nanjing 210019 , China )
关键词:
道岔故障诊断; 卷积神经网络; 门控循环单元; 注意力机制
Keywords:
turnout fault diagnosis ;  convolutional neural network ;  gated recurrent unit ;  attention mechanism
分类号:
U284 ; TP277
文献标志码:
A
摘要:
道岔是关系列车运行安全的铁路信号基础设备之一。通过分析道岔运行过程的功率数据,可以有效判断道岔的运行状况。为实现对道岔故障自动、高效、准确的诊断,研究并提出了一种基于深度学习的故障诊断方法。首先利用卷积神经网络提取数据空间性特征,再调用门控循环单元网络提取时间性特征,再引入注意力机制对特征进行权重分配,最后使用 Softmax 分类器进行分类。在对比实验中用多种指标评定该方法的性能,结果表明,所提方法相较于基础方法和另外 2 种现有方法在诊断性能上有着显著的优势。
Abstract:
Turnout is one of the railway signal infrastructures that affects the safety of trains.By analyzing the power data of the turnout operation process , the operation status of the turnout can be effectively judged.In order to achieve automatic , efficient and accurate diagnosis of turnout faults , a fault diagnosis method based on deep learning is studied and proposed.The study first utilizes convolutional neural networks to extract spatial features from data , then calls on gated recurrent unit networks to extract temporal features , introduces attention mechanisms for allocating weights to features , and finally uses Softmax classifiers for classification.In comparative experiments , multiple indicators are used to evaluate the performance of this method , and the results show that this method has significant advantages in diagnostic performance compared to the basic methods and two other existing methods.

参考文献/References:

[ 1 ] 杨菊花,于苡健,陈光武,等 . 基于 CNN-GRU 模型的道岔故障诊断算法研究[ J ] . 铁道学报, 2020 , 42 ( 7 ):102-109.

[ 2 ] 张钉,李国宁 . 基于改进 WNN 分析功率曲线的 S700K 转辙机故障诊断[ J ] . 铁道科学与工程学报,2018 , 15( 8 ): 2123-2130.
[ 3 ] 姬文江,左元,黑新宏,等 . 基于 FastDTW 的道岔故障智能诊断方法 [ J ] . 模式识别与人工智能,2020 , 33( 11 ): 1013-1022.
[ 4 ] EKER O F , CAMCI F , KUMAR U.SVM based diagnostics on railway turnouts [ J ] .International journal of performability engineering , 2012 , 8 ( 3 ): 289-398.
[ 5 ] ATAMURADOV V , CAMCI F , BASKAN S , et al.Failure diagnostics for railway point machines using expert systems [ C ] ∥2009 IEEE International Symposium on Diagnostics for Electric Machines , Power Electronics and Drives , 2009 : 1-5.
[ 6 ] 唐维华 . 基于 LSTM / NN 的道岔故障特征提取与识别研究[ J ] . 计算机应用与软件, 2019 , 36 ( 1 ): 159-163.
[ 7 ] 池毅 . 基于深度学习的道岔故障智能诊断方法研究[ D ] . 兰州:兰州交通大学,2021.
[ 8 ] FORESTIER G , PETITJEAN F , DAU H A , et al.Generating synthetic time series to augment sparse datasets [ C ] ∥2017 IEEE International Conference on Data Mining , 2017 : 865870.
[ 9 ] 王 瑞峰,李 扬 . 基 于 1DCNN-BiLSTM 组合模型的 S700K 转辙机故障诊断 [ J ] . 电子测量与仪器学报,2022 , 36 ( 11 ): 193-200.

相似文献/References:

[1]王骁贤,张保华,陆思良.基于连续小波变换和卷积神经网络的无刷直流电机故障诊断[J].机械与电子,2018,(06):29.
　WANG Xiaoxian,ZHANG Baohua,LU Siliang.Fault Diagnosis of Brushless Direct Current Motor Based on Continuous Wavelet Transform and Convolutional Neural Network[J].Machinery & Electronics,2018,(06):29.
[2]刘志宇,黄亦翔.基于深度学习和迁移学习的液压泵健康评估方法[J].机械与电子,2018,(09):67.
　LIU Zhiyu,HUANG Yixiang.Health Assessment for Hydraulic Pump Based on Deep Learning and Transfer Learning[J].Machinery & Electronics,2018,(06):67.
[3]曾雪琼,黎杰.基于卷积神经网络的时频图像识别研究[J].机械与电子,2016,(05):25.
　ZENG Xueqiong,LI Jie.Time-frequency Image Recognition Based on Convolutional Neural Network[J].Machinery & Electronics,2016,(06):25.
[4]齐爱玲１,李 琳１,朱亦轩２,等.基于融合特征的双通道CNN滚动轴承故障识别[J].机械与电子,2021,(05):15.
　QI Ailing,LI Lin,ZHU Yixuan,et al.Dual Channel CNN Bearing Fault Identification Based on Fusion Feature[J].Machinery & Electronics,2021,(06):15.
[5]周岳斌,杨 沫,曹煜晖.无线视频监控系统人脸跟踪功能的实现[J].机械与电子,2021,(06):35.
　ZHOU Yuebin,YANG Mo,CAO Yuhui.Realization of Face Tracking Function in Wireless Video Surveillance System[J].Machinery & Electronics,2021,(06):35.
[6]杨永灿,刘 韬,柳小勤,等.基于注意力机制的一维卷积神经网络行星齿轮箱故障诊断[J].机械与电子,2021,(10):3.
　YANG Yongcan,LIU Tao,LIU Xiaoqin,et al.Fault Diagnosis of Planetary Gearbox Based on One-dimensional Convolutional Neural Network with Attention Mechanism[J].Machinery & Electronics,2021,(06):3.
[7]潘长玉.基于时频分析的移频轨道交通信号检测方法[J].机械与电子,2022,(01):71.
　PAN Changyu.Frequency-shift Rail Transit Signal Detection Method Based on Time-frequency Analysis[J].Machinery & Electronics,2022,(06):71.
[8]覃 剑,杜 珂,苏淑敏,等.基于场景识别的变电站智能机器人巡视技术[J].机械与电子,2022,(08):76.
　QIN Jian,DU Ke,SU Shumin,et al.Substation Intelligent Robot Patrol Technology Based on Scene Recognition[J].Machinery & Electronics,2022,(06):76.
[9]王浏洋,徐彦伟,等.基于优化 CNN 与信息融合的地铁牵引电机轴承故障诊断[J].机械与电子,2023,41(08):39.
　WANG Liuyang,XU Yanwei,XIE Tancheng,et al.Fault Diagnosis of Metro Traction Motor Bearing Based on Optimized CNN and Information Fusion[J].Machinery & Electronics,2023,41(06):39.
[10]陈 宇,程道来,马向华,等.基于 WDCNN-LSTM 混合模型的滚动轴承故障诊断[J].机械与电子,2025,(02):9.
　CHEN Yu,CHENG Daolai,MA Xianghua,et al.Fault Diagnosis of Rolling Bearing Based on WDCNN-LSTM Hybrid Model[J].Machinery & Electronics,2025,(06):9.

备注/Memo

备注/Memo:
收稿日期: 2023-09-21
作者简介:王凡 ( 1997- ),男,江苏南京人,硕士研究生,研究方向为轨道交通故障诊断;甄子洋 ( 1981- ),男,浙江金华人,博士,教授,研究方向为舰载机/无人机着舰引导与控制、无人机集群编队协同控制与决策等。
更新日期/Last Update: 2024-07-02