[1]蔡俊鹏,吴炳福,陈德旺.基于机器学习的高速列车转向架振动信号监测[J].计算机技术与发展,2019,29(08):130-135.[doi:10. 3969 / j. issn. 1673-629X. 2019. 08. 025]
　CAI Jun-peng,WU Bing-fu,CHEN De-wang.High-speed Train Bogie Vibration Signal Monitoring Based on Machine Learning[J].,2019,29(08):130-135.[doi:10. 3969 / j. issn. 1673-629X. 2019. 08. 025]
点击复制

基于机器学习的高速列车转向架振动信号监测()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年08期
页码:
130-135
栏目:
应用开发研究
出版日期:
2019-08-10

文章信息/Info

Title:
High-speed Train Bogie Vibration Signal Monitoring Based on Machine Learning
文章编号:
1673-629X(2019)08-0130-06
作者:
蔡俊鹏1; 2 ; 吴炳福1; 2 ; 陈德旺1; 2
1. 福州大学 数学与计算机科学学院,福建 福州 350116; 2. 福州大学 轨道交通研究院,福建 福州 350116
Author(s):
CAI Jun-peng1; 2 ; WU Bing-fu1; 2 ; CHEN De-wang1; 2
1. School of Mathematics and Computer Science,Fuzhou University,Fuzhou 350116,China; 2. Institute of Rail Transport,Fuzhou University,Fuzhou 350116,China
关键词:
机器学习; 小波变换去噪; 随机森林算法; 列车转向架
Keywords:
machine learning; wavelet transform denoising; random forest algorithm; train bogie
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 08. 025
摘要:
为了提高列车运行时的稳定性和安全性,对列车运行时安全加速进行实时监控与预测。根据动车实际运营保存的大量转向架振动信号数据,不同于传统的基于动力学的研究,提出了基于机器学习的高速列车转向架振动信号的研究。首先通过小波变换去噪对原始数据进行数字滤波处理,强化所需部分的数据,增加了转向架振动信号数据的精确度。其次,通过实验对几种常用的机器学习算法模型进行参数拟合,经分析和对比实验结果表明,随机森林算法在转向架枕梁振动信号监测中性能表现最好且预测精度最优,均方根误差达到最低 0.069,其稳定性达到最高。 最后总结得出,在不同里程、不同速度下,转向架振动信号的有效值和最大值的变化在转向架服役性能、安全运行方面具有可推广性,能够说明基于随机森林算法的转向架振动信号的监测可以有效地监控和预测高速列车运行速度的安全阈范围并优化列车转向架轮对镟修周期。
Abstract:
In order to improve the stability and safety of high-speed train vehicles,real-time monitoring and prediction of safe acceleration during train operation are carried out. In this paper,according to the data of a large number of bogie vibration signals stored and maintained in the actual operation of the motor vehicle,different from the traditional research based on dynamics,a vibration signal based on machine learning for high-speed train bogies is proposed. First of all,the raw data is filtered digitally by wavelet transform denoising to strengthen the required part of the data and increase the precision of the bogie vibration signal data. Secondly,parameter fitting of several commonly used machine learning algorithm models through experiments, the results of analysis and comparison show that the random forest algorithm has the best performance and the best prediction accuracy in the monitoring of bogie bolster vibration signals. The root-mean-square error reaches the minimum 0.069,and its stability is the highest. Finally,it is concluded that the changes in the effective value and the maximum value of the bogie vibration signal at different mileage and at different speeds can be generalized in terms of the service performance and safe operation of the bogie,and can explain the vibration signal of the bogie based on the random forest algorithm. The monitoring can effectively monitor and predict the safety threshold range of the high-speed train operating speed and optimize the train bogie repair cycle.

相似文献/References:

[1]陈全 赵文辉 李洁 江雨燕.选择性集成学习算法的研究[J].计算机技术与发展,2010,(02):87.
　CHEN Quan,ZHAO Wen-hui,LI Jie,et al.Research of Selective Ensemble Learning Algorithm[J].,2010,(08):87.
[2]黄秀丽 王蔚.SVM在非平衡数据集中的应用[J].计算机技术与发展,2009,(06):190.
　HUANG Xiu-li,WANG Wei.Application of SVM in Imbalances Dataset[J].,2009,(08):190.
[3]鲁晓南 接标.一种基于个性化邮件特征的反垃圾邮件系统[J].计算机技术与发展,2009,(08):155.
　LU Xiao-nan,JIE Biao.An Individual Anti- Spam Technology[J].,2009,(08):155.
[4]张苗 张德贤.多类支持向量机文本分类方法[J].计算机技术与发展,2008,(03):139.
　ZHANG Miao,ZHANG De-xian.Research on Text Categorization Based on. M- SVMs[J].,2008,(08):139.
[5]汤萍萍 王红兵.基于强化学习的Web服务组合[J].计算机技术与发展,2008,(03):142.
　TANG Ping-ping,WANG Hong-bing.Web Service Composition Based on Reinforcement -Learning[J].,2008,(08):142.
[6]杨雪洁 赵姝 张燕平.基于商空间理论的冬小麦产量预测和分析[J].计算机技术与发展,2008,(03):249.
　YANG Xue-jie,ZHAO Shu,ZHANG Yan-ping.Analysis on Winter Wheat Yield Based on Quotient Space Theory[J].,2008,(08):249.
[7]汤伟 程家兴 纪霞.一种基于概率推理的邮件过滤系统的研究与设计[J].计算机技术与发展,2008,(08):76.
　TANG Wei,CHENG Jia-xing,JI Xia.Research and Design of a Spam Filtering System Based on Probability Inference[J].,2008,(08):76.
[8]孙海虹 丁华福.基于模糊粗糙集的Web文本分类[J].计算机技术与发展,2010,(07):21.
　SUN Hai-hong,DING Hua-fu.Web Document Classification Based on Fuzzy-Rough Set[J].,2010,(08):21.
[9]汤伟 程家兴 纪霞.统计学理论在邮件分类中的应用研究[J].计算机技术与发展,2008,(12):231.
　TANG Wei,CHENG Jia-xing,JI Xia.Research and Design of a Spam Filtering System Based on Statistical Learning Theory[J].,2008,(08):231.
[10]张高胤 谭成翔 汪海航.基于K-近邻算法的网页自动分类系统的研究及实现[J].计算机技术与发展,2007,(01):21.
　ZHANG Gao-yin,TAN Cheng-xiang,WANG Hai-hang.Design and Implementation of Web Page Automation Classification System Based on K- Nearest Neighbor Algorithm[J].,2007,(08):21.

更新日期/Last Update: 2019-08-10