1.中车唐山机车车辆有限公司,河北 唐山 063035
庞学苗(1987—),女,硕士,高级工程师,主要从事轨道交通车辆故障预测与健康管理相关工作;E-mail:pangxuemiao@tangche.com
扫 描 看 全 文
庞学苗, 裴春兴, 燕春光, 等. 动车组牵引电机接地故障预测[J]. 机车电传动, 2021,(4):126-130.
Xuemiao PANG, Chunxing PEI, Chunguang YAN, et al. Electrical Grounding Fault Prediction of EMU Traction Motor[J]. Electric Drive for Locomotives, 2021,(4):126-130.
庞学苗, 裴春兴, 燕春光, 等. 动车组牵引电机接地故障预测[J]. 机车电传动, 2021,(4):126-130. DOI: 10.13890/j.issn.1000-128x.2021.04.020.
Xuemiao PANG, Chunxing PEI, Chunguang YAN, et al. Electrical Grounding Fault Prediction of EMU Traction Motor[J]. Electric Drive for Locomotives, 2021,(4):126-130. DOI: 10.13890/j.issn.1000-128x.2021.04.020.
牵引电机是动车组动力传动系统中的关键部件,在牵引电机故障中最常见的故障为牵引电机接地故障。通过对某动车组牵引电机控制单元的历史数据挖掘,实现对牵引电机接地故障的预测。数据挖掘建模使用了RBF神经网络、决策树和支持向量机3种机器学习算法。试验结果表明,3种算法的预测准确度均高于84%,其中决策树相较于RBF神经网络和支持向量机,具有更高的预测精度,模型预测精度达到85.6%。因此,选取决策树模型预测动车组牵引电机接地故障的发生。
The traction motor plays a key role in the EMU train’s power transmission system. The most frequent fault of traction motor is grounding fault. By using RBF neural network, decision tree and support vector machine (SVM) respectively, the traction motor’s electrical fault prediction model was built based on the historical data of the traction motor control unit. It shows that the prediction accuracy of the three algorithms is higher than 84% at all. And comparing with RBF neural network and support vector machine, decision tree has higher prediction accuracy and reaches 85.6%. Therefore, the decision tree was selected to predict the occurrence of grounding fault.
动车组牵引电机高速铁路接地故障预测决策树RBF神经网络支持向量机故障诊断
EMUtraction motorhigh-speed railwaygrounding fault predictiondecision treeRBF neural networkSVMfault diagnosis
高斐. 胶济铁路通道旅客列车开行相关问题研究[D]. 成都: 西南交通大学, 2016.
GAO Fei. Research on issues related to passenger train of the Jiao-ji railway passage[D]. Chengdu: Southwest Jiaotong University, 2016.
黄彩虹, 梁树林, 曾京, 等. 牵引电机架悬参数对动车转向架稳定性的影响[J]. 铁道车辆, 2014, 52(11): 1-5.
HUANG Caihong, LIANG Shulin, ZENG Jing, et al. Influence of traction motor suspension parameters on stability of EMU bogies[J]. Rolling Stock, 2014, 52(11): 1-5.
王韬. 基于贝叶斯网络的动车组牵引传动系统可靠性分析[D]. 成都: 西南交通大学, 2015.
WANG Tao. Reliability analysis of traction drive system based on Bayesian networks[D]. Chengdu: Southwest Jiaotong University, 2015.
郝阳阳. 动车组运用计划编制方法研究[D]. 石家庄: 石家庄铁道大学, 2015.
HAO Yangyang. Study on the method of preparation of EMU scheduling plan[D]. Shijiazhuang: Shijiazhuang Tiedao University, 2015.
朱一迪. 机车状态信息装置装车试运成功[J]. 机车电传动, 2006(4): 18.
ZHU Yidi. Locomotive status information device commissioning successfully[J]. Electric Drive for Locomotives, 2006(4): 18.
王新伟, 李文权. JL-601A机车走行部诊断系统[J]. 内燃机车, 2007(9): 41-42.
WANG Xinwei, LI Wenquan. Diagnostic system of running gear for JL-601A locomotive[J]. Diesel Locomotives, 2007(9): 41-42.
樊兆峰, 马小平, 邵晓根. 非线性系统RBF神经网络多步预测控制[J]. 控制与决策, 2014, 29(7): 1274-1278.
FAN Zhaofeng, MA Xiaoping, SHAO Xiaogen. RBF neural network multi-step predictive control for nonlinear systems[J]. Control and Decision, 2014, 29(7): 1274-1278.
张棪, 曹健. 面向大数据分析的决策树算法[J]. 计算机科学, 2016, 43(增刊1): 374-379.
ZHANG Yan, CAO Jian. Decision tree algorithm for big data analysis[J]. Computer Science, 2016, 43(Suppl 1): 374-379.
焦卫东, 林树森. 整体改进的基于支持向量机的故障诊断方法[J]. 仪器仪表学报, 2015, 36(8): 1861-1870.
JIAO Weidong, LIN Shusen. Overall-improved fault diagnosis approach based on support vector machine[J]. Chinese Journal of Scientific Instrument, 2015, 36(8): 1861-1870.
0
浏览量
11
下载量
0
CSCD
1
CNKI被引量
关联资源
相关文章
相关作者
相关机构