期刊文献+

四种电力机车主变流器的故障诊断方法及仿真对比 被引量:3

Comparison of Fault Diagnosis Method and Simulation of Four Main Converter of Electric Locomotive
下载PDF
导出
摘要 我国铁路运输事业正在高速发展,机车的可靠安全运行对于铁路安全生产运输至关重要。对电力机车主变流器进行及时故障诊断可有效预防和减少铁路运输事故的发生。选取韶山8型(SS8)电力机车的主变流器作为研究对象,在MATLAB软件的Simulink环境下构建SS8型电力机车主变流器的仿真系统,模拟不同故障类型的运行模式,仿真得到相应的输出电压波形;分别利用小波变换、压缩感知方法处理输出电压数据,提取故障特征,构建故障特征向量;最后分别利用BP神经网络的方法对故障特征向量进行类别划分和利用支持向量机(SVM)工具箱构建多故障分类器,进行主变流器故障分类,从而实现故障诊断。 With the rapid development of China's railway transportation, the safe and reliable operation of locomo tives is becoming particularly important for railway safety. The timely fault diagnosis of the main converter of electric locomotives can effectively prevent or reduce the occurrence of railway accidents. In this paper, the main converter of SS8 electric locomotive was investigated and the operation with different fault types were simulated by es tablishing the simulation system of SS8 electric locomotive in Simulink of MATLAB. The output voltage data obtained from the simulation were processed by wavelet transform and compression sensing respectively to extract the fault features and construct the fault eigenvector. The fault diagnosis was finally achieved by categorizing the fault eigenvector with back propagation (BP) neural network and by building a multi fault categorizer to classify the faults of main electric converter with support vector machine (SVM).
作者 鲁其东 杨瑞 LU Qidong YANG Rui(College of Electrical Engineering and Automation,Shandong University of Science and Technology, Qingdao, Shandong 266590, Chin)
出处 《山东科技大学学报(自然科学版)》 CAS 2017年第4期73-79,95,共8页 Journal of Shandong University of Science and Technology(Natural Science)
关键词 小波变换 压缩感知 BP神经网络 支持向量机 故障诊断 wavelet transform compression sensing BP neural network support vector machine fault diagnosis
  • 相关文献

参考文献7

二级参考文献60

  • 1蔡骋,张明,朱俊平.基于压缩感知理论的杂草种子分类识别[J].中国科学:信息科学,2010,40(S1):160-172. 被引量:16
  • 2龙建霞.株洲北牵引变电所地回流过大的原因及对策[J].电气化铁道,2007(3):19-21. 被引量:9
  • 3Holland, J. H. Genetic Algorithms[J]. Scientific American, July, 1992:114-116.
  • 4E Keogh and M Pazzani. A Comparison of Distribution-Based and Classification-Based Approaches [C]// Workshop Artificial Intelligence and Statistics, Francisco, USA, Morgan Kaufmann Publishers, 1999: 225-230.
  • 5Wang Xin, Yu Hongliang, Zhang Lin, et al. Improved Naive Bayesian Classifier Method and the Application in Diesel Engine Valve Fault Diagnostic[C]// IEEE ICMTMA2011, 2011(1): 382-385.
  • 6Andrea Mariscotti. Distribution of the traction return current in AC and DC electric railway system[J]. IEEE Transactions on Power Delivery, 2003, 18(4): 1422-1432.
  • 7IEEE Std 367-1996, IEEE recommended practice for determining the electric power station ground potential rise and induced voltage from a power fault[S]. IEEE, Inc 1996.
  • 8Feffari P, Pozzobon P. Railway lined models for impedance evaluation [C] // International Conference on Harmonics and Power Quality, Athens, Greece, 1998: 641-646.
  • 9CHEN Jian-cheng. Analysis of the earth potential problems of the electrified railway[C] // Asia-Pacific Conference on Environment Electromagnetic, Shanghai, China, 2007: 222-225.
  • 10曹建猷.电气化铁道供电系统[M].北京:中国铁道出版社,1984.71—200.

共引文献149

同被引文献19

引证文献3

二级引证文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部