Intelligent Fault Diagnosis for ZPW-2000 Track Circuit Based on Rough Set Theory and Fuzzy Cognitive Map

被引：0

作者：

Dong Y. ^{[1
]}

Chen X. ^{[1
]}

机构：

[1] School of Automation & Electrical Engineering, Lanzhou Jiaotong University, Lanzhou

来源：

Tiedao Xuebao/Journal of the China Railway Society | 2018年 / 40卷 / 06期

关键词：

Fault diagnosis; Fuzzy cognitive map classifier; Rough set theory; ZPW-2000 track circuit;

D O I：

10.3969/j.issn.1001-8360.2018.06.011

中图分类号：

学科分类号：

摘要：

In view of the disadvantages of low diagnostic efficiency, long diagnosis cycle and high depen-dence on the experiences of data analyzers in the fault diagnosis of ZPW-2000 track circuit fault by manual analysis of monitoring data, the concepts of fuzzy cognitive map and rough set theory were introduced into fault diagnosis of ZPW-2000 track circuit. Firstly, the attribute reduction of the original fault data was performed by the main component heuristic algorithm, to obtain the fault characteristic parameters. Then the fuzzy cognition map was used to construct the classifier based on reduction attribute and fuzzy cognitive map, to complete FCM weights learning in term of the adaptive genetic algorithm during the process. Computer simulations show that the method of using the rough set to extract the features on the basis of fuzzy cognitive map, and then to diagnose the fault of the ZPW-2000 track circuit is effective and feasible. Compared with the diagnosis method of using manual analysis of monitoring data, the classifier based on attribute reduction and fuzzy cognitive map has high failure recognition rate and short diagnosis time. © 2018, Department of Journal of the China Railway Society. All right reserved.

引用

页码：83 / 89

页数：6

共 14 条

[1]

Zhang X., Du X., Liu C., Development of Railway Station Signaling Control Equipment Fault Diagnosis Expert System, Journal of the China Railway Society, 31, 3, pp. 43-49, (2009)

[2]

Zhao L., Ran Y., Mu J., A Comprehensive Fault Diagnosis Method for Jointless Track Circuit Based on Genetic Algorithm, China Railway Science, 31, 3, pp. 107-113, (2010)

[3]

Huang Z., Wei X., Liu Z., Fault Diagnosis of Railway Track Circuits Using Fuzzy Neural Network, Journal of the China Railway Society, 34, 11, pp. 54-59, (2012)

[4]

Mi G., Yang R., Liang L., Research on Diagnosis Method of Complex Fault Diagnosis of Track Circuit Based on Combined Model, Journal of the China Railway Society, 36, 10, pp. 65-68, (2014)

[5]

Yang S., Wei X., Fan B., Et al., Study of Data-based Hybrid Algorithm on Track Circuit Fault Diagnosis, Journal of Beijing Jiaotong University, 36, 2, pp. 40-46, (2012)

[6]

Jiang F., Du J., Ge Y., Et al., Sequence Outlier Detection Based on Rough Set theory, Acta Flectronica Sinica, 39, 2, pp. 345-350, (2011)

[7]

Zhang Q., Hu R., Yao L., Et al., Risk DTRS Attribute Reduction Based on Attribute Importance, Control and Decision, 31, 7, pp. 1199-1205, (2016)

[8]

Ge H., Li L., Yang C., Discernibility Matrix-based Reduct Representation and Quick Algorithms, Control and Decision, 31, 1, pp. 12-20, (2016)

[9]

Ma L., Zheng X., Yin J., Short-term Load Forecasting Based on Main Attribute-component Heuristic Algorithm, Electric Power Science and Engineering, 31, 1, pp. 27-30, (2015)

[10]

Zhang G., Liu Y., Wang Y., Reference Algorithm Text Categorization Based on Fuzzy Cognitive Maps, Computer Engineering and Applications, 43, 12, pp. 155-157, (2007)

← 1 2 →