基于代价敏感RBF神经网络的道岔故障诊断系统

马艳东; 崔能西

基于代价敏感RBF神经网络的道岔故障诊断系统

马艳东^1,2,
崔能西³

1.
河北省科学院应用数学研究所,石家庄 050081;
2.
河北省信息安全认证工程技术研究中心,石家庄 050081;
3.
石家庄精英中学,石家庄 050081

详细信息

作者简介:
马艳东,助理研究员;崔能西,助理工程师。

中图分类号: U213.6:TP39
计量
- 文章访问数: 54
- HTML全文浏览量: 2
- PDF下载量: 25
出版历程
- 收稿日期: 2017-09-23
- 刊出日期: 2018-02-24

Switch fault diagnosis system based on cost sensitive RBF neural network

MA Yandong^1,2,
CUI Nengxi³

1.
Institute of Applied Mathematics, Hebei Academy of Sciences, Shijiazhuang 050081, China;
2.
Hebei Information Security Authentication Engineering Technology Research Center, Shijiazhuang 050081, China;
3.
Shijiazhuang Jingying Middle School, Shijiazhuang 050081, China

摘要

摘要: 针对铁路道岔故障中几种常见类型故障,为尽量减少道岔故障误分类所造成的损失,特建立基于遗传算法的代价敏感RBF神经网络模型以及基于该模型的道岔故障诊断系统。模型通过建立代价敏感适应度函数,实现基于遗传算法的RBF神经网络向代价最优的方向进行随机搜索。利用某车站道岔动作电流监测数据进行验证,证明系统能够提高故障数据的识别精度,降低故障数据的误分类代价。该系统可帮助维护人员快速、准确地对道岔故障进行诊断,缩短故障处理时间,提高铁路行车的安全性。
- 代价敏感 /
- RBF神经网络 /
- 遗传算法 /
- 道岔动作电流
Abstract: In order to diagnose several common types of switch faults and reduce the loss caused by misclassification, this paper presented a new switch fault diagnosis system which was based on the genetic algorithm based cost sensitive RBF neural network model. In this model, the cost sensitive fitness function was established to guide the optimal direction of random search based on genetic algorithm, which has lower false classification cost. The system was validated by using the monitoring data of switch action current at a certain railway station. The result showed that this system could not only improve the overall recognition accuracy of the fault data, but also significantly reduce the proportion of false classification of fault data. So this system could help railway maintain personnel quickly and accurately diagnosis the switch fault, reduce the fault processing time, and improve the safety of railway traffic.
- cost sensitive /
- RBFNN(radial basis function neural network) /
- genetic algorithm /
- switch action current

HTML全文

参考文献(8)

[1]	陈振东,肖先勇,李长松,等.基于代价敏感极限学习机的电力系统暂态稳定评估方法[J].电力自动化,2016,36(3):118-123.
[2]	付忠良. 多标代价敏感分类集成学习算法[J].自动化学报,2014,40(6):1075-1085.
[3]	廖元秀,周生明.误差在Cost-Sensitive分类中的应用[J].广西师范大学学报:自然科学版,2011,29(2).
[4]	Friedhelm Schwenker,Hans A.Kestler,Günther Palm.Three learning phase for radial-basis-function networks[J].Neural networks 14 (2001) 439-458, 18 December 2000.
[5]	段录平,周丽娟,王宇.基于RBF神经网络的在线分类挖掘系统[J].铁路计算机应用,2007,16(3):40-42.
[6]	葛继科,邱玉辉,吴春明,等.遗传算法研究综述[J].计算机应用研究,2008,25(10):2911-2916.
[7]	梅欢,马艳东,单九思,等. 基于样条插值与RBF网络的道岔故障诊断系统[J]. 计算机技术与发展,2017,27(5):160-163,169.
[8]	李雅美,魏文军.基于模糊神经网络的道岔故障诊断系统研究[J].铁路计算机应用,2012,21(1):35-39.