基于大数据的高速动车组关键部件故障诊断技术研究

基金项目: 国家863计划资助项目（2015AA043701）

详细信息

Failure diagnosis for key parts of high-speed EMU based on big data

Department of Information Technology, CSR QINGDAO SIFANG CO. LTD., Qingdao 266011, China

摘要: 高速动车组的零部件故障是由多种因素引起,故障诊断需要对多个环节及其相互影响规则进行分析判断。关联规则挖掘技术在关联性发现方面有较强的优势,可以充分发现在高速动车组零部件故障与动车组实时状态的关联关系。本文介绍大数据挖掘、关联规则及Apriori算法等基础知识。将Apriori算法用于高速动车组故障诊断,发现故障规律,以生成强关联规则,为高速动车组诊断提供决策依据。
- 大数据分析 /
- 故障诊断 /
- 关联规则挖掘 /
- Apriori算法 /
- 数据预处理
Abstract: Many factors could cause the parts failure of the high-speed EMU. Failure diagnosis should be focused on the analysis of multiple links and their interaction rules. Association rule mining technique has advantages in association discovery, which can discover the relationship between parts failure of EMU and real-time status of high-speed EMU. This article introduced basic concept of big data mining, association rule and Apriori Algorithm. Apriori Algorithm was adopted to diagnose failure of high-speed EMU, find the rule of failure, and generate strong association rule. This strong association rule would become helpful to make decisions on the failure diagnosis for key parts of high-speed EMU.
- big data analysis /
- failure diagnosis /
- association rule mining /
- Apriori Algorithm /
- data preprocessing

[1]	刘智慧,张泉灵.大数据技术研究综述[J].浙江大学学报：工学版,2014,48（6）：957-972.
[2]	马高峰.关联规则在电力变压器故障评估中的应用研究[D]. 重庆：重庆大学,2010.
[3]	J. Han, and M.Kamber. Data mining: Concepts and techni-ques[M]. Morgan Kaufmann. San Francisco, CA. 2001.
[4]	Agrawal R, Srikant R. Fast algorithm for mining association rules[C]. In :Proceedings of the 1994 International Conference on Very Large Databases, Santiago ,Chile, 1994: 487-499.
[5]	Chen Han Liao. Transaction-Filtering Data mining and A Predictive Model for Intelligent Data Management[D].Cranfield University. 2008.
[6]	黄学文,刘春明,冯璨,等.CRH3高速动车组故障诊断系统[J].计算机集成制造系统,2010,16（10）：2314.