基于数据挖掘的汽车运行数据采集设备故障诊断方法
|
摘要
提出了一种基于大数据挖掘技术的、用于汽车运行工况数据采集设备的故障诊断方法。该方法依托中国汽车测试工况(CATC)项目和内蒙古道路运输企业节能降耗监控技术研究(NJ-2017-8),运用了k-means故障模式聚类算法、诊断状态参数Apriori关联规则、及相关性分析算法。并进行了案例实证分析。结果表明:采用k-mean算法能有效分析数据采集设备的故障模式,Apriori算法挖掘出的数据采集设备特征参数之间的关联规则与相关性能,有效地找出数据采集设备的故障环节和原因;与设备实际维修试验结果相符。因此,该方法可为数据采集设备的运行维护与管控提供参考。
A fault diagnosis method of vehicles driving cycle data acquisition devices were proposed based on a project sponsored by the China Automotive Test Cycle(CATC) and the Research on Monitoring Technology of Energy Saving and Consumption Reduction for Road Transportation Enterprises in Inner Mongolia(NJ-2017-8) by using large data mining technology, a k-means clustering algorithm, an Apriori algorithm association rules, a correlation analysis algorithm, and made an empirical study with a case. The results show that the fault modes of data acquisition devices can be effectively analyzed by k-means algorithm, and the fault diagnosis and causes of data acquisition devices can effectively find out by Apriori algorithm of association rules and correlation between the characteristic parameters of data acquisition devices, which are consistent with the actual maintenance test results. Therefore, this method provides a reference for the operation, maintenance and control of data acquisition devices.
A fault diagnosis method of vehicles driving cycle data acquisition devices were proposed based on a project sponsored by the China Automotive Test Cycle(CATC) and the Research on Monitoring Technology of Energy Saving and Consumption Reduction for Road Transportation Enterprises in Inner Mongolia(NJ-2017-8) by using large data mining technology, a k-means clustering algorithm, an Apriori algorithm association rules, a correlation analysis algorithm, and made an empirical study with a case. The results show that the fault modes of data acquisition devices can be effectively analyzed by k-means algorithm, and the fault diagnosis and causes of data acquisition devices can effectively find out by Apriori algorithm of association rules and correlation between the characteristic parameters of data acquisition devices, which are consistent with the actual maintenance test results. Therefore, this method provides a reference for the operation, maintenance and control of data acquisition devices.
引文
[1]Witten I H,Frank E,Hall M A,et al.Data Mining:Practical machine learning tools and techniques[M].San Francisco:Morgan Kaufmann,2016:83-139.
[2]Larose D T,Larose C D.Discovering Knowledge in Data:An Introduction to Data Mining[M].Hoboken:John Wiley&Sons,2014:25-45.
[3]Chen Philip C L,ZHANG Chunyang.Data-intensive applications,challenges,techniques and technologies:Asurvey on big data[J].Info Sciences,2014,275:314-347.
[4]张延旭,胡春潮,黄曙,等.基于Apriori算法的二次设备缺陷数据挖掘与分析方法[J].电力系统自动化,2017,41(19):147-151+163.ZHANG Yanxu,HU Chunchao,HUANG Shu,et al.Apriori algorithm based data mining and analysis method for secondary device defects[J].Automat Electric Power Syst,2017,41(19):147-151+163.
[5]胡军,尹立群,李振,等.基于大数据挖掘技术的输变电设备故障诊断方法[J].高电压技术,2017,43(11):3690-3697.HU Jun,YIN Liqun,LI Zhen,et al.Fault diagnosis method of transmission and transformation equipment based on big data mining technology[J].High Voltage Engi,2017,43(11):3690-3697.
[6]刘云,向婵.基于虚构理论对不平衡数据集中少数关联规则挖掘的研究[J].云南大学学报:自然科学版,2017,39(1):33-38.LIU Yun,XIANG Chan.Research on association rule mining for minority classes of unbalanced database by confabulation theory[J].J YunanUniv:Nat Sci,2017,39(1):33-38.
[7]Ku J H.A study on prediction model of equipment failure through analysis of big data based on RHadoop[J].Wireless Pers Commun,2018,98(4):3163-3176.
[8]LIU Binghan,FU Zhongguang,WANG Pengkai,et al.Big-data-mining-based improved k-means algorithm for energy use analysis of coal-fired power plant units:A case study[J].Entropy,2018,20(9),doi:10.3390/e20090702.
[9]Amruthnath N,Gupta T.Fault class prediction in unsupervised learning using model-based clustering approach[C]//Info and Computer Tech(ICICT),2018 Int’l Conf,IEEE,2018:5-12.
[10]SHENG Gehao,HOU Huijuan,JIANG Xiuchen,et al.Anovel association rule mining method of big data for power transformers state parameters based on probabilistic graph model[J].IEEE T Smart Grid,2018,9(2):695-702.
[11]ZHANG Feng,LIU Min,GUI Feng,et al.A distributed frequent item set mining algorithm using Spark for Big Data analytics[J].Cluster Comput,2015,18(4):1493-1501.
[12]ZHOU Xinhao,HUANG Yongfeng.An improved parallel association rules algorithm based on MapReduce framework for big data[C]//Fuzzy Systems and Knowledge Discovery(FSKD),2014 11th Int’l Conf,IEEE,2014:284-288.
[13]WU Xindong,ZHU Xingquan,WU Gongqing,et al.Data mining with big data[J].IEEE T Knowl Data Eng,2014,26(1):97-107.
[2]Larose D T,Larose C D.Discovering Knowledge in Data:An Introduction to Data Mining[M].Hoboken:John Wiley&Sons,2014:25-45.
[3]Chen Philip C L,ZHANG Chunyang.Data-intensive applications,challenges,techniques and technologies:Asurvey on big data[J].Info Sciences,2014,275:314-347.
[4]张延旭,胡春潮,黄曙,等.基于Apriori算法的二次设备缺陷数据挖掘与分析方法[J].电力系统自动化,2017,41(19):147-151+163.ZHANG Yanxu,HU Chunchao,HUANG Shu,et al.Apriori algorithm based data mining and analysis method for secondary device defects[J].Automat Electric Power Syst,2017,41(19):147-151+163.
[5]胡军,尹立群,李振,等.基于大数据挖掘技术的输变电设备故障诊断方法[J].高电压技术,2017,43(11):3690-3697.HU Jun,YIN Liqun,LI Zhen,et al.Fault diagnosis method of transmission and transformation equipment based on big data mining technology[J].High Voltage Engi,2017,43(11):3690-3697.
[6]刘云,向婵.基于虚构理论对不平衡数据集中少数关联规则挖掘的研究[J].云南大学学报:自然科学版,2017,39(1):33-38.LIU Yun,XIANG Chan.Research on association rule mining for minority classes of unbalanced database by confabulation theory[J].J YunanUniv:Nat Sci,2017,39(1):33-38.
[7]Ku J H.A study on prediction model of equipment failure through analysis of big data based on RHadoop[J].Wireless Pers Commun,2018,98(4):3163-3176.
[8]LIU Binghan,FU Zhongguang,WANG Pengkai,et al.Big-data-mining-based improved k-means algorithm for energy use analysis of coal-fired power plant units:A case study[J].Entropy,2018,20(9),doi:10.3390/e20090702.
[9]Amruthnath N,Gupta T.Fault class prediction in unsupervised learning using model-based clustering approach[C]//Info and Computer Tech(ICICT),2018 Int’l Conf,IEEE,2018:5-12.
[10]SHENG Gehao,HOU Huijuan,JIANG Xiuchen,et al.Anovel association rule mining method of big data for power transformers state parameters based on probabilistic graph model[J].IEEE T Smart Grid,2018,9(2):695-702.
[11]ZHANG Feng,LIU Min,GUI Feng,et al.A distributed frequent item set mining algorithm using Spark for Big Data analytics[J].Cluster Comput,2015,18(4):1493-1501.
[12]ZHOU Xinhao,HUANG Yongfeng.An improved parallel association rules algorithm based on MapReduce framework for big data[C]//Fuzzy Systems and Knowledge Discovery(FSKD),2014 11th Int’l Conf,IEEE,2014:284-288.
[13]WU Xindong,ZHU Xingquan,WU Gongqing,et al.Data mining with big data[J].IEEE T Knowl Data Eng,2014,26(1):97-107.