With the increase of the scale and quantity of China’s EMU trains and the continuous improvement of the level of integrated intelligence, the application and maintenance system of EMU has accumulated a large number of fault warning information data. It is of great significance to reduce the scope of fault search and improve the efficiency of maintenance by using an efficient association rule mining algorithm to obtain the correlation knowledge among alarms from the data of fault alarm information. FP-Growth algorithm is one of the classical methods in association rule mining algorithm, which is used to mine frequent itemsets in the data set. To solve the problem of unequal importance proportion of fault alarm data items, a weight assigned FP-Growth algorithm was proposed, which combined the importance degree of fault alarm and calculated the support threshold value of transaction items, thus generating a conditional pattern base. The experimental results show that the weight assigned FP-Growth algorithm can effectively reduce the number of mining rules, and accelerate the algorithm running speed with the variation of support threshold, which will improve the efficiency of fault warning data mining of EMU.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on Alarm Correlation Analysis for EMU Train Based on Association Rule Mining Algorithm


    Additional title:

    Lect. Notes Electrical Eng.


    Contributors:
    Qin, Yong (editor) / Jia, Limin (editor) / Liang, Jianying (editor) / Liu, Zhigang (editor) / Diao, Lijun (editor) / An, Min (editor) / Wang, Chong (author) / Wang, Lide (author) / Qiu, Yu (author) / Yang, Yueyi (author)

    Conference:

    International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021



    Publication date :

    2022-02-23


    Size :

    8 pages





    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English




    Research on Alarm Correlation Analysis for EMU Train Based on Association Rule Mining Algorithm

    Wang, Chong / Wang, Lide / Qiu, Yu et al. | British Library Conference Proceedings | 2022



    Factors correlation mining on railway accidents using association rule learning algorithm

    Wang, Yakun / Zheng, Wei / Dong, Hairong et al. | IEEE | 2020


    Train approaching alarm device and train approaching alarm method

    ZHANG PENG / TANG FEI / LI JINBO et al. | European Patent Office | 2023

    Free access

    Train alarm circuit, train alarm method, device, equipment and medium

    HUANG ZHEN / CHU YONGCHEN / LIU BINPU et al. | European Patent Office | 2023

    Free access