Hot-spot temperature (HST) is a typical indicator of transformer’s health status, and accurate prediction of HST is critical for prognosis and health management (PHM) of traction transformer in urban rail transit (URT), where dramatically fluctuating loads and complex climates pose serious challenges. This article proposed a novel deep-learning-enabled method to predict multispot temperatures of transformer simultaneous using long short-term memory (LSTM) neural networks. Real-world operation data collected from Qingdao Metro over a year-long period were used to train the prediction model and verify its validity. The most appropriate transformer-related parameters were selected as the inputs of model by Pearson correlation coefficients (PCCs) to improve the accuracy and efficiency of the model. Besides, the dropout and early stopping techniques are used to prevent model from overfitting. Furthermore, the robustness and versatility of proposed method were verified by testing the data on different seasons of multiple transformers, and the superiority of the method was also proved by comparing with other methods. The results show that the proposed model can achieve accurate on-line temperature prediction of transformer, and the mean relative error of 16-min-ahead HST prediction is less than 0.26%. The proposed method can provide a reference for PHM of transformers.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Simultaneous Multispot Temperature Prediction of Traction Transformer in Urban Rail Transit Using Long Short-Term Memory Networks


    Contributors:
    Li, Chao (author) / Chen, Jie (author) / Xue, Chengjian (author) / Liu, Zhigang (author) / Davari, Pooya (author)


    Publication date :

    2023-09-01


    Size :

    4432040 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Trajectory Prediction of Urban Rail Transit Based on Long Short-Term Memory Network

    He, Yijuan / Lv, Jidong / Zhang, Daqian et al. | IEEE | 2021


    Traction transformer assembly of rail transit vehicle

    HU GUI / ZHONG HENG / ZHU LILI et al. | European Patent Office | 2022

    Free access

    Traction transformer oil tank and rail transit vehicle

    LONG GUZONG / LIU HAIBIN / TONG HAO et al. | European Patent Office | 2021

    Free access


    Bidirectional traction rectifying device for urban rail transit

    DAI WEI / SHU GUANLAN | European Patent Office | 2021

    Free access