While the safety concerns of lithium-ion batteries have garnered increasing attention due to the frequent accidents in electric vehicles and energy storage stations, fault diagnosis serves as an effective approach to mitigate the potential risks. However, the continuous minor short-circuit (CMSC) fault, with long incubation and unpredictable inducing factors, poses significant challenges for real-time monitoring. To address this problem, a hierarchical quantitative fault diagnosis method is proposed based on M-distance long short-term memory (MD-LSTM) network. First, the M-distance is extracted from the battery module constant current (CC) charging voltage curves, which captures the two characteristics of the charging plateau hysteresis and the voltage sequential difference (VD) reduction. Then, a two-layer LSTM network is established for the hierarchical quantitative diagnosis of CMSC fault. Experimental validation demonstrates that the proposed method achieves a fault detecting accuracy (FDA) of near 100% and a fault classification accuracy of 99.6%, which are about 60.9% and 64% higher than the conventional methods, respectively.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Quantitative Fault Diagnosis Method for Lithium-Ion Battery Based on MD-LSTM


    Contributors:
    Li, Jinglun (author) / Mao, Ziheng (author) / Gu, Xin (author) / Tao, Xuewen (author) / Shang, Yunlong (author)


    Publication date :

    2025-02-01


    Size :

    3660341 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Vehicle power battery system fault diagnosis method based on LSTM-GAN

    WANG ZHENPO / LIU PENG / JIA ZIRUN et al. | European Patent Office | 2023

    Free access


    Lithium ion battery fault diagnosis method based on voltage reconstruction

    LI SHUN / JI CHANGJIAN / LIU GUOLIANG et al. | European Patent Office | 2024

    Free access

    Turnout fault diagnosis method and system based on 1DCNN-LSTM

    FU YATING / WEN SHIMING / YANG HUI et al. | European Patent Office | 2023

    Free access

    Bearing Fault Diagnosis Method of Bearing Based on LSTM Auto-Encoder

    Lu, Zhencong / Qin, Yong / Cheng, Xiaoqing et al. | British Library Conference Proceedings | 2022