The invention relates to the field of machine learning and the field of load prediction, in particular to an LSTM model generation method, a charging duration prediction method and a medium. Accordingto the method, the advantages of a machine learning method are used, the LSTM artificial neural network is used for giving the charging remaining duration, different prediction stages can be effectively selected according to the current SOC state, voltage, current and other information, charging duration prediction in a segmented charging mode is carried out, prediction accuracy can be improved,the influence of overcharge and other phenomena on the safety and the service life of an electric vehicle is reduced; in addition, in the establishment of the LSTM model of the segmented charging mode, an applicant changes a general charging mode from constant current to constant voltage charging along with the increase of the SOC value of the remaining electric quantity in the actual charging process of the electric vehicle, sets the threshold value of the SOC to be 80%, establishes the LSTM models and carries out segmented prediction, the prediction stability and reliability are greatly improved, and the method is simple and fast in processing.

    本发明涉及机器学习领域和负荷预测领域,更具体地,本发明涉及一种LSTM模型的生成方法、充电时长预测方法及介质。本发明结合了机器学习方法的优势,利用长短时记忆人工神经网络(LSTM)来给出充电剩余时长,可以有效的根据当前的SOC状态、电压、电流等信息选择不同的预测阶段,进行分段充电模式下的充电时长预测,可提高预测的准确性,减少过充等现象的发生对电动汽车安全和使用寿命的影响;且在进行分段充电模式的LSTM模型的建立中,申请人根据电动汽车实际充电过程中,随着剩余电量SOC值的增加,一般充电模式会从恒流改为恒压充电,将SOC的阈值设为80%,分别建立LSTM模型,并分段进行预测,极大提高了预测的稳定性和可靠性,且方法简单,处理快速。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    LSTM model generation method, charging duration prediction method and medium


    Weitere Titelangaben:

    一种LSTM模型的生成方法、充电时长预测方法及介质


    Beteiligte:
    TANG XURI (Autor:in) / LI CHUNXI (Autor:in) / WEI GAOYI (Autor:in)

    Erscheinungsdatum :

    2021-01-12


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    Charging duration prediction method and device, electronic equipment and storage medium

    WANG ZHIPING / NI SIYU | Europäisches Patentamt | 2023

    Freier Zugriff

    Battery charging duration prediction method and device, electronic equipment and storage medium

    RAO WEI / LEI JINGJING / ZHANG QINGLING et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    New energy vehicle wireless charging duration prediction method and wireless charging device

    GUO RENWEI / ZHOU MENGXIONG / TANG JIANKANG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    LSTM LSTM-based future threat prediction method and apparatus

    PARK YOUNG TACK / JEON MYUNG JOONG / KIM MIN SUNG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    LSTM model-based vulnerable traffic participant trajectory prediction method

    ZHANG XI / YIN CHENGLIANG / CHEN HAO et al. | Europäisches Patentamt | 2022

    Freier Zugriff