The invention provides a lithium ion battery energy state prediction method based on a neural network model fused by convolution and gating circulation units, and the method comprises the steps: obtaining the data of a lithium ion power battery, and carrying out the preprocessing of the data; dividing the preprocessed data into a training set and a test set; building a neural network model with fusion of convolution and gating circulation units, inputting the training set into a neural network for training, and enabling the neural network to learn features between data; inputting the test set into the neural network, predicting the energy state of the battery, and when the test effect of the model on the test set is not ideal, adjusting the parameters of the model until the effect is ideal; and adopting an absolute mean error and a root-mean-square error as evaluation indexes of a prediction result, and checking prediction data of the model. The method can effectively improve the estimation of the SOE of the electric vehicle, further improves the prediction of the remaining endurance mileage, enables a driver to select the charging time and the driving route according to the prediction result, and effectively relieves the mileage anxiety of the driver.

    本发明提供一种基于卷积与门控循环单元融合的神经网络模型的锂离子电池能量状态预测方法,包括:获取锂离子动力电池数据,对数据进行预处理;将预处理后的数据划分为训练集和测试集;搭建卷积与门控循环单元融合的神经网络模型,并将训练集输入神经网络进行训练,使神经网络学习数据之间特征;将测试集输入神经网络,预测电池能量状态,且当模型对测试集进行测试的效果不理想时,调整模型的参数直到效果理想;采用平均绝对误差、均方根误差作为预测结果的评价指标,对模型的预测数据进行检验。本发明能够有效提高电动汽车SOE的估计,进而提高剩余续航里程的预测,驾驶员根据预测结果自行选择充电时间和行驶路线,有效地缓解驾驶员的里程焦虑。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Lithium ion battery energy state prediction method


    Weitere Titelangaben:

    一种锂离子电池能量状态预测方法


    Beteiligte:
    LI JUNJIE (Autor:in) / ZHENG LI (Autor:in) / MOU JIANHUI (Autor:in) / DUAN PEIYONG (Autor:in) / ZHAO JINGRUI (Autor:in) / WANG YANGWEI (Autor:in) / LIU XINHUA (Autor:in) / WANG BO (Autor:in) / WEI XIANGKANG (Autor:in)

    Erscheinungsdatum :

    2024-03-15


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G01R Messen elektrischer Größen , MEASURING ELECTRIC VARIABLES



    BATTERY STATE PREDICTION DEVICE AND BATTERY STATE PREDICTION METHOD

    YOON HO BYUNG | Europäisches Patentamt | 2022

    Freier Zugriff

    BATTERY STATE PREDICTION DEVICE AND BATTERY STATE PREDICTION METHOD

    YOON HO BYUNG | Europäisches Patentamt | 2021

    Freier Zugriff

    Lithium battery SOH prediction method and device

    YU HUI / GUO JIELONG / LUO PENG et al. | Europäisches Patentamt | 2023

    Freier Zugriff

    Lithium battery dynamic peak power prediction method

    PIAO CHANGHAO / YI MAOQING / WANG PINGZHONG et al. | Europäisches Patentamt | 2020

    Freier Zugriff