The invention relates to a hybrid electric vehicle energy management control method based on stochastic dynamic programming. The method comprises the steps that a Gaussian mixture model is adopted to conduct clustering analysis on historical data of vehicle driving working conditions; establishing a probability transfer matrix for each type of clustered working conditions by adopting a nearest neighbor method, and solving a corresponding energy management strategy by adopting a random dynamic programming iterative algorithm according to the corresponding probability transfer matrix; the posterior probability of the Gaussian mixture model is used as a weight, the energy management strategies of different types of working conditions are linearly combined, and the combined energy management strategies are used as a final energy management strategy; and then the driving state of the hybrid electric vehicle is correspondingly controlled. Compared with the prior art, the method has the advantages that the classification model is established by performing clustering analysis on a large amount of real-time historical working condition data, the energy management strategies of different types of working conditions are determined in combination with the random dynamic programming iterative algorithm, the adaptability and accuracy of energy management control can be effectively improved, and the process is simple and efficient.

    本发明涉及一种基于随机动态规划的混合动力汽车能量管理控制方法,该方法包括:采用高斯混合模型对车辆行驶工况的历史数据进行聚类分析;采用最近邻方法对聚类后的每一类工况建立概率转移矩阵,根据相应的概率转移矩阵,采用随机动态规划迭代算法,求解相应的能量管理策略;再以高斯混合模型的后验概率作为权重,将不同类别工况的能量管理策略进行线性组合,以此作为最终的能量管理策略;进而相应控制混合动力汽车的行驶状态。与现有技术相比,本发明通过对大量的实时历史工况数据进行聚类分析,以建立得到分类模型,结合随机动态规划迭代算法,以确定出不同类别工况的能量管理策略,能够有效提高能量管理控制的适应性和精准性,过程简单高效。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Hybrid electric vehicle energy management control method based on random dynamic programming


    Weitere Titelangaben:

    一种基于随机动态规划的混合动力汽车能量管理控制方法


    Beteiligte:
    GUO RONG (Autor:in) / SUN ZIYI (Autor:in)

    Erscheinungsdatum :

    2022-11-01


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06K Erkennen von Daten , RECOGNITION OF DATA




    Energy Management Strategy of Hybrid Electric Vehicle using Stochastic Dynamic Programming

    Lee, Heeyun / Cha, Suk Won / Kim, Hyunsup et al. | British Library Conference Proceedings | 2015


    Energy Management Strategy of Hybrid Electric Vehicle using Stochastic Dynamic Programming

    Lee, Heeyun / Kim, Hyunsup / Kim, Seok-Joon et al. | SAE Technical Papers | 2015


    Hybrid electric vehicle energy management control method

    LIU KE / GAO BAIJUN / NIE XIANGHONG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Hybrid electric vehicle real-time prediction energy management method based on convex programming

    MA ZETAO / TIAN TIAN / CUI QIONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff