The invention discloses a high-precision fitting method of a motor MAP and application thereof. The motor MAP is made based on a motor efficiency fitting value output by a trained BP neural network; the BP neural network training method comprises the following steps: taking actual motor efficiency values of a motor at different rotating speeds and torques as samples to train the BP neural network, so that an error between a motor efficiency fitting value obtained through the BP neural network and the actual motor efficiency value is within a preset error range; according to the method, the motor efficiency fitting value output by the BP neural network is used as a data basis, a high-precision motor MAP can be obtained, and a reliable and stable data basis is provided for a vehicle modular multi-phase motor to realize an optimal efficiency algorithm.

    本发明公开了一种电机MAP图的高精度拟合方法及其应用,基于完成训练后的BP神经网络输出的电机效率拟合值来制作电机MAP图;其中,所述BP神经网络的训练方法包括:对所述电机在不同转速、转矩情况下的实际电机效率值作为样本对所述BP神经网络进行训练,使得通过BP神经网络得到的电机效率拟合值与实际电机效率值之间的误差处于在预设误差范围内;本发明将该BP神经网络输出的电机效率拟合值作为数据基础,可以得到高精度的电机MAP图,为车辆用模块化多相电机实现最优效率算法提供了可靠稳定的数据基础。


    Access

    Download


    Export, share and cite



    Title :

    High-precision fitting method of motor MAP and application of high-precision fitting method


    Additional title:

    一种电机MAP图的高精度拟合方法及其应用


    Contributors:
    ZHANG HENGLIANG (author) / HUA WEI (author) / BU YANZHU (author) / LI YUGANG (author) / HU YIBAO (author) / HU JINLONG (author) / LI SHENG (author) / LIU YAJUN (author) / ZHOU JIANHUA (author) / ZHOU WEI (author)

    Publication date :

    2023-05-02


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06T Bilddatenverarbeitung oder Bilddatenerzeugung allgemein , IMAGE DATA PROCESSING OR GENERATION, IN GENERAL / B60L PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES , Antrieb von elektrisch angetriebenen Fahrzeugen / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen