The invention relates to a vehicle motion state calculation method. The method comprises the following steps: measuring basic data of vehicle kinematics by using a sensor group; inputting the basic data of the vehicle kinematics into the vehicle motion state calculation model; outputting vehicle kinematics parameters; wherein the model comprises three layers of neural networks; the input of the first-layer neural network is vehicle kinematics basic data measured by using the sensor group, and the output of the first-layer neural network is the calculated wheel load; the input of the second-layer neural network is vehicle kinematics basic data measured by using the sensor group and the wheel load calculated by the first-layer neural network, and the output of the second-layer neural network is the real-time vehicle speed of the vehicle; the input of the third-layer neural network is vehicle kinematics basic data measured by using a sensor group, a wheel load calculated by the first-layer neural network and a wheel load reference value obtained through an equivalent physical model; the output is vehicle kinematics parameters. Compared with the prior art, the method has the characteristics of high precision, fast network calculation after fitting and the like.
本发明涉及一种车辆运动状态计算方法,包括:使用传感器组测量车辆运动学基本数据;将车辆运动学基本数据输入至车辆运动状态计算模型中;输出车辆运动学参数;其中模型包括三层神经网络;第一层神经网络的输入为使用传感器组测量的车辆运动学基本数据,输出为计算得到的车轮载荷;第二层神经网络的输入为使用传感器组测量的车辆运动学基本数据及由第一层神经网络计算得到的车轮载荷,输出为车辆实时车速;第三层神经网络的输入为使用传感器组测量的车辆运动学基本数据、由第一层神经网络计算得到的车轮载荷及通过等效物理模型得到的车轮载荷参考值;输出为车辆运动学参数。与现有技术相比,本发明具有精确度高、拟合之后的网络计算快等特点。
Vehicle motion state calculation method
一种车辆运动状态计算方法
2023-07-04
Patent
Electronic Resource
Chinese
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 |
European Patent Office | 2019
|VEHICLE, VEHICLE MOTION STATE ESTIMATION DEVICE AND VEHICLE MOTION STATE ESTIMATION METHOD
European Patent Office | 2019
|European Patent Office | 2021
|