The invention provides a self-adaptive cruise control method and device based on an RBF neural network. The method comprises the following steps: acquiring a self-adaptive cruise input variable; the self-adaptive cruise input variable is input into a torque control model, and the engine torque variation output by the torque control model is obtained; wherein the torque control model is obtained by performing off-line optimization on a previously established radial basis function (RBF) neural network by using an adaptive particle swarm optimization algorithm; and according to the engine torque variable quantity obtained through control, the vehicle is controlled to conduct self-adaptive cruise. According to the method, the RBF neural network is optimized based on the adaptive particle swarm optimization algorithm so as to adaptively adjust parameters, the efficiency and effect of parameter optimization are remarkably improved, the adaptability and reliability of the model are enhanced, adaptive cruise control can be conveniently carried out by using the torque control model obtained through optimization, and the method is suitable for large-scale popularization and application. And the precision and the response speed of adaptive cruise control are improved.
本发明提供一种基于RBF神经网络的自适应巡航控制方法及装置,方法包括:获取自适应巡航输入变量;将自适应巡航输入变量输入至扭矩控制模型中,得到扭矩控制模型输出的发动机扭矩变化量;其中,扭矩控制模型是利用自适应粒子群优化算法对在先建立的径向基函数RBF神经网络进行离线优化得到的;根据控制获得的发动机扭矩变化量,控制车辆进行自适应巡航。本发明通过利用基于自适应粒子群优化算法优化RBF神经网络,以自适应调整参数,显著提高参数优化的效率和效果,增强模型的适应能力和可靠性,进而便于利用优化得到的扭矩控制模型进行自适应巡航控制,提高自适应巡航控制的精度和响应速度。
Adaptive cruise control method and device based on RBF neural network
基于RBF神经网络的自适应巡航控制方法及装置
08.11.2024
Patent
Elektronische Ressource
Chinesisch
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 |
Adaptive cruise control method based on neural network approximation
Europäisches Patentamt | 2024
|