摘要
针对传统的模糊自适应PID算法在车辆稳定控制的应用中还存在控制精度不高的问题,本文设计了一种以RBF神经网络优化模糊自适应PID算法为基础的车辆稳定性控制模型。这一模型首先优化RBF神经网络算法隐含层的中心数目,这一优化过程主要是借助减聚类的方法进行。然后采用Logistic对其中心值进行精度的提升,最后采用改进RBF神经网络对模糊自适应PID控制算法进行改进,以达到更精确的控制。仿真实验结果发现,与PID算法相比,基于模糊自适应PID算法设计的这一车辆稳定性控制模型的控制精度更高,并且在车辆稳定性控制应用中具有更好的效果。
According to low control accuracy of the traditional fuzzy adaptive PID algorithm in the application of vehicle stability control, a vehicle stability control model is designed based on the fuzzy adaptive PID algorithm with the optimized RBF neural network. First, the model to optimize the center numbers of hidden layer in the RBF neural network algorithm, the process is mainly with the help of the subtraction clustering method. And then uses the Logistic center to increase its value accuracy. Finally with the improved RBF neural network to improve the fuzzy adaptive PID control algorithm, in order to achieve more precise control. The simulated experiments results show that, compared with PID algorithm and fuzzy adaptive PID algorithm, the designed vehicle stability control model has higher control precision, and has better effect in vehicle stability control applications.
出处
《科技通报》
北大核心
2016年第1期183-186,共4页
Bulletin of Science and Technology