The invention discloses a CMAC-based intelligent driver model construction method, which adopts a CMAC local neural network and a single neuron adaptive PID controller as decision modules of a driver model, and the CMAC neural network has locality, that is, only activated weights are updated after learning each time, so that the CMAC neural network has good real-time performance. The single-neuron adaptive PID controller is a single-neuron network which is designed according to incremental PID and can change proportion, integral and differential coefficients in real time, and the stability and the anti-interference capability of the controller can be improved. According to the method, the CMAC neural network and the adaptive neuron controller form a composite controller, the adaptive neuron controller can be used for judging the performance of the CMAC controller, the stability and the anti-interference capability of a control system can be improved, and the method has the advantages of being good in real-time performance, small in output error and high in robustness.
本发明公开了一种基于CMAC的智能驾驶员模型构建方法,采用了CMAC局部神经网络和单神经元自适应PID控制器作为驾驶员模型的决策模块,CMAC神经网络具有局部性,即每次学习后只对被激活的权值进行更新,具有很好的实时性。单神经元自适应PID控制器是根据增量式PID设计出的可以实时改变比例、积分、微分系数的单神经元网络,可以提高控制器的稳定性和抗干扰能力。本发明将CMAC神经网络与自适应神经元控制器构成复合控制器,不仅能用自适应神经元控制器评判CMAC控制器的性能,也能提高控制系统的稳定性和抗干扰能力,具有实时性好、输出误差小、鲁棒性强的特点。
Intelligent driver model construction method based on CMAC
基于CMAC的智能驾驶员模型构建方法
2022-05-27
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 |
Online Contents | 2004
Online Contents | 2007
|Freeway Traffic Density Control Based on CMAC
Trans Tech Publications | 2012
|CMAC-based modelling for HPDDL welding process control
Automotive engineering | 2006
|