自动巡航汽车自适应逆控制的建模与仿真

研究神经网络非线性系统的自适应建模和逆建模策略用于非线性的自动巡航系统的控制及可行性。通过对自适应逆控制方法与现行的反馈控制、模糊控制、PID控制进行对比,并在有干扰的情况下系统需要一定的收敛时间,通过运用Matlab软件进行仿真。根据仿真结果分析,当对象输出没有受到干扰时,其在线辨识对象模型和逆模型有十分好的效果;当对象输出存在一些干扰时,由于干扰的存在,需要一段时间来将两个辨识模型收敛。因此,基于动态神经网络的非线性自适应逆控制系统是十分可行的。

Modeling and simulation for adaptive inverse control of auto cruise cars

The adaptive modeling and inverse modeling strategies of neural network nonlinear system are investigated for the control of nonlinear automatic cruise system. The adaptive inverse control method is compared with the available feedback control,fuzzy control and PID control. The convergent time required by the systems in the context of interference was simulated with MATLAB software. According to the analysis based on simulation results,it is known that its online identification object model and inverse model have very good results when the object output is not affected by interference,and a certain period is needed due to interference to make convergence of two identification models when some interference exists in the object output. Therefore,the nonlinear adaptive inverse control system based on dynamic recurrent neural network is quite feasible.