清洗机器人自适应PID控制研究

摘要

Cleaning robot is such a complex nonlinear, time - varying system, that the conventional control method is difficult to achieve a satisfactory control effect. We proposed an intelligent control method by combining BP neural network with the traditional PID control, and used the identification network to approximate the controlled system to get the gradient information that the BP neural network learning needs, thus to realize the parameters online adjustment of the PID control, and to adapt to the dynamic changes of the control system. Approximating simulation was carried out on the system identification model under sine input. Simulation results indicate that the adaptive PID control based on the BP neural network can improve the real - time, enhance the stability of the system, and achieve a better control quality than the traditional PID control.%对于清洗机器人这样一个复杂的非线性、时变系统,常规PID控制方法难以达到满意的控制效果.提出了一种BP神经网络与常规PID(比例、积分、微分)控制相结合的智能控制方法,利用辨识网络逼近被控系统获得BP神经网络学习所需梯度信息,从而实现PID控制参数的在线调整,以适应控制系统的动态变化.对系统辨识模型进行了正弦输入下的逼近仿真；在对建立的运动学模型经离散化处理,得到其传递函数的基础上,对控制系统进行的角阶跃输入响应进行了对比仿真分析.仿真结果表明,辨识模型能很好的逼近被控对象,基于BP神经网络的自适应PID控制方法在解决清洗机器人控制问题时,提高了控制的响应时效,增强了系统的稳定性,获得了比传统PID控制更好的控制品质.