基于RBF网络自整定PID控制的应用研究

经典PID的控制参数难以精确整定，且依赖于对象的数学模型，故自适应性较差，很难适应具有非线性、时变不确定性的被控对象，控制精度难以保证。该文对纯滞后工业对象提出了一种基于RBF神经网络PID参数自整定的控制方法，采用将RLS算法和梯度法相融合的新型学习算法，并将这种控制方法与PID控制器相结合应用于纯滞后工业对象中，克服了不确定性对控制对象性能的不利影响，解决了传统PID控制鲁棒性差，及需要预先知道受控对象精确数学模型的问题。仿真结果表明了该方法的鲁棒性和跟踪性能均优于传统PID控制方法。

Application of Self Tuning PID Controller Based on RBF Network

It is difficult to get classic PID controller precise parameters, and PID control method is based on the precise mathematical model. Generally, its adaptiveability is poor. So, PID control method is not adaptive to nonlinear and time-variant plants. It is impossible to insure the accuracy of the system. A self tuning PID control strategy based on RBF network for dead time objects in industry is stated in this paper. By using a new learning algorithm which is generated by RLS algorithm and gradient method and combining this control method together with PID controller, this method has been used for controlling dead time industrial objects. It can be used to solve the problem of bad robustness and the prerequisite condition that precise mathematical models must be known in advance for the traditional PID control method. Simulation results indicate that the system robustness and tracking performance are superior to those of the traditional PID control method.