用PID梯度算法训练基于神经网络的广义非线性PID控制器(英文)

PID Gradient Algorithm for Neural Network Based Generalised Nonlinear PID Controller

将梯度优化过程看作反馈控制系统 ,从而提出了一种带动量项的PID梯度算法 (PIDGDM ) .进一步讨论了该算法的收敛特性 .提出了一种非线性PID控制器以对付一些非线性控制问题 .神经网络被用于实现该非线性PID控制器 .PIDGDM算法被用于训练所提出的神经网络非线性PID控制器 .最后 ,给出了有关方法应用于两个化工过程的仿真研究结果 .

An algorithm of PID gradient descent with momentum term (PIDGDM) is proposed. In this algorithm, the procedure of gradient optimization is considered as a feedback control system. Then, the convergent characteristic of the algorithm is presented. In this paper, a nonlinear PID controller is also proposed to handle some nonlinear control problems. The nonlinear PID control strategy is realized using neural networks. The PIDGDM algorithm is applied to the training of the neural nonlinear PID controller. Finally, simulation study of applying the neural nonlinear PID control strategy to a continuous-stirred-tank-reactor (CSTR) and a van de Vusse reactor is illustrated.