CAJ | 학술논문

电加热过程具有强非线性和时变特性，参数固定的常规PID很难对其进行精确的控制。将常规PID控制和径向基函数（RBF）神经网络结合，提出了基于RBF神经网络的PID控制。该方法是通过神经网络的自学习能力在线调整PID控制的参数。通过Matlab与组态软件“组态王”的动态数据交换，在Matlab上编程实现了基于RBF神经网络的PID控制算法。将该控制算法应用于小型电加热反应温度控制装置，结果显示这种算法取得了比常规PID更好的控制效果。
전가열과정구유강비선성화시변특성，삼수고정적상규PID흔난대기진행정학적공제。장상규PID공제화경향기함수（RBF）신경망락결합，제출료기우RBF신경망락적PID공제。해방법시통과신경망락적자학습능력재선조정PID공제적삼수。통과Matlab여조태연건“조태왕”적동태수거교환，재Matlab상편정실현료기우RBF신경망락적PID공제산법。장해공제산법응용우소형전가열반응온도공제장치，결과현시저충산법취득료비상규PID경호적공제효과。
Electric-heating process owns strong nonlinearity and time-varying properties. It is difficult to control the temperature accurately using conventional PID controller with fixed PID parameters. Combined with conventional PID controller and radial basis function (RBF) neural network, a PID controller based on RBF neural network is proposed. The parameters of PID controller are tuned on-line using self-learning ability of RBF neural network. This PID control algorithm is successfully implemented in Matlab software which is integrated with configuration software KingView through their Dynamic Data Exchange (DDE) channel. The PID controller is used in a small electric-heating reactor. The result shows that the RBF neural network PID controller has much better control performance than the traditional PID controller.