小型电加热反应器温度的RBF神经网络自整定PID控制  

Temperature Control of a Small Electric-heating Reactor Using RBF Neural Network Based on Auto-tuning PID Control Algorithm

作　　者：于蒙[1] 邹志云[1] 赵丹丹[1] 王志甄[1] 盖希杰[1] 

机构地区：[1]防化研究院,北京102205

出　　处：《石油化工自动化》2012年第6期31-35,共5页Automation in Petro-chemical Industry

摘　　要：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。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.

关 键 词：径向基神经网络PID电加热反应器组态王 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]