改进Smith控制与RBF单神经元PID的换热器控制系统

为了高效控制工质出口温度,维持换热器稳定运行,针对Smith预估控制算法及径向基函数(RBF)神经网络辨识单神经元比例-积分-微分(PID)控制算法特点,提出了Smith控制算法和RBF神经网络辨识单神经元PID相结合的控制策略,对Smith控制算法在结构上进行了改进,以提高RBF神经网络辨识单神经元PID控制的抗干扰能力,减少Smith控制算法对模型的依赖程度.仿真分析表明:应用于换热器工质出口温度控制系统,改进算法控制性能显著优于其它控制方法,抗干扰能力得到了大幅提高.

Heat exchanger control system based on improved Smith control and RBF single neuron PID

In order to control working fluid outlet temperature efficiently and maintain the stable operation of the heat exchanger,aiming at characteristics of Smith predicted control algorithm and radial basis function(RBF)neural network of single neuron PID control algorithm,control strategy combined Smith control algorithm and RBF neural network single neuron PID is proposed.Smith predicted control algorithm is improved in the structure to reduce its dependence on the model.Meanwhile,the anti-interference ability of RBF neural network PID is increased.The simulation results show that the proposed algorithm can make the control performance and the antiinterference ability significantly better than others when it is applied to temperature control system of heat exchanger.