基于神经网络的热力站换热器系统的预测控制

Prediction control simulation of heat substation system based on neural networks

在利用实验法确定热力站换热器系统动态特性的基础上,提出利用神经网络预测控制器对热力站换热器系统进行控制,并进行阶跃扰动的控制仿真。结果表明,神经网络预测控制的效果要优于手动调节和传统的PID调节,适合时滞对象的动态调节。

The dynamic characters of the heat substation heat exchanger was achieved through the step-response experiment,and step-response control simulations of both the PID controller and NN prediction controller were presented.The results shows that the NN prediction controller has great superiority than PID controller in the time-lag system.