热工过程时滞对象的神经网络内模控制

Neural Networks Internal Model Control for Object with Time Delay of Thermal Process

针对火电厂热工过程的时滞对象,提出采用基于神经网络的内模控制方法,即用神经网络对复杂系统的辨识能力来实现内模控制中被控对象的正模型及内模控制器。仿真研究表明,文中所采用的控制方案比常规PID控制表现出更好的控制品质,在实际应用中具有一定的实用价值。

As to the object with time delay of thermal process in power plant, an internal model control based on neural networks is presented in this paper. It recurs to the identification ability for complex object of the Neural Networks to identify the model and inverse model controller of the object. Simulation results show that this method has perfect control performance compared with PID controller, which shows it is preferable to the practical application.