论文部分内容阅读
针对采用常规PID串级控制方法控制火电厂过热汽温系统难以获得满意的控制效果的问题,将模糊控制和神经网络相结合,详细介绍了模糊神经网络控制器的设计过程,利用神经网络实现模糊推理,并对隶属函数进行调整,从而使其具有自适应和学习能力。将其应用于过热汽温控制系统中,仿真研究表明该方法能较好地适应对象特性的变化,基本上可以消除振荡,具有超调量小,鲁棒性强等特点,且控制系统的性能比常规串级控制系统有较大的提高。
Aiming at the problem of using conventional PID cascade control method to control the superheated steam temperature in thermal power plant, it is difficult to obtain the satisfactory control effect. The fuzzy control and neural network are combined to describe the design process of the fuzzy neural network controller in detail. The neural network is used to realize the fuzzy Reasoning, and membership functions to adjust, so that it has the ability to adapt and learn. It is applied to superheated steam temperature control system. The simulation results show that this method can better adapt to the change of object characteristics, basically eliminate the oscillation, have the advantages of small overshoot and strong robustness, and control the performance of the system Than the conventional cascade control system has been greatly improved.