论文部分内容阅读
经过分析某超临界600MW直流锅炉高温过热器动态特性,过热器动态特性随机组的运行工况变化而变化,可以认为用蒸汽流量就能近似表示运行工况。在此基础上,提出了串级过热汽温智能控制系统。该智能控制系统中的副调节器仍然采用比例调节器;设计该主调节器时,把整个副回路和主对象看成广义被控对象,主调节器是一个自整定PID控制器,需要用到被控对象的Jacobian信息。随后构造了一个径向基函数(RBF)神经网络对被控对象进行辨识,从而求出了被控对象的Jacobian信息。最后将文中提出的智能控制系统用到了某超临界600MW直流锅炉的过热汽温控制中,仿真结果表明,用这种方法建立的过热汽温控制系统在机组运行工况发生变化时,具有较好的控制品质和较强的自适应能力。
After analyzing the dynamic characteristics of a supercritical 600MW supercritical once-through boiler superheater and the dynamic characteristics of the superheater varied with the operating conditions of the superheater, it can be considered that the steam flow can approximate the operating conditions. On this basis, proposed a series of superheated steam temperature intelligent control system. The adjuster in the intelligent control system still uses a proportional regulator. When designing the main regulator, the entire secondary loop and the main object are regarded as a generalized controlled object. The main controller is a self-tuning PID controller and needs to be used Jacobian information of the accused. Then, a radial basis function (RBF) neural network is constructed to identify the controlled object, so as to obtain the Jacobian information of the controlled object. Finally, the intelligent control system proposed in this paper is used in the superheated steam temperature control of a supercritical 600 MW once-through boiler. The simulation results show that the superheated steam temperature control system established by this method has a better performance when the unit operating conditions change The control of quality and strong self-adaptive ability.