摘要
循环流化床(CFB)锅炉主蒸汽压力系统是一种大滞后系统,采用传统控制方法其效果并不理想。为此,将灰色预测及单神经元控制思想用于CFB锅炉主蒸汽压力控制系统,利用神经网络对系统的滞后时间进行辨识,并在此基础上采用AR拟合残差的变步长灰色预测方法对蒸汽压力系统的行为进行预测,同时结合单神经元控制器克服辨识误差、预测误差、系统干扰等不确定因素带来的影响,从而提高系统的自适应性。仿真结果表明,系统运行平稳,受不确定因素的影响较小,对CFB锅炉主蒸汽压力系统具有良好的控制效果。
Main vapor pressure systems of CFB boiler is a kind of time-delay system, it is unfavorable to control it with traditional controller, So, we use grey prediction and single neuron controlling maneuver in controlling main vapor pressure systems of CFB boiler. Neural network is proposed to indentify the delay time of such a system. Moreover, the advanced grey predicition algorithm in which error fitting with AR （p） modle is used to predict future behviors of main vapor pressure systems of CFB boiler, and at the same time, single neuron controller is used to overcome the effect of uncertain factors such as error in indentify and predicition, disturbance in systems and so on. In computer simulation, the systems exert stabily, the effect of uncertain factors is small, the system has perfect control effect to main vapor pressure systems of CFB boiler.
出处
《工业加热》
CAS
2005年第6期9-12,共4页
Industrial Heating
