基于模型的RBF循环流化床锅炉床温控制  

RBF Control of Circulating Fluidized Bed Boiler Temperature Based on Model

作　　者：蒋晓肖[1,2] 樊建[1,2] 陈广博[1] 

机构地区：[1]上海大学机电工程与自动化学院,上海200072 [2]南京陆军指挥学院作战实验中心,江苏南京210045

出　　处：《控制工程》2009年第S1期114-116,共3页Control Engineering of China

基　　金：上海高校选拔培养优秀青年教师科研专项基金;上海大学创新基金

摘　　要：针对循环流化床锅炉(Circulating Fluidized Bed Boiler,CFBB)床温控制对象,提出一种基于模糊神经模型的RBF神经网络控制算法,算法主要由模糊神经模型、RBF控制器、控制对象三部分构成。此算法首先利用采集到的输入输出数据对建立给煤量与床温的模糊神经模型,同时在模糊神经模型的基础上引入RBF控制器,并根据所建模型利用梯度下降法在线调节控制器中高斯基函数的中心值、宽度及隐含层到输出层的权值。通过将此控制算法应用于循环流化床锅炉床温的控制中,并与传统PID控制的Matlab仿真结果比较表明,提出的基于模糊神经模型的RBF控制算法动态响应时间和到达稳态时间比传统PID短,并且其跟踪性能较好。For the control object of Circulating Fluidized Bed Boiler(CFBB) Temperature,a RBF neural network control algorithm based on fuzzy neural model is proposed.The algorithm is constituted of three parts that are fuzzy neural model,RBF controller and control object.Firstly the fuzzy neural model is constructed through the collected input-output data,and at the same time import the RBF controller.So in this algorithm,the RBF neural network controller's center value,width and weight value from hidden layer to output layer are modified on-line by the model. At last this algorithm is applied to the temperature control of circulating fluidized bed boiler.In comparison with PID control,the system has short response time,short steady time and well tracking performance.

关 键 词：床温 模糊神经模型 RBF 控制 

分 类 号：TK229.66[动力工程及工程热物理—动力机械及工程]