循环流化床锅炉床温控制神经网络动态建模  

Neural Network Dynamic Modeling for Bed Temperature Control of Circulating Fluidized Bed Boiler

作　　者：康支霞[1] 张宪[2] 马永光[1] 王兵树[1] 

机构地区：[1]华北电力大学控制科学与工程学院,河北保定071003 [2]华北电力大学电气工程学院,河北保定071003

出　　处：《锅炉技术》2006年第B04期32-35,共4页Boiler Technology

摘　　要：针对循环流化床锅炉燃烧过程非常复杂,难以建立精确的数学模型,提出基于神经网络的方法对床温控制系统进行建模,并对标准的BP网络进行了改进,引入系统动态性,较好地解决了床温调节的滞后性。根据所提的建模方法对某电厂已投产的一台循环流化床锅炉实际建模。计算结果表明,该模型对床温具有较好的预测能力,能够反映一次风、给煤量等操作量变化时循环流化床锅炉床温的动态特性,说明了该建模方法的可行性,对床温控制系统的研究有一定的实际意义和应用价值。Circulating Fluidized Bed （CFB） is one of the complex nonlinear systems. In the absence of conventional means to derive a reliable model, we devise a model of the CFB using Neural Networks, which have the ability to characterize such complex systems through their nondinear mapping.The process of dynamic modeling for bed temperature system of CFB boiler is displayed.The results shows that the performance of this model is available when predicting the bed temperature of the CFB,and the proposed new strategy is feasible and effective.

关 键 词：循环流化床 床温 神经网络 动态建模 

分 类 号：TP291[自动化与计算机技术—检测技术与自动化装置]