基于GA-BP对锥形布风板双流化床颗粒循环流率的预测研究  

GA-BP algorithm based prediction of solids circulation rate in a dual fluidized bed with conical gas distributor

作　　者：陈鸿伟[1] 吴晶[1] 何骏鹏 李岩[1] 

机构地区：[1]华北电力大学电站设备状态监测与控制教育部重点实验室,河北保定071003

出　　处：《热力发电》2015年第2期90-95,共6页Thermal Power Generation

基　　金：国家自然科学基金项目(50876030);高校博士点基金项目(20090036110008)

摘　　要：为了合理地控制锥形布风板双流化床的颗粒循环流率,在自行搭建的冷态实验台上,研究了一些参数对颗粒循环流率的影响。结果显示,颗粒循环流率分别随着气化室风速、提升管风速、床料重量的增加而增加,随着颗粒粒径的增加而减小,随着锥形布风板角度的增加而增加。建立了GA-BP神经网络模型,利用预测值与实际值的最大相对误差和均方差来评价模型优劣,通过比较,找到了模型的最优参数设置,其预测结果的最大相对误差仅为0.108 7,均方差为0.002 0。In order to control solids circulation rate in dual fluidized bed with conical gas distributor properly,a cold test bench was built up to investigate the influence of several parameters on solids circulation rate.The results show that,the solids circulation rate increased with the gas velocities（to the gasification chamber or the riser）and bed material weight,while decreases with the increasing particle size.It grew with the angle of the conical gas distributor.The GA-BP neural network model was established to predict the circulation rate,and the maximum relative error and mean square error were defined to evaluate the models.By comparison,the optimal parameters of the model were found.The maximum relative error is only 0.108 7and the mean square error is 0.002.

关 键 词：颗粒循环流率 双流化床 锥形布风板 GA-BP 预测 

分 类 号：TK229.66[动力工程及工程热物理—动力机械及工程]