论文部分内容阅读
自行设计并搭建中心提升管内循环流化床冷态试验台,就提升管风速、鼓泡床风速、鼓泡床静床高、床料平均粒径几方面因素对颗粒循环流率的影响进行系统的试验研究。试验结果表明:对于给定的床料,颗粒循环流率随两床风速的增大而增大;固定两床风速,颗粒循环流率随鼓泡床静床高的增大而增大,随物料平均粒径的增大而减小。利用Matlab神经网络工具箱,建立3层BP神经网络颗粒循环流率预测模型。预测结果表明:在隐含层神经元数量为6时,误诊率最小,预测相对误差在±9%以内,网络性能最优,能较好地预测颗粒循环流率。
The design and construction of a central cold-bed test bed for circulating fluidized bed in the riser was designed and carried out systematically on the influence of riser velocity, bubbling bed velocity, bed height of bubbling bed and average particle size of bed material on the circulation rate of particles Experimental study. The experimental results show that for a given bed material, the circulating rate of particles increases with the increase of the velocity of the two beds. With the two fixed bed velocity and the circulation rate of the particles increasing with the increase of the height of the bubble bed, Material average particle size increases and decreases. Using Matlab neural network toolbox, a 3-layer BP neural network particle circulation flow rate prediction model was established. The results show that the number of hidden layer neurons is the lowest, the misdiagnosis rate is the smallest, the relative error is within ± 9% and the network performance is the best, which can predict the particle circulation rate better.