摘要
在水平T型分支管道中,用压缩空气作为输送气体,对平均粒径为0.25 mm和0.5 mm的砂石进行气力输送试验。通过试验和GRNN神经网络对输送表观气速和两分支管路流量控制阀开度发生变化时,各分支管路中的阻力特性进行了研究。结果表明:随着表观气速的逐渐减小和两分支管路流量控制阀开度差值的增加,各分支管路中的阻力特性相应地发生了变化。通过试验值和GRNN网络模拟值的对比,发现试验值和模拟值间相互吻合得较好,说明采用GRNN网络来模拟两分支管路中各自的阻力特性适应性较好。
The experiment for pneumatic conveying sands in average particle diameter of 0.25 mm and 0.5 mm was carried out by using compressed air in horizontal tee branch pipe. The respective resistance properties for branch pipe were investigated through experiments and GRNN neural network when both conveying velocity and the flow valve opening of branch pipe were changed. It shows that the respective resistance properties of branch pipe have some obvious changes with the decrease of apparent air velocity and the increase of the differential value for flow valve opening of branch pipe. Through the comparison between the neural networks simulated results and the experimental data, it shows that the simulated value agrees well with the experimental data. This illuminates that the GRNN network has a better adjustability to the simulation and prediction of the resistance properties for horizontal branch pipe.
出处
《化学工程》
EI
CAS
CSCD
北大核心
2008年第11期29-32,共4页
Chemical Engineering(China)
关键词
气力输送
分支管路
阻力特性
神经网络
pneumatic conveying
branch pipe
resistance properties
neural network