Research on Fogdrop Diameter based on Neural Network
Because of the importance of dust abatement by sprayer, this paper studies the characteristic of fogdrop generated by one kind of nozzle on basis of Back Propagation (BP) Neural Network, using Marvin-3000 type laser granularity instrument in lab. It is pointed that the maximum and minimum errors of widely used BP Neural Network are 2.18％ and 0.61％, when we compute the fogdrop diameter computing repeatedly. In more general case, if the nozzle diameter change, the maximum and minimum errors using BP Neural Network are 1.92％ and 0.34％ by comparing with others work, while the errors are 2.13％ and 1.50％ when pressure change. The experimental results show that BP neural network is an effective tool to predict the variation of the non linear fogdrop diameter. Furthermore, it is potential to be used in other kinds of fogdrop and real industry application.
neural network dust abatement spraying fogdrop diameter forecasting and computing
LI-Rui KOU-Ziming LI-Rui KOU-Ziming
Department of Mechanical Engineering Taiyuan University of Technology, TUT Taiyuan, China Mine Fluid Control Engineering Research Center Shanxi Province Taiyuan, China
国际会议
张家界
英文
285-288
2009-04-11（万方平台首次上网日期，不代表论文的发表时间）