基于BP神经网络的粮食颗粒群流量预测

基金项目:

河南省科技攻关项目(102102210134)资助

The Flow Prediction of Grain Particle Group Based on BP Neural Network

1.
Mechanical and Electrical Engineering Institute, Zhengzhou University of Light Industry, Zhengzhou 450002;
2.
Zhengzhou Dagong Grain Machinery Co.,LTD, Zhengzhou 450000

摘要: 针对粮食气力输送的固相流量与其影响因素之间存在复杂的非线性关系使输出产量难以实现精确控制的问题,建立了基于BP(Back Propagation)神经网络的流量预测模型。该模型能够根据管道中压损和风速的变化来预测气力输送系统的固相颗粒流量,通过MATLAB软件进行仿真,并与实验数据相比对。结果表明:该预测方案简便易行、预测准确。
- 气力输送 /
- 颗粒群 /
- BP神经网络 /
- 流量预测
Abstract: The flow prediction model based on BP(Back Propagation) neural network was put forward to solute the problem that a complex non-linear relationship exists between solid-phase flow and influencing factors in grain pneumatic conveying pipes,which is difficult to control output production accurately.The model can effectively predict solid-phase flow of system according to the change of pressure loss along pipeline and conveying wind speed,and was simulated by MATLAB software,moreover,was compared with the experimental data.The results show the prediction scheme is convenient,feasible and accurate,which have important instruction significance for detection and control in pneumatic transport system.
- back propagation /
- flow of solids /
- pneumatic propulsion /
- closed loop control systems

[1]	董礼，邓小文. 风力机湍流滤波器设计与等效风速的产生[J].机械科学与技术，2012，31(6):933～937
[2]	许传龙，赵延军. 基于人工神经网络的固相质量流量软测量研究[J]. 计量学报，2006，27(3):246～249
[3]	张英健. 基于 Elman 神经网络的浓相输送模糊控制[J]. 系统微计算机信息，2007，23(9):68～70
[4]	杭柏林，姜丰辉. 气力输送系统两级计算机管理控制方案的设计与实现[J]. 橡胶工业杂志，2007，54(2):107～110
[5]	任建新，谭剑. 基于刚度模型分析流体压力对直管科氏质量流量计的影响[J]. 机械科学与技术，2012，31(1):67～70
[6]	Gu· · ner M. Pneumatic conveying characteristics of some agriculturalseeds[J]. Journal of Food Engineering，2006，80:904～913
[7]	杨伦，谢一华. 气力输送工程[M]. 北京:机械工程出版社，2006
[8]	Lu LU，Liu F G. Neural-network adaptive controller for nonlinearsystems and its application in pneumatic servo systems[J]. Con-trol Theory Application，2008，6(1):97～103
[9]	李国勇. 智能控制及其 MATLAB 实现[M]. 北京:电子工业出版社，2006