摘要
采用流体力学软件Fluent对不同结构的旋风分离器气固流场进行了数值模拟,并基于BP神经网络建立了旋风分离器的分离效率模型。对模型进行验证后表明,BP神经网络具有逼近复杂非线性函数的能力,能够快速估算出旋风分离器分离效率,并且预测的分离效率的误差低于5%,能够完全满足工程实际要求。
This paper uses the fluid dynamics software Fluent to do the numerical simulations of cyclone separators with various geometries and establishes the model of its separation efficiency based on BP neural network.The results show that the BP neural network can quickly estimate its separation efficiency and the error of the estimated separation efficiency is below 5%.It fully meets the engineering requirements.
作者
胡江玮
陆金桂
HU Jiangwei;LU Jingui(College of Mechanical and Power Engineering,Nanjing University of Technology,Nanjing 211816,China)
出处
《机械制造与自动化》
2018年第5期145-148,共4页
Machine Building & Automation
关键词
旋风分离器
数值模拟
分离效率
神经网络
cyclone separator
numerical simulation
separation efficiency
neural network
