基于BP神经网络的压力容器CFD温度场预测Prediction of CFD temperature in pressure vessel by applying BP neural network
杨磊磊,陆皓,余春,王学成,刘陈,孙乙轩
摘要(Abstract):
利用计算流体动力学软件FLUENT建立了烟气、容器、保温棉多层热流固耦合模型。模拟得到了大型压力容器热处理升温阶段温度场分布。结果表明,模拟结果与实验相吻合,相对误差在±1.2%以内。基于FLUENT计算结果,以富氧燃烧时火焰温度和容器不同层位置作为输入变量建立含15个隐含层的BP神经网络。采用经过训练的神经网络,预测容器不同层温度,得到的相对误差仅为0.34%,准确性高,省去了大量的FLUENT计算,提高了预测效率。
关键词(KeyWords): FLUENT;压力容器;神经网络;计算流体动力学;热处理
基金项目(Foundation): 国家科技重大专项(2012ZX04010-091);; 国家自然科学基金(51575347)
作者(Author): 杨磊磊,陆皓,余春,王学成,刘陈,孙乙轩
DOI: 10.13289/j.issn.1009-6264.2016.12.028
参考文献(References):
- [1]李友,杨成刚.球形储罐焊后热处理[J].金属热处理,2002,27(3):42-44.LI You,YANG Cheng-gang.Post weld heat treatment for spherical tanks[J].Heat Treatment of Metals,2002,27(3):42-44.
- [2]王志明.球形储罐内燃法整体热处理[J].化工设计,2002,12(3):19-21.WANG Zhi-ming.The overall heat treatment of spherical tank with internal combustion method[J].Chemical Engineering Design,2002,12(3):19-21.
- [3]Fu J R.Large tank overall heat treatment method:China,CN1178249A[P].1998-04-08.
- [4]Graa M,Duarte A,Coelho P J,et al.Numerical simulation of a reversed flow small-scale combustor[J].Fuel Processing Technology,2013,107(1):126-137.
- [5]álvarez L,Gharebaghi M,Jones J M,et al.CFD modeling of oxy-coal combustion:prediction of burnout,volatile and NO precursors release[J].Applied Energy,2013,104(1):653-665.
- [6]YapcH,Kayata爧N,Albayrak B,et al.Numerical calculation of local entropy generation in a methane-air burner[J].Energy Conversion and Management,2005,46(11):1885-1919.
- [7]Bouras F,Soudani A.Impact of the equivalence ratio and the mass flow rate on turbulent lean premixed prevaporized combustion[J].Energy Procedia,2011,6(1):251-260.
- [8]Danon B,Cho E S,De Jong W,et al.Numerical investigation of burner positioning effects in a multi-burner flameless combustion furnace[J].Applied Thermal Engineering,2011,31(17):3885-3896.
- [9]Saario A,Rebola A,Coelho P J,et al.Heavy fuel oil combustion in a cylindrical laboratory furnace:measurements and modeling[J].Fuel,2005,84(4):359-369.
- [10]Hao X,Gu J,Chen N,et al.3-D Numerical analysis on heating process of loads within vacuum heat treatment furnace[J].Applied Thermal Engineering,2008,28(14):1925-1931.
- [11]吉方.大型球罐内燃法焊后热处理工艺稳态数值模拟研究[D].太原:太原理工大学,2015.JI Fang.Steady numerical simulation research on post weld heat treatment of large spherical tank by internal combustion method[D].Taiyuan:Taiyuan University of Technology,2015.
- [12]杨夏炜,朱景川,何东,等.利用CFD模拟和ANN模型对A357铝合金大型复杂构件淬火槽内介质流场分布的优化设计[J].中国有色金属学报,2013,23(5):1442-1451.YANG Xia-wei,ZHU Jing-chuan,HE Dong,et al.Optimum design of flow distribution in quenching tank for heat treatment of A357 aluminum alloy large complicated thin-wall workpieces by CFD simulation and ANN approach[J].Transactions of Nonferrous Metals Society of China,2013,23(5):1442-1451.
- [13]周舸,张善庆,莫卫红,等.基于人工神经网络的DD6合金表面贫化层厚度预测[J].材料热处理学报,2015,36(12):252-257.ZHOU Ge,ZHANG Shan-qing,MO Wei-hong,et al.Application of artificial neural network for prediction of surface depletion layer in single crystal superalloy DD6[J].Transactions of Materials and Heat Treatment,2015,36(12):252-257.
- [14]左秀荣,陈蕴博,王淼辉,等.基于人工神经网络的P20钢热处理工艺[J].材料热处理学报,2010,31(4):61-66.ZUO Xiu-rong,CHEN Yun-bo,WANG Miao-hui,et al.Heat treatment process of P20 steel using artificial neural network[J].Transactions of Materials and Heat Treatment,2010,31(4):61-66.
- [15]Guo L,Li B,Zhang Z.Constitutive relationship model of TC21 alloy based on artificial neural network[J].Transactions of Nonferrous Metals Society of China,2013,23(6):1761-1765.
- [16]潘亮.富氧燃烧火焰特性及热工特性试验研究[D].长春:吉林大学,2007.PAN Liang.Experimental study on flame characteristic and thermal characteristic of oxygen-rich air combustion[D].Changchun:Jilin University,2007.
文章评论(Comment):
|
||||||||||||||||||
|
||||||||||||||||||