基于遗传算法和神经网络的C/C复合材料等温CVI工艺参数优化模型
详细信息    查看全文 | 推荐本文 |
  • 英文篇名:Optimization model for isothermal CVI process parameters for C/C composites based on genetic algorithm and neural network
  • 作者:李妙玲 ; 仝军锋 ; 赵红霞
  • 英文作者:LI Miaoling;TONG Junfeng;ZHAO Hongxia;School of Mechanical Engineering,Luoyang Institute of Science and Technology;College of Electrical Engineering and Automation,Luoyang Institute of Science and Technology;
  • 关键词:C/C复合材料 ; 化学气相渗透 ; BP神经网络 ; 遗传算法 ; 参数优化
  • 英文关键词:C/C composites;;chemical vapor infiltration;;BP neural network;;genetic algorithm;;parameter optimization
  • 中文刊名:FUHE
  • 英文刊名:Acta Materiae Compositae Sinica
  • 机构:洛阳理工学院机械工程学院;洛阳理工学院电气工程与自动化学院;
  • 出版日期:2016-04-14 14:12
  • 出版单位:复合材料学报
  • 年:2016
  • 期:v.33
  • 基金:国家自然科学基金(51472203);; 河南省科技攻关计划(132102210136)
  • 语种:中文;
  • 页:FUHE201611033
  • 页数:8
  • CN:11
  • ISSN:11-1801/TB
  • 分类号:268-275
摘要
建立了基于遗传算法和误差反传(GA-BP)神经网络的化学气相渗透(CVI)工艺参数优化模型。以新型等温CVI工艺制备C/C复合材料时采集的实验数据作为模型评价样本,分析了主要可控影响因素(沉积温度、前驱气体分压与滞留时间等)对C/C复合材料制件密度及其密度均匀性的作用规律。在该模型指导下,样本的期望密度和实测密度最大误差不超过6.2%,密度差最大误差不超过8.2%。实验结果也证明了该模型具有较高的精度和良好的泛化能力,可以用于CVI工艺参数的优化。
        An optimization model of the process parameters during a chemical vapor infiltration(CVI)was established based on genetic algorithm and back propagation(GA-BP)neural network.The experimental data from the novel isothermal CVI process of carbon/carbon(C/C)composites were selected as the samples to evaluate the model.The effect of the main controllable factors,such as infiltration temperature,part pressure of precursor gas and resident time etc,on the density and uniformity of C/C composites were analyzed.Under the guidance of the model,the maximum errors between the desired densities and the tested densities of the experiment samples are not larger than 6.2% and those between their density differences were not larger than 8.2%.The results show that the established optimization model has high precision and good generalization.It can be efficiently applied for optimizing CVI process parameters.
引文
[1]NIE J J,XU Y D,ZHANG L T,et al.Microstructure and tensile behavior of multiply needled C/SiC composite fabricated by chemical vapor infiltration[J].Journal of Materials Processing Technology,2009,209(1):572-576.
    [2]张丹,黄清波,李爱军,等.碳/碳复合材料热解碳基体的织构界面形成机制Monte Carlo模拟[J].复合材料学报,2014,31(4):859-865.ZHANG D,HUANG Q B,LI A J,et al.Monte Carlo simulations of texture interface formation within pyrocarbon matrix of carbon/carbon composites[J].Acta Materiae Compositae Sinica,2014,31(4):859-865(in Chinese).
    [3]边国军,齐乐华,宋永善,等.基于数值模拟的热梯度CVI制备C/C复合材料致密化行为[J].复合材料学报,2011,28(4):29-33.BIAN G J,QI L H,SONG Y S,et al.Densification process for thermal gradient CVI fabricating C/C composites based on numerical simulation[J].2011,28(4):29-33(in Chinese).
    [4]LI A J,NORINAGA K,ZHANG W G,et al.Modeling and simulation of materials synthesis:Chemical vapor deposition and infiltration of pyrolytic carbon[J].Composites Science and Technology,2008,68(5):1097-1104
    [5]郭春付.C/C复合材料CVI过程模拟仿真[D].武汉:华中科技大学,2011.GUO C F.Numerical simulation of chemical vapor infiltration process of C/C composites[D].Wuhan:Huazhong University of Science&Technology,2011(in Chinese).
    [6]王建武,李克智,张守阳,等.ICVI工艺致密化C/C复合材料的数值模拟[J].固体火箭技术,2014,37(5):711-718.WANG J W,LI K Z,ZHANG S Y,et al.Numerical simulation of densification of caebon/carbon composites by ICVI process[J].Journal of Solid Rocket Technology,2014,37(5):711-718(in Chinese).
    [7]王春红,赵玲,白肃跃,等.改进Back Propagation神经网络预测麻纤维/UP复合材料的界面性能[J].复合材料学报,2015,32(6):1696-1702.WANG C H,ZHAO L,BAI S Y,et al.Prediction of bast fiber/UP composites interfacial property by improved Back Propagation neural network[J].Acta Materiae Compositae Sinica,2015,32(6):1696-1702(in Chinese).
    [8]顾正彬,李贺军,李克智,等.C/C复合材料等温CVI工艺模糊神经网络建模[J].稀有金属材料与工程,2004,33(10):1037-1040.GU Z B,LI H J,LI K Z,et al.Modeling of isothermal CVI process of C/C composites by fuzzy neural network[J].Rare Metal Materials and Engineering,2004,33(10):1037-1040(in Chinese).
    [9]朱大奇,史慧.人工神经网络原理及应用[M].北京:科学出版社,2006:33-53.ZHU D Q,SHI H.Principle and applications of artificial neural networks[M].Beijing:Science Press,2006:33-53(in Chinese).
    [10]玄光南,程润伟.遗传算法与工程优化[M].北京:清华大学出版社,2004:2-100.XUAN G N,CHENG R W.Genetic algorithm and engineering optimization[M].Beijing:Tsinghua University Press,2004:2-100(in Chinese).
    [11]徐国忠,李贺军,白瑞成,等.新技术制备C/C复合材料及特性研究[J].无机材料学报,2006,21(6):1385-1389.XU G Z,LI H J,BAI R C,et al.The investigation of carbon/carbon composites preparation by novel technology and its characteristic[J].Journal of Inorganic Materials,2006,21(6):1385-1389(in Chinese).
    [12]XU G Z,LI H J,BAI R C,et al.Influence of the matrix texture on the fracture behavior of 2Dcarbon/carbon composites[J].Materials Science and Engineering:A,2008,478(1-2):319-323.
    [13]刘志成,张守阳,李贺军,等.正丙醇ICVI制备C/C复合材料的组织结构及力学性能[J].无机材料学报,2011,26(2):191-196.LIU Z C,ZHANG S Y,LI H J,et al.Microstructures and mechanical behavior of C/C composites prepared by ICVI using n-propanol as precusor[J].Journal of Inorganic Materials,2011,26(2):191-196(in Chinese).
    [14]杨静,张守阳,李贺军,等.CVI沉积炭纤维束的组织结构[J].固体火箭技术,2012,35(2):258-261.YANG J,ZHANG S Y,LI H J,et al,.Texture structure of carbon fiber bundle by CVI[J].Journal of Solid Rocket Technology,2012,35(2):258-261(in Chinese).
    [15]拓亚亚,张守阳,李贺军,等.温度对乙烯热解制备炭/炭复合材料织构的影响[J].固体火箭技术,2012,35(4):528-531.TUO Y Y,ZHANG S Y,LI H J,et al.The influence of temperature on the texture of carbon/carbon composites infiltrated by ethylene pyrolysis[J].Journal of Solid Rocket Technology,2012,35(4):528-531(in Chinese).
    [16]LI W,LI H J,WANG J,et al.Preparation and mechanical properties of carbon/carbon composites with high textured pyrolytic carbon matrix[J].Transactions of Nonferrous Metals Society of China,2013,23(7):2129-2134.