[1]乔英杰,尹海莲,梁军.基于人工神经网络的碳/陶瓷复合材料性能预测[J].东南大学学报(自然科学版),2005,35(3):400-403.[doi:10.3969/j.issn.1001-0505.2005.03.017]
 Qiao Yingjie,Yin Hailian,Liang Jun.Property prediction of carbon-ceramics composite material based on artificial neutral network[J].Journal of Southeast University (Natural Science Edition),2005,35(3):400-403.[doi:10.3969/j.issn.1001-0505.2005.03.017]
点击复制

基于人工神经网络的碳/陶瓷复合材料性能预测()
分享到:

《东南大学学报(自然科学版)》[ISSN:1001-0505/CN:32-1178/N]

卷:
35
期数:
2005年第3期
页码:
400-403
栏目:
材料科学与工程
出版日期:
2005-05-20

文章信息/Info

Title:
Property prediction of carbon-ceramics composite material based on artificial neutral network
作者:
乔英杰12 尹海莲2 梁军2
1 哈尔滨工程大学机电学院, 哈尔滨 150001; 2 哈尔滨工业大学复合材料研究所, 哈尔滨 150001
Author(s):
Qiao Yingjie12 Yin Hailian2 Liang Jun2
1 School of Mechanical and Electrical Engineering, Harbin Engineering University, Harbin 150001, China
2 Institute of Composite Materials, Harbin Institute of Technology, Harbin 150001, China
关键词:
人工神经网络 碳/陶瓷复合材料 石墨化 材料性能
Keywords:
artificial neutral network carbon-ceramics composite material graphitization material properties
分类号:
TB302
DOI:
10.3969/j.issn.1001-0505.2005.03.017
摘要:
利用人工神经网络的BP算法,建立了碳/陶瓷复合材料性能与多组分掺杂含量之间的预测模型.模型由输入层、隐含层和输出层3层神经元组成,用以模拟人脑的结构.以掺杂物的质量分数为输入参数,经石墨化后测得的复合材料的电阻率和抗折强度为输出参数.选取了30组实验数据作为学习样本,任意的7组数据作为“未知样品”对网络进行验证.结果表明,实验值和预测值相比电阻率的最大误差不超过8%,抗折强度的最大误差不超过12%.所建的网络可为碳/陶瓷复合材料设计提供理论指导.
Abstract:
Models were established to predict the relation between components and properties of carbon-ceramics composite material based on the back propagation(BP)algorithm of the artificial neural network(ANN). The prediction models are composed of three neuron layers, i.e. input layer,hidden layer and output layer, to simulate the real structure of human brain. The volume percentages of the components are regarded as input parameters and the resistivity and antiflex strength of the composite material after graphitizing are regarded as output parameters. The selected thirty samples are considered as the data of the study and the random seven samples are predicted and assessed in the artificial neutral network of BP. On condition that the training data are precise enough,the models provide good results for the relation between components and properties of carbon-ceramics composite material. The electric resistance and benging strength error are respectively within 8% and 12% compared with experimental data. Therefore the models proposed are helpful to the design of carbon-ceramics composite material systems.

参考文献/References:

[1] Ogawa Ichitaro,Kobayashi Kazuo,Nishikawa Susumu.Oxidation resistance of carbon-ceramics composite materials sintered from ground powder mixtures of raw coke and cermics [J].Journal of Materials Science,1988,23(4):1363-1367.
[2] 李杰.碳/陶复合材料浅述 [J].碳素,1990,9(4):12.
  Li Qie.Simple introduction of carbon/ceramic composites [J]. Carbon,1990,9(4):12.(in Chinese)
[3] 董利民.SiC 晶须/碳陶瓷复合材料研究 [D].北京:清华大学核能技术设计研究院,1991.
[4] Malinov S,Sha W,Mckeown J J.Modelling the correlation between processing parameters and properties in titanium alloys using artificial neural network [J]. Computational Materials Science,2001,21(3):375-394.
[5] Qi Lehua,Hou Junjie,Cui Peiling,et al.Research on prediction of the processing parameters of liquid extrusion by BP network [J]. Journal of Materials Processing Technology,1999,95(1-3):232-237.
[6] Manabe K,Yang M,Yoshihara S.Artificial intelligence identificant of process parameters and adaptive control system for deep-drawing process [J]. Journal of Materials Processing Technology,1998,80(11):421-426.
[7] Korcak P,Dyja H.Using neural network models for predicting mechanical properties after hot plate rolling process [J].Journal of Materials Processing Technology,1998,27(4):481-486.
[8] 胡守仁.神经网络导论 [M].长沙:国防科技大学出版社,1992.22-89.
[9] 丛爽.面向MATLAB工具箱的神经网络理论与应用 [M].合肥:中国科学技术大学出版社,1998.50-80.
[10] Taylor K K, Darsey J A.Prediction of the electronic properties of polymers using artificial neural networks [J]. Polymer Preprints, 2000,41(1):331-332.

相似文献/References:

[1]何永勇,钟秉林,黄仁.基于人工神经网络的旋转机械多故障同时性诊断策略[J].东南大学学报(自然科学版),1996,26(5):39.[doi:10.3969/j.issn.1001-0505.1996.05.008]
 He Yongyong,Zhong Binglin,Huang Ren.Multiple Fault Simultaneous Diagnosis Based on Artificial Neural Networks for Rotating Machine[J].Journal of Southeast University (Natural Science Edition),1996,26(3):39.[doi:10.3969/j.issn.1001-0505.1996.05.008]

备注/Memo

备注/Memo:
基金项目: 国家自然科学基金资助项目(10102005)、哈尔滨工业大学校基金资助项目(HIT.2002.01).
作者简介: 乔英杰(1965—),男,博士,教授,qiaoyj1930@163.com.
更新日期/Last Update: 2005-05-20