用 RBF 型人工神经网络研究了碳/陶瓷复合材料的化学成分对其硬度的影响。首先设计了 RBF 型神经网络模型，用“舍一法”进行了训练，使模型具有满意的预测性能。随后分析了化学组分对硬度的影响，包括单因素影响和双因素耦合影响。结果表明：材料的两种组分同时变化时，对硬度的影响更加复杂，呈现典型的非线性特征。
RBF artificial neural network was developed to study the effects of chemical compositions on the hardness of carbon/ceramic composite material.The RBF neural network model was designed and trained by the“leave-one-out method”.After being trained,the model had satisfactory prediction performance.Then,the ANN model was used to analyze the effects of chemical compositions on the hardness of carbon/ceramic,including single ones of single factor and coupling ones of dual factors.The results showed that the coupling effects of dual factors on the hardness are more complicated,presenting typical non-linear characteristics.
参考文献
| [1] | Ogawa Ichitaro;Kobayashi Kazuo;Nishikawa Susumu .Oxi-dation resistance of carbon-ceramics composite materials sin-tered from ground powder mixtures of raw coke and cera-mics[J].Journal of Materials Science,1988,23(4):1363. |
| [2] | 李杰.碳/陶复合材料浅析[J].碳素,1990(04):12-21. |
| [3] | 丁燕鸿 .SiC晶须增韧Ti(C,N)基金属陶瓷复合材料的研究[D].中南大学,2006. |
| [4] | 龙萍,许立坤,李庆芬,唐益,辛永磊.均匀设计RulrSnLa/Ti氧化物涂层的回归与灰色关联分析[J].化学学报,2009(12):1325-1330. |
| [5] | 汤爱涛;胡红军;杨明波.计算机在材料工程中的应用[M].重庆:重庆大学出版社,2008 |
| [6] | 曾令可.计算机在材料工程中的应用[M].武汉:武汉理工大学出版社,2008 |
| [7] | Hecht-Nielesn R.Neurocomputing[M].Don Mills,Ontario:Addison-Wesley Publishing,1991:59. |
| [8] | 沙全友,范喆,蒋志强,孙建华.人工神经网络在材料性能预测中的应用[J].郑州航空工业管理学院学报（管理科学版）,2004(04):43-44. |
| [9] | 徐文峰,廖晓玲,刘希东.人工神经网络在材料性能研究中的应用[J].材料导报,2006(z2):237-240,257. |
| [10] | 博荟璇;赵红.MATLAB 神经网络应用设计[M].北京:机械工业出版社,2010 |
| [11] | 由伟,白秉哲,方鸿生.钢的连续冷却转变图的神经网络计算模型及预测软件设计[J].金属热处理,2004(07):17-20. |
| [12] | 徐雪霞,由伟,白秉哲,方鸿生.人工神经网络预测Si对空冷贝氏体钢CCT图的影响[J].材料热处理学报,2009(04):198-202. |
| [13] | 尹海莲 .基于人工神经网络技术的复合材料性能预报[D].哈尔滨:哈尔滨工业大学,2004. |
| [14] | Narayan V;Abad R;Bhadeshia H K D H .Estimation of hot torsion stress strain curves in iron alloys using neural network analysis[J].ISIJ International,1999,39(10):999. |
| [15] | Sung-Sau So et al.Evolutionary optimization in quantitative structure-activity relationship:An application of genetic neural networks[J].J Medicinal Chem,1996,39(7):1524. |
| [16] | Cybenko G.Mathematics of control,signals and systems[M].New York:Springer International Press,1980:303. |
| [17] | Hornik K;Baldi P .Multilayer feedforward and networks are universial approximators[J].NEURAL NETWORKS,1989,2:359. |
| [18] | Chen T P;Chen H;Liu R W .Approximation capability in C(Rn)by multilayer feedforward networks and related prob-lems[J].IEEE Transactions on Neural Networks,1995,6(1):25. |
| [19] | Scarselli F;Tsoi A C .Universal approximation using feed-forward neural network:A survey of some existing me-thods,and some new results[J].NEURAL NETWORKS,1998,11(1):15. |
- 下载量()
- 访问量()
- 您的评分：
-
10%
-
20%
-
30%
-
40%
-
50%