期刊文献+

基于BP神经网络的敏感性分析模型在天然橡胶耐磨性分析中的应用 被引量:1

Application of sensitivity analysis model based on BP neural network in abrasion property analysis of natural rubber composites
下载PDF
导出
摘要 采用主成分分析法将天然橡胶复合材料的8种力学性能降维后作为BP神经网络的输入向量,耐磨性作为输出向量,得到训练优秀的BP神经网络。对输入向量进行敏感性分析,得出各主成分对耐磨性影响大小的顺序。对影响最大的主成分所包含的力学性能再一次进行敏感性分析,得到对天然橡胶耐磨性影响最大的力学性能。结果表明,BP神经网络的预测精度达到93.1%,说明BP神经网络适用于橡胶材料耐磨性的预测。 The dimensionality of 8 mechanical properties of natural rubber composites was reduced by principal component analysis, and then the components were used as the input vectors of BP neural network, while abrasion property as the output vector. After training,the BP neural network was established, and the sensitivity matrixes of the input vectors were calculated in order to search the mechani- cal properties which had most significant effect on abrasion property. The results showed that the prediction accuracy of the BP neural network was 93.1% ,indicating that the BP network was suitable for the abrasion prediction of NR composites. Sensitivity analysis indicated that modulus at 100% was the most important factor to influence the abrasion property of NR composites.
出处 《合成橡胶工业》 CAS CSCD 北大核心 2014年第1期14-19,共6页 China Synthetic Rubber Industry
基金 教育部新世纪优秀人才计划资助项目(NCET-10-0202)
关键词 天然橡胶 耐磨性 神经网络 敏感性分析 主成分分析 natural rubber abrasion neural network sensitivity analysis principal component analysis
  • 相关文献

参考文献10

  • 1Thavamani P,Bhowmick A K. Abrasion of vulcanizates of NR and SBR at high temperatures[J].{H}Plastics Rubber and Composites Processing and Applications,1993,(04):239-246.
  • 2Zhang S W,Yang Zhaochun. Energy theory of rubber abrasion by a line contact[J].{H}Tribology International,1997,(12):839-843.
  • 3王伟,罗仁,曾京.车轮型面磨耗预测模型及仿真分析[J].铁道车辆,2009,47(9):1-5. 被引量:12
  • 4周海滨.工程轮胎磨耗寿命的预测[J].世界橡胶工业,2004,31(6):36-40. 被引量:4
  • 5Im H J,Song B C,Park Y J. Classification of materials for explosives from prompt gamma spectra by using principal component analysis[J].{H}Applied Radiation and Isotopes,2009,(7/8):1458-1462.
  • 6Kadi H E1,Al-Assaf Y. Prediction of the fatigue life of unidirectional glass fiber/epoxy composite lamina using different neural network paradigms[J].{H}Computers & Structures,2002,(12):239-246.
  • 7陈燕.数据挖掘技术与应用[M]{H}北京:清华大学出版社,2011102-128.
  • 8Wang Bin,Ma Jianhua,Wu Youping. Application of artificial neural network in prediction of abrasion of rubber composites[J].{H}Materials and Design,2013.802-807.
  • 9Gevrey M,Dimopoulos I,Lek S. Two-way interaction of input variables in the sensitivity analysis of neural network models[A].2002.43-50.
  • 10赵野军,吕柏源,程源.基于人工神经网络的橡胶螺杆挤出机智能化设计[J].特种橡胶制品,2005,26(2):21-23. 被引量:4

二级参考文献9

  • 1李丽娟,吕柏源.橡胶冷喂料挤出过程的模糊综合评判[J].合成橡胶工业,1996,19(1):50-52. 被引量:2
  • 2Kalker J J.三维弹性体的滚动接触[M].峨眉:西南交通大学出版社,1997.
  • 3Polach O. A fast wheel-rail forces calculation computer code[J]. Vehicle System Dynamics, 1999,33(S) : 728-739.
  • 4Jendel T. Prediction of wheel and rail Wear-methodology and verification[R]. 1999.
  • 5Telliskivi T. Wheel-rail wear simulation[J]. Wear, 2004,257: 1145-1153.
  • 6Tomas Jendel, Mats Berg. Prediction of wheel profile wear-methodology and verification[J]. Vehicle System Dynamics, 2002,37(S) :502-513.
  • 7日本ゴム協会杂志,(2003):46-51.
  • 8唐国俊.橡胶机械设计[M].北京:化学工业出版社,1984.260-263.
  • 9D J Kim, B M Kim. Application of neural network and FEM for metal forming process [J]. International Journalof Machine Tools & Manufacture 2000,40:911--925.

共引文献15

同被引文献22

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部