全部 标题 作者
关键词 摘要

OALib Journal期刊
ISSN: 2333-9721
费用:99美元

查看量下载量

相关文章

更多...

基于BP神经网络的生物质发泡材料性能预测模型及应用

, PP. 107-111

Keywords: 神经网络,EVA,发泡,拉伸强度,回弹率

Full-Text   Cite this paper   Add to My Lib

Abstract:

以EVA(乙烯-醋酸乙烯酯)和淀粉质量比、甘油含量、NaHCO3含量为3个输入量,以拉伸强度和回弹率为输出量,建立3层BP(backpropagation)神经网络,并将淀粉挤出发泡的正交实验结果作为样本对其进行训练,用以预测淀粉发泡材料的性能。研究结果证明,该BP神经网络能准确预测淀粉发泡材料的性能;同时发现,随着甘油含量的增加,淀粉发泡材料的回弹率逐渐增加,而拉伸强度则逐渐减小;NaHCO3发泡剂的质量分数为3%时,淀粉发泡材料的拉伸强度最小。研究结果将为提高生物质发泡材料的性能以及扩展其使用范围提供信息。

References

[1]  戴宏民, 戴佩华. 发泡植物纤维制品关键工艺技术研讨[J].包装工程, 2004, 25(2): 9-10. Dai Hongmin, Dai Peihua. Study on the key technologies of products of the foaming plant fibre[J]. Packaging Engineering, 2004, 25(2): 9-10.
[2]  吴 强.淀粉类生物降解材料研究进展[J].甘肃科技, 2000, 53(4): 16. Wu Qiang. The research progress of starchy biodegradable materials[J].Gansu Science and Technology, 2000, 53(4): 16.
[3]  黄 鹍, 陈森发, 周振国.基于正交试验法的神经网络优化设计[J].系统工程理论方法应用, 2004, 13(3): 272-275. Huang Kun, Chen Senfa, Zhou Zhenuo. Neural network optimal design based on orthogonal experiment method[J].System Engineering Theory-Methodology-Applications, 2004, 13(3): 272-275.
[4]  林新波, 张质良, 阮雪榆.利用BP神经网络预测材料温锻流动应力[J].上海交通大学学报, 2002, 36(4): 459-461. Lin Xinbo, Zhang Zhiliang, Ruan Xueyu.Prediction of material flow stress in warm forging with BP neural network[J]. Journal of Shanghai Jiaotong University, 2002, 36(4): 459-461.
[5]  张 雯, 王红洁, 张 勇, 等.凝胶注模工艺制备高强度多孔氮化硅陶瓷[J].无机材料学报, 2004, 19(4): 743-748. Zhang Wen, Wang Hongjie, Zhang Yong, et al. Preparation and study of porous Si3N4 ceramics with high strength by gelcasting[J].Journal of Inorganic Materials, 2004, 19(4): 743-748.
[6]  He Z Y, Zhang Y F, Wei C J, et al. A multistage self-organizing algorithm combined transiently chaotic neural network for cellular channel assignment[J]. IEEE Transactions on Vehicular Technology, 2002, 51(6): 1386-1396.
[7]  Geogre D M, Michael N V, Geogre S A. Effective backpropagation training with variable stepsize[J]. Neural Networks, 1997, 10(1): 69-82.
[8]  蔡安辉, 刘永刚, 孙国雄.基于正交实验的BP神经网络预测研究[J].中国工程科学, 2003, 5(7): 67-71. Cai Anhui, Liu Yonggang, Sun Guoxiong. Research on the forecast of the BP neural network based on the orthogonal test[J]. Engineering Science, 2003, 5(7): 67-71.
[9]  高宪文, 张傲岸, 魏庆来.基于神经网络的钢包精炼终点预报[J]. 东北大学学报, 2005, 26(8): 726-728. Gao Xianwen, Zhang Aoan, Wei Qinglai. Neural network based prediction of endpoint in ladle refining process[J]. Journal of Northeastern University, 2005, 26(8): 726-728.
[10]  李 烁, 徐元铭, 张 俊. 基于神经网络响应面的复合材料结构优化设计[J].复合材料学报, 2005, 22(5): 134-140. Li Shuo, Xu Yuanming, Zhang Jun. Composite structural optimization design based on neural network response surfaces[J].Acta Materiae Compositae Sinica, 2005, 22(5): 134-140.
[11]  皮文山, 周红标, 胡金平. 基于BP神经网络混凝土抗压强度预测[J].低温建筑技术, 2011(4): 14-16. Pi Wenshan, Zhou Hongbiao, Hu Jinping. Prediction of concrete compressive strength based on bp neural network[J].Low Temperature Architecture Technology, 2011(4): 14-16.
[12]  陈 坤, 郑梯和, 宋克东, 等. BP神经网络在POE-g-MAH/HDPE增韧PA6研究中的应用[J].塑料工业, 2011, 39(8): 45-47. Chen Kun, Zheng Tihe, Song Kedong, et al. Application of BP neural network to POE-g-MAH/HDPE toughening PA6[J].China Plastics Industry, 2011, 39(8): 45-47.
[13]  何晓凤, 周红标.基于GA-BP的混凝土抗压强度预测研究[J].淮阴工学院学报, 2011, 20(3): 21-25. He Xiaofeng, Zhou Hongbiao. Prediction of concrete compressive strength based on GA-BP[J].Journal of Huaiyin Institute of Technology, 2011, 20(3): 21-25.
[14]  曾广胜, 林瑞珍, 孟 聪, 等. AC/ZnO发泡剂系对植物纤维增强淀粉复合发泡材料性能的影响[J].功能材料, 2012, 46(3): 708-711. Zeng Guangsheng, Lin Ruizhen, Meng Cong, et al. The effect of the mixed foaming agent of azodicarbonamide and zinc oxide on the properties of foamed starch-based composite strengthened by plant-fiber[J].Journal of Functional Materials, 2012, 46(3): 708-711.

Full-Text

Contact Us

[email protected]

QQ:3279437679

WhatsApp +8615387084133