基于BP神经网络的生物质发泡材料性能预测模型及应用  

Prediction model and application of biological foaming materials based on BP neural network

作　　者：曾广胜[1] 孙刚[1] 

机构地区：[1]湖南工业大学包装与材料工程学院,株洲412007

出　　处：《复合材料学报》2014年第1期107-111,共5页Acta Materiae Compositae Sinica

基　　金：国家自然科学基金(61174100);湖南省科技计划项目(2010JT4039);湖南省教育厅产业化培育项目(09CY016);福建晋江市科技局重点项目(晋财指标{2011}200号);湖南省自然科学杰出青年基金(13JJ1024)

摘　　要：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(back propagation)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。Using the mass ratio of ethylene-vinyl acetate to starch, glycerol content and NaHCO3 content as the input parameters, the tensile strength and resilience as the output parameters, a 3-layer BP （back propagation） neural network were established. The extrusion foaming orthogonal experiment result of the starch were taken as sample to forecast the properties of starch foaming materials. The results show that the BP neural network could accurately predict the properties. Meanwhile, the resilience of foaming material increases with the increase of glycerol content, while the tensile strength decreases with the glycerol contenCs increasing. When the mass fraction of NaHCO3is 3, the tensile strength reaches its minimum. The results provide information for improving the properties and expanding the application scope of the biomass foaming material.

关 键 词：神经网络 EVA 发泡 拉伸强度 回弹率 

分 类 号：TB332[一般工业技术—材料科学与工程]