基于人工神经元网络的PA6/POE/POE-g-MAH共混物力学性能预测  

Prediction of Mechanical Properties of PA6/POE/POE-g-MAH Ternary Composite by an Artificial Neural Network Model

在线阅读下载全文

作  者:冯婷婷 赖元文[2] FENG Tingting;LAI Yuanwen(Puyang Institute of Technology,Henan University,Puyang,Henan 457000,China;College of Civil Engineering,Fuzhou University,Fuzhou,Fujian 350116,China)

机构地区:[1]河南大学濮阳工学院,河南濮阳457000 [2]福州大学,土木工程学院,福建福州350116

出  处:《塑料》2023年第6期71-75,99,共6页Plastics

基  金:国家自然科学青年基金(71804026)。

摘  要:将人工神经元网络与全析因实验设计相结合,预测了PA6/POE/POE-g-MAH三元共混物的拉伸和缺口冲击强度,研究了注塑温度、注射速度、注射时间和冷却时间对共混物以上力学性能的影响。结果表明,当三元共混物质量比为74.5/20/5/0.5时,材料的缺口冲击强度均大于95 kJ/m^(2),POE分散相粒径约为200~400 nm。通过析因实验设计发现,注塑温度、注射速度以及两者的交互效应对共混物拉伸强度影响显著,注塑温度、冷却时间以及两者的交互效应是影响冲击强度的显著因素。采用4-14-1的ANN模型可以较好地预测三元共混物拉伸强度和缺口冲击强度,预测结果与实验结果回归曲线的斜率均大于97%。与多元线性回归模型相比,ANN模型预测性能明显更佳,其Pearson相关系数大于0.97。An artificial neuron network was combined with a full factorial experimental design to predict the tensile and notched impact strength of PA6/POE/POE-g-MAH ternary composite,in which four injection molding parameters,namely injection temperature,injection speed,injection time and cooling time were considered.The results showed that when the mass fraction of the ternary blend was 74.5/20/5/0.5,the notched impact strength of the composite exceeded 95 kJ/m^(2),and the particle size of the POE dispersed phase was between 200 and 400 nm.It was also found that injection temperature,injection speed and their interaction effect had significant effects on the tensile strength of the composite.Injection temperature,cooling time and their interaction effect were the significant factors effecting the notched impact strength of the composite.The ANN models with 4-14-1 structure could predict the tensile strength and notched impact strength of the ternary blends well,and the slopes of the regression curves were both greater than 97%.The prediction performance of ANN models were significantly better than the multiple linear regression ones,and the Pearson correlation coefficients exceeded 0.97.

关 键 词:尼龙三元共混物 人工神经元网络 全析因实验设计 拉伸强度 缺口冲击强度 

分 类 号:TQ323.6[化学工程—合成树脂塑料工业]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象