当前位置: X-MOL 学术J. Text. Inst. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A model for predicting the tensile strength of ultrafine glass fiber felts with mathematics and artificial neural network
The Journal of The Textile Institute ( IF 1.5 ) Pub Date : 2020-06-16 , DOI: 10.1080/00405000.2020.1779167
Fei Wang 1, 2 , Zhaofeng Chen 1, 2 , Cao Wu 1, 2 , Yong Yang 3 , Duanyin Zhang 1, 2 , Shun Li 1, 2
Affiliation  

Abstract

In this article, a model for predicting the tensile strength of ultrafine glass fiber felts is presented with theoretical formula. On the basis of this model, the tensile strength depends on the mean diameter of fibers, resin content and bulk density, but the exact value of strength cannot be calculated directly. The artificial neural network (ANN) is introduced to work out the problem, where the mean diameter of fibers, resin content and bulk density are selected as input parameters, and the tensile strength of longitudinal direction and transverse direction are selected as output parameters. After compared with measured data, the predicted results by the optimized ANN model have been confirmed to have a high accuracy. The mean relative errors of the strength values of longitudinal and transversal direction predicted by the ANN model are 0.0193 and 0.0288, respectively. Three-dimensional planes for the predicted tensile strength as a function of each parameters are established to exhibit the relationship intuitively.



中文翻译:

数学和人工神经网络预测超细玻璃纤维毡拉伸强度的模型

摘要

本文用理论公式给出了预测超细玻璃纤维毡的拉伸强度的模型。在此模型的基础上,抗拉强度取决于纤维的平均直径,树脂含量和堆积密度,但强度的精确值无法直接计算。引入了人工神经网络(ANN)来解决该问题,其中选择纤维的平均直径,树脂含量和堆积密度作为输入参数,并选择纵向和横向的拉伸强度作为输出参数。与实测数据进行比较后,通过优化的人工神经网络模型预测的结果已被证实具有较高的准确性。ANN模型预测的纵向和横向强度值的平均相对误差为0。0193和0.0288。建立用于预测抗张强度作为每个参数的函数的三维平面,以直观地显示该关系。

更新日期:2020-06-16
down
wechat
bug