A model for predicting the tensile strength of ultrafine glass fiber felts with mathematics and artificial neural network

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.

Keywords:

• Tensile strength
• ultrafine glass fiber felts
• artificial neural network
• model

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

The present work was supported by the National Natural Science Foundation of China (Grant Nos. 51772151 and 51705113) and the Priority Academic Program Development of Jiangsu Higher Education Institutions. This work was also supported by the Natural Science Foundation of Jiangsu Province (Grant No. BK20191192), China Postdoctoral Science Foundation (Grant No. 2019M661934), Jiangsu Postdoctoral Science Foundation (Grant No. 2019K210), Open Project of Key Laboratory of Jiangsu Provincial University (Grant No. KJS1931).