Modeling of filament level plain woven Kevlar 49 fabric for accurate prediction of yarn pull-out behavior

This paper proposes two numerical and one analytical yarn pull-out models to investigate pull-out behavior and its energy transfer mechanism. First, the microgeometry of a two-dimensional woven fabric is generated with 112 fibers per yarn mesh implementing the digital element approach. In this approach, one yarn consists of a bundle of fibers and one fiber is made of a chain of rod elements. As such, the realistic yarn surface and yarn cross-section shapes are derived from fiber alignment. Meanwhile, a yarn-level fabric model with constant yarn cross-sectional shape is built on commercial textile modeling software TexGen. Then, both numerical and analytical yarn pull-out models are proposed to investigate the fabric performance. Results show the pull-out force and transferred energy of the digital element approach model is higher than the other two models and closer to the experimental data. This indicates that the realistic yarn surface introduces more contact points and the period of the pull-out force is determined by material properties rather than detailed fabric geometric configuration. Second, a detailed parametric study is carried out with a broad range of friction coefficient and tensile preload. The simulation results find out, when the tensile pre-load is between 50 N and 300 N, the transverse force drops immediately after the pull-out process begins. When the tensile pre-load reaches 400 N, the transverse force increases instead. This phenomenon indicates that the transverse force is sensitive to tensile pre-load and can be used as an indicator to detect residual stress in fabric.