Prediction of the nonlinear transversal compression behavior of high performance fibers using machine learning

Experimental determination of the nonlinear mechanical behavior of high performance fibers is still a big challenge due to tiny size of these materials at the micrometer level. This study proposes a prediction of the nonlinear behavior of these fibers in transversal compression using machine learning based on near 10000 data simulated from a finite element model (FE model). The study showed that this proposed method is a robust tool that permits to predict correctly the transversal compression behavior of any high performance fiber.