This article presents research conducted on various polymer models imitating biological structures. Tests were conducted using a newly developed research method described in [1]. The purpose of our research was to check if the measuring system [1] is able to distinguish multilayer samples. Test materials were two different polymer models which were subjected to pressure in the central point. Marked points on the external surface of the sample were followed during the measurement. The arrangement of points on the image allowed to reconstruct the 3D surface of the sample and to determine the displacement of the analysed points. Measurements were repeated 10 times to ensure the representativeness (credibility) of the conducted research. Statistical tests and artificial neural networks (ANN) were used to classify the examined samples. We used 5-fold cross-validation for training and validating the ANN. The entire set of 75 cases was divided into 5 equinumerous subsets. The obtained results suggest that the proposed method distinguished between the tested samples on the basis of results. Analysed materials react differently to the given mechanical factor.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.