Self-Supervised Algorithm for Predicting Data Based on Knitting Direction in Capacitive Strain Stitch Sensors

초록

In this study, the characteristics of knit-based stitch sensors were compared using capacitance and stress values based on the knit direction. The restored predicted data were analyzed using a masked autoencoder algorithm. First, changes in capacitance with respect to strain were compared, followed by a comparison of stress values with respect to strain. The capacitance (C)$(C)$ values reflected differences in the distance between electrodes (d)$(d)$ and the area of the electrodes (A)$(A)$, with the course direction showing a larger variation. Although the stress values (sigma)$(\sigma )$ exhibited similar trends in the graph, the comparison using the elastic modulus (E)$(E)$ and Poisson's ratio (nu)$(\nu )$ confirmed that the course direction had greater deformation under the same tensile strain. Finally, using the masked autoencoder algorithm, the restoration rate of the original data was measured under 10%, 30%, 50%, and 100% noise levels, showing nearly perfect consistency. These results demonstrate the analysis of knit stitch sensor characteristics and the performance evaluation of the masked autoencoder algorithm.

키워드