Surrogate Eye Modeling for the Statistical Assessment of a Smart Textile Interconnect

Abstract

This paper focuses on the generation of a compact and accurate model of the eye aperture for a differential textile interconnect. The considered eye metric is computed through a simple and effective procedure based on a polygonal approximation of the clean inner eye area. Least squares support vector machine regression is used, yielding a fast and accurate surrogate model of the link, providing a quantitative information of the data communication quality. The generated model turns out to be a parametric description which is used in the framework of stochastic analysis and uncertainty quantification, allowing to take into account the effects of the variation of the electrical and geometrical parameters of the link. The accuracy and convergence of the proposed machine learning solution are thoroughly discussed.