Models and computer simulations of mechanical behavior of two-component material for structures data-driven reliability prediction

Abstract

This monograph deals with investigation the influence of material microstructure on its mechanical properties. The authors use machine learning and computer vision techniques to assess material microstructure, and computational and experimental methods to determine mechanical characteristics. The theoretical background of material elastic characteristics is investigated, with a focus on processing microstructure images, determining microstructure stress-strain states, and yield criterion. The study also examines the microstructure of dual- component material, generating statistically equivalent artificial microstructures, and evaluating the yield surface. The authors apply data-driven yield surface for structural reliability prediction and evaluate the proposed algorithm for predicting the reliability on example of the Kirsch plate and water pump housing.