A new fast approach for crack prediction based on Machine and Deep Learning

The identification of crack in plate structures is a critical element in the management of maintenance and quality assurance processes in mechanical and civil engineering constructions. Non-Destructive Testing (NDT) techniques based on a wide range of physical principles have been developed and are used in common practice for Structural Health Monitoring (SHM). Furthermore, NDT techniques are usually limited in their ability to predict the correct information about crack (location, length, and shape), which is important in engineering applications, such as SHM in aircrafts structures. Hence, various researchers have used the extended finite element method (XFEM) to study the fracture mechanics problems using inverse analysis, which takes large time for the prediction. Therefore, this project will contribute to a better and deeper understanding of cracked plates using extended Isogeometric analysis (XIGA) and experimental measurements with fast prediction based on newly creating approaches using Machine Learning (ML) and Deep Learning (DL) techniques.