Identification of elastic properties of composites is relevant for both nondestructive materials characterization as well as for in-situ condition monitoring to assess and predict any possible material degradation. Learning paradigms have been well explored when it comes to detection and characterization of defects in safety-critical structures, but are relatively unexplored when it comes to structural materials characterization. In this thesis we propose a learning paradigm that includes the potential use of Machine Learning (ML) and Deep Learning (DL) algorithms to solve the inverse problem of material properties identification using ultrasonic guided waves. The propagation of guided waves in a composite laminate is modelled using two different modelling techniques as part of the forward problem. Here, we use the two fundamental modes of guided waves, i.e. the anti-symmetric (A0) and the symmetric modes (S0) as features for the proposed learning models. As part of the inverse problem, different learning models are used to map feature space to target space that consists of the material properties of composites. The performance of the algorithms is evaluated based on different metrics and it is seen that the networks are able to learn the mapping and generalize well to unseen examples even in the presence of noise at various levels. Overall, we are able to develop a complete framework consisting of many interlinking data processing algorithms that can effectively estimate and predict the material properties of any given composite.
Read
