Research projects

Spatiotemporal dynamics of plasma

Spatiotemporal dynamics of charged particles beams in particle accelerators

Structural health monitoring

  1. Out-of-distribution detection/Anomaly detection in aerospace composites: Collecting datasets accommodating all possible damage scenarios is cumbersome, costly, and inaccessible for aerospace applications. In this paper, we have proposed two different self-supervised representation learning approaches to learn the distribution of baseline signals. The trained self-supervised learner is used for delamination prediction with an anomaly detection philosophy. We metholdogies like autoencoders, variational autoencoders, PCA-SVM, ICA-SVM are employed. More about this work is available here Paper-1, Paper-2

  1. Deep variational filtering for temperature effects in guided wave structural health monitoring. More about this work is available here Paper-1
  2. Physical-knowledge assisted ML for structural health monitoring. More about this work is available here Paper-1
  3. Deep surrogate inverse solvers for guided wave SHM: More about this work is available here Paper-1

Neural surrogate solvers for PDEs.

Material informatics

Safety of space habitats

Robotics