Crack Growth Prognostics with Particle Filtering Technique

This paper is the project deliverable for the MSc course entitled "Artificial Intelligence and Advanced Simulation", held at Politecnico di Milano for the Master of Science in Nuclear Engineering. It presents a simple application of a Particle Filtering Technique to track the crack degradation state of a 1D loaded plate, adopting a Bayesian framework and implementing a Sampling Importance Resampling algorithm..