Ramanan Sridaran Venkat

TL;DR: In this paper, the authors adapted the NDT according to the Berens model to guided wave-based structural health monitoring (SHM) systems, and the concept of a POD map was introduced to evaluate the effect of damage position on system reliability.

TL;DR: A plausible theoretical perspective inspired from neuroscience is proposed for signal representation of deep learning framework to model machine perception in structural health monitoring (SHM), especially because SHM typically involves multiple sensory input from different sensing locations.

TL;DR: In this article, a numerical simulation platform for structural health monitoring purposes has been established, where the requirements and options for further extension of those tools and different test cases applied for validation so far are described.

TL;DR: In this article, the authors propose a study on an experimental panel where Probability of Damage analysis is performed and using the information of the damage location and the mesh created to perform such analysis, a guided wave simulation is performed to optimize the actuator-sensor locations so that the sensors mounted can capture the signal carrying the signature of the defect present in the component.

TL;DR: The sequence developed will be demonstrated along two examples, a first one being a plate with a notch grove through which guided waves are sent and the resulting signals are processed considering different algorithms looking at the time domain signal first and then moving onwards to difference of signals, Hilbert transform, oblique polarization filtering, and statistical methods like Auto-Covariance Function.