None

Characterization of micrometeoroid and orbital debris impacts on space structures using deep learning neural networks incorporating experimental and simulated data

Authors: John Aldrin (Computational Tools) , Michael Weiss (Orbital Transports, LLC) , Nabil Boutaleb (Orbital Transports, LLC) , Geza Gyuk (Orbital Transports, LLC) , David Hurst (Orbital Transports, LLC)

  • Characterization of micrometeoroid and orbital debris impacts on space structures using deep learning neural networks incorporating experimental and simulated data

    None

    Characterization of micrometeoroid and orbital debris impacts on space structures using deep learning neural networks incorporating experimental and simulated data

    Authors: , , , ,

Options

Abstract

Deep Learning Neural Network (DLNN) algorithms are introduced in this work to detect the occurrence of MMOD impacts, determine the location of the impact site, and classify the severity of consequent damage. To address the challenges of limited empirical training data and ensuring robustness to varying test conditions, training DLNN is explored using a mixture of simulated and experimental data. Even with a relatively small training data set, the effectiveness of this approach was demonstrated for characterizing low velocity impacts on representative Whipple shielding structures.

How to Cite:

Aldrin, J., Weiss, M., Boutaleb, N., Gyuk, G. & Hurst, D., (2019) “Characterization of micrometeoroid and orbital debris impacts on space structures using deep learning neural networks incorporating experimental and simulated data”, Review of Progress in Quantitative Nondestructive Evaluation .

Downloads:
Download PDF

219 Views

104 Downloads

Published on
2019-12-03

Peer Reviewed

License