DMCA
ElSharkawi, ″Environmentally Adaptive Sonar Control in a Tactical (2002)
| Venue: | Impact of Environmental Variability on Acoustic Predictions and Sonar Performance |
| Citations: | 3 - 0 self |
BibTeX
@INPROCEEDINGS{Fox02elsharkawi,″environmentally,
author = {Warren L. J. Fox and Megan U. Hazen and Chris and J. Eggen and Robert J. Marks and Ii and Mohamed A. El-sharkawi},
title = {ElSharkawi, ″Environmentally Adaptive Sonar Control in a Tactical},
booktitle = {Impact of Environmental Variability on Acoustic Predictions and Sonar Performance},
year = {2002},
pages = {595602}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Automatic environmentally adaptive sonar control in littoral regions characterized by high spatial/temporal acoustic variability is an important operational need. An acoustic model-based sonar conroller requires an accurate model of how the sonar would perform in the current environment while in any of its possible configurations. Since high-fidelity acoustic models are computationally intensive, and finding the optimal sonar mode may require a large number of these model runs, such a controller may not be able to provide optimal line-up solutions in tactically useful time frames. We have explored a method of statistically characterizing a given operations area, generating a large ensemble of acoustic model runs, and training specialized artificial neural networks to emulate acous-tic model input/output relationships. The neural networks reproduce the acoustic model outputs to a good degree of accuracy in a small fraction of the compute time needed for one of the original model runs. In this paper, the neural network training method is described, examples of neural network performance are given, and an example of con-troller solutions in a variable environment are presented. (Approved for Public Release; Distribution is Unlimited.) 1
Keyphrases
environmentally adaptive sonar control optimal line-up solution large number specialized artificial neural network neural network public release variable environment littoral region neural network performance model run acoustic model run acoustic model output acous-tic model input output relationship high spatial temporal acoustic variability neural network training method adaptive sonar control con-troller solution high-fidelity acoustic model optimal sonar mode large ensemble acoustic model-based sonar conroller important operational need compute time current environment operation area useful time frame original model run accurate model good degree possible configuration small fraction
