By Topic

Intelligent diagnosis for autonomous underwater vehicles using a neuro-symbolic system in a distributed architecture

Sign In

Cookies must be enabled to login.After enabling cookies , please use refresh or reload or ctrl+f5 on the browser for the login options.

Formats Non-Member Member
$31 $13
Learn how you can qualify for the best price for this item!
Become an IEEE Member or Subscribe to
IEEE Xplore for exclusive pricing!
close button

puzzle piece

IEEE membership options for an individual and IEEE Xplore subscriptions for an organization offer the most affordable access to essential journal articles, conference papers, standards, eBooks, and eLearning courses.

Learn more about:

IEEE membership

IEEE Xplore subscriptions

2 Author(s)
Perrier, M. ; Underwater Syst. Dept., Ifremer Mediterranean Center, La Seyne sur mer, France ; Kalwa, J.

The paper presents the utilisation of a neuro-symbolic system designed and developed for health monitoring and diagnosis of autonomous underwater vehicles (AUVs) within a complete modular and distributed architecture. The neuro-symbolic system, named NSS has been developed within the IST European project ADVOCATE II and is part of the global architecture designed in the project. The paper focuses on the application of the ADVOCATE II solution on two different experimental AUVs: the VORTEX underwater vehicle owned and operated by Ifremer and the experimental MiniC AUV developed and operated by ATLAS ELEKTRONIK GmbH. The paper briefly describes the ADVOCATE II modular and distributed architecture, and presents in detail some study cases for the two underwater applications, and the added-value of such an approach for AUV. The NSS system developed and used within the architecture is dedicated to diagnosis of thrusters and actuators. NSS is a neuro-symbolic system which allow us to simultaneously work on symbolic rules and on neural networks, using transformation techniques. The symbolic rules are compiled at the initialisation of the system into a neural structure, further trained with representative examples. The trained neural network is then used for real-time diagnosis during the AUV mission execution.

Published in:

Oceans 2005 - Europe  (Volume:1 )

Date of Conference:

20-23 June 2005