loading
Papers Papers/2022 Papers Papers/2022

Research.Publish.Connect.

Paper

Paper Unlock

Authors: Maxime Pouilly-Cathelain 1 ; Philippe Feyel 2 ; Gilles Duc 3 and Guillaume Sandou 3

Affiliations: 1 Safran Electronics & Defense, Massy, France, L2S, CentraleSupélec, CNRS, Université Paris-Sud, Université Paris-Saclay, Gif-sur-Yvette and France ; 2 Safran Electronics & Defense, Massy and France ; 3 L2S, CentraleSupélec, CNRS, Université Paris-Sud, Université Paris-Saclay, Gif-sur-Yvette and France

Keyword(s): Neural Network, Prediction, Disturbance Observer.

Related Ontology Subjects/Areas/Topics: Informatics in Control, Automation and Robotics ; Intelligent Control Systems and Optimization ; Machine Learning in Control Applications ; Neural Networks Based Control Systems ; Nonlinear Signals and Systems ; Signal Processing, Sensors, Systems Modeling and Control

Abstract: Neural network prediction is a very challenging subject in the presence of disturbances. The difficulty comes from the lack of knowledge about perturbation. Most papers related to prediction often omit disturbances but, in a natural environment, a system is often subject to disturbances which could be external perturbations or also small internal parameters variations caused, for instance, by the ageing of the system. The aim of this paper is to realize a neural network predictor of a nonlinear system; for the predictor to be effective in the presence of varying perturbations, we provide a neural network observer in order to reconstruct the disturbance and compensate it, without any a priori knowledge. Once the disturbance is compensated, it is easier to realize such a global neural network predictor. To reach this goal we model the system with a State-Space Neural Network and use this model, completed with a disturbance model, in an Extended Kalman Filter.

CC BY-NC-ND 4.0

Sign In Guest: Register as new SciTePress user now for free.

Sign In SciTePress user: please login.

PDF ImageMy Papers

You are not signed in, therefore limits apply to your IP address 3.90.242.249

In the current month:
Recent papers: 100 available of 100 total
2+ years older papers: 200 available of 200 total

Paper citation in several formats:
Pouilly-Cathelain, M.; Feyel, P.; Duc, G. and Sandou, G. (2019). Enhancing Neural Network Prediction against Unknown Disturbances with Neural Network Disturbance Observer. In Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO; ISBN 978-989-758-380-3; ISSN 2184-2809, SciTePress, pages 210-219. DOI: 10.5220/0007831102100219

@conference{icinco19,
author={Maxime Pouilly{-}Cathelain. and Philippe Feyel. and Gilles Duc. and Guillaume Sandou.},
title={Enhancing Neural Network Prediction against Unknown Disturbances with Neural Network Disturbance Observer},
booktitle={Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO},
year={2019},
pages={210-219},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0007831102100219},
isbn={978-989-758-380-3},
issn={2184-2809},
}

TY - CONF

JO - Proceedings of the 16th International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO
TI - Enhancing Neural Network Prediction against Unknown Disturbances with Neural Network Disturbance Observer
SN - 978-989-758-380-3
IS - 2184-2809
AU - Pouilly-Cathelain, M.
AU - Feyel, P.
AU - Duc, G.
AU - Sandou, G.
PY - 2019
SP - 210
EP - 219
DO - 10.5220/0007831102100219
PB - SciTePress