Conference Paper

Neural network identification and characterization of digital satellite channels: application to fault detection

Nat. Polytech. Inst. of Toulouse
DOI: 10.1109/ICC.1997.594987 Conference: Communications, 1997. ICC 97 Montreal, 'Towards the Knowledge Millennium'. 1997 IEEE International Conference on, Volume: 3
Source: IEEE Xplore


The paper proposes a neural network technique to adaptively model
and characterize digital satellite channels. The neural network model
allows to identify each component of the channel by the use of the
channel input-output signals as learning data. This technique was
applied to fault detection in digital satellite links, especially those
arising in on-board devices. The paper gives simulation examples of
changes in the on-board filter characteristics. Our adaptive method
allows to determine the origins of the changes and gives the new
characteristics of the channel

1 Read
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a neural network approach for modeling nonlinear memoryless communication channels. In particular, the paper studies the approximation of the nonlinear characteristics of traveling-wave tube (TWT) amplifiers used in satellite communications. The modeling is based upon multilayer neural networks, trained by the odd and even backpropagation (BP) algorithms. Simulation results demonstrate that neural network models fit the experimental data better than classical analytical TWT models,
    IEEE Transactions on Communications 08/1997; 45(7-45):768 - 771. DOI:10.1109/26.602580 · 1.99 Impact Factor