Improved fault detection in cable television networks
Date
1998
Authors
Kourounakis, Nicolaos P.
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This thesis presents a novel model-based fault detection system specifically designed to offer improved fault detection for the reverse pilot of cable television networks. The approach, however, is general and can be applied to a variety of large scale engineering plants. For the modeling part of the system, feedforward neural networks and statistical analysis techniques are employed. A description of these techniques as well as the fault detection methodology used is provided. Finally, this thesis presents the results of a large scale experiment on which the fault detection properties of the developed technique were evaluated and compared to those of limit checking fault detection.