By Topic

Fitting of a neural network to control the intelligent operation of a high voltage circuit breaker

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
$33 $33
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

4 Author(s)
X. Chen ; Lab. d'Etude et de Recherche en Instrum. Signaux et Syst., Univ. de Paris Val-de-Marne, Creteil, France ; P. Siarry ; Z. Ma ; S. Huang

'Intelligent operation (IO)' can improve the reliability of a high voltage circuit breaker and prolong its life. In this paper an artificial neural network (ANN) is used in the control of circuit breaker intelligent operation. Thus, during real-time control, it can save a lot of calculating time spent in the very complicated opening process of the circuit breaker. In the design of the controller of a circuit breaker IO, the structure of feedforward multilayer network is used, and two kinds of back-propagation learning algorithms, the self-adapting adjusting learning and the momentum method, are applied to the supervised training of the neural network. Both algorithms greatly enhance the training speed, shorten the training time and speed up the convergence. After training, an artificial neural network controller (ANNC) of the system is formed. It is proved that the ANNC has a higher accuracy and can meet the controlling requirement of the circuit breaker IO. This method can be used for reference by other control systems for solving complicated nonlinear control equations.

Published in:

IEE Proceedings - Generation, Transmission and Distribution  (Volume:151 ,  Issue: 6 )