Scheduled System Maintenance:
On Monday, April 27th, IEEE Xplore will undergo scheduled maintenance from 1:00 PM - 3:00 PM ET (17:00 - 19:00 UTC). No interruption in service is anticipated.
By Topic

Neural Network Application for Lightning Characteristics & Mapping for Peninsular Malaysia

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

3 Author(s)
Rahman, R.Z.A. ; Dept. of Electr. & Electron., Univ. Putra Malaysia, Serdang, Malaysia ; Soh, A.C. ; Adnan, S.N.N.

Lightning protection system design that can handle Malaysia's extreme lightning strength is crucial to maintain the reliability of the system. Therefore, system that classified the lightning characteristic by using neural networks needs to be provided to give the guidelines to obtain optimum protection system. The objectives were to classify lightning characteristics for peninsular Malaysia by using Neural Network System, to implement the design of the desired Neural Network System by using Microsoft Visual Basic in order to classify the region of Peninsular Malaysia into 9 region which are Southern, Center and Northern and to classify each of the classified region into 3 main current range which are High, Medium and Low. A neural network with back propagation training mechanism for classification was designed and trained to classify the latitude and longitude of the strike point in MS Access database. The proposed network classification results were used in the Graphical User Interface environment. The network was tested with random 7056 strike points that represent the 30% of the total data only. As a conclusion, the method was robust and flexible and can be easily extended to more database set. The network accuracies rate was approaching 97% with reasonable noise tolerance.

Published in:

Computational Intelligence, Modelling and Simulation (CIMSiM), 2011 Third International Conference on

Date of Conference:

20-22 Sept. 2011