Pushpa Publishing House

Journal Menu

Content

Volume 17 (2018)

Volume 16 (2016)

Volume 15 (2015)

Volume 14 (2015)

Volume 13 (2014)

Volume 12 (2014)

Volume 11 (2013)

Volume 10 (2013)

Volume 9 (2012)

Volume 8 (2012)

Volume 7 (2011)

Volume 6 (2011)

Volume 5 (2010)

	Volume 5, Issue 2 Pg 131 - 263 (November 2010)
	Volume 5, Issue 1 Pg 1 - 129 (August 2010)

Volume 4 (2010)

Volume 3 (2009)

Volume 2 (2008)

Volume 1 (2007)

Advances in Computer Science and Engineering

Advances in Computer Science and Engineering
Volume 5, Issue 1, Pages 11 - 23 (August 2010)

A GENERIC MULTI AGENT-BASED PLATFORM FOR RELIABLE DIAGNOSTIC BY DGA
Jean-Pierre Lienou, Marcellin Nkenlifack, Emmanuel Tanyi and Thierry Noulamo

Abstract:
Dissolved Gas Analysis (DGA) is a set of methods used to classify defects in transformer’s diagnostic but the classification is often error-prone and the great number of DGA methods does not simplify the job for a field engineer to decide which method to choose for a fast and or a reliable diagnostic. Since the formed gases depend on the transformers’ environment (temperature, solar irradiation, etc.), the constants used in different methods are different from one place to another. This paper uses a multi agent based platform to collect measurement data online and apply on different DGA methods, use knowledge engineering techniques to help refine the constants used in different methods for a specific environment for fast and better diagnosis. The stored data permits to choose best DGA methods for specific transformers at a specific time of their life, perform unsupervised learning that could lead to a new emergent method which is less error-prone. The platform also permits the integration of non-DGA method since its architecture is opened.

Keywords and phrases: dissolved gas analysis, remote diagnosis, reinforcement learning, multi agent system, Jadex.

Number of Downloads: 342 | Number of Views: 782