2012 | OriginalPaper | Buchkapitel
The Application of Improved Artificial Fish Swarm and Support Vector Machine in Transformer Fault Diagnosis
verfasst von : Hong Yu, Jie Wei, Dada Wang, Peng Sun
Erschienen in: Advances in Technology and Management
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
IEC three-ratio of the dissolved gas analysis (DGA) is an important and effective method for transformer fault diagnosis. Fuzzy theory is availed to avoid the deficiency of the three-ratio boundary that is too absolute. Meanwhile, an improved artificial fish swarm optimization (IAFSO) technique is utilized to optimize and automatically confirm the parameters of the SVM. The global searching ability of the IAFSO approach is utilized to find the optimization solution of the SVM parameters. Aiming at the shortcoming of three-ratio and SVM that its parameters are confirmed by the cross validation, blurring the boundary of the gas ratio and the IAFSO algorithm is inducted to optimizing the SVM. Then the IAFSO-IECSVM means is proposed in this paper. Experimental results show that the proposed algorithm in this paper that can find out the optimum accurately in a wide range. The proposed approach is robust and practical for transformer fault diagnosis.