Title :
Fault diagnosis of power transformers using multi-class least square support vector machines classifiers with particle swarm optimisation
Author :
Zheng, H.B. ; Liao, R.J. ; Grzybowski, S. ; Yang, L.J.
Author_Institution :
State Key Lab. of Power Transm. Equip., & Syst. Security & New Technol., Chongqing Univ., Chongqing, China
fDate :
11/1/2011 12:00:00 AM
Abstract :
This study presents a multi-class least square support vector machines (LS-SVM)-based classifier for transformer fault diagnosis. First, the original binary classifier is extended for multi-class classification that is common in fault diagnosis by using combination schemes, that is, the minimal output coding, error correcting output codes, one-against-one and one-against-all schemes. Second, the algorithm of particle swarm optimisation is implemented to select the optimal feature parameters for the multi-class LS-SVM classifiers. Then the effectiveness of the proposed approach is verified on the basis of the experiments on benchmark classification data and real-world transformer data. For comparison purpose, three widely used transformer diagnosis methods such as the IEC criteria, back propagation neural network and standard support vector machines are utilised. The results show the proposed approach has a better performance both in training and testing accuracies.
Keywords :
error correction codes; fault diagnosis; least squares approximations; neural nets; particle swarm optimisation; power transformers; support vector machines; back propagation neural network; binary classifier; combination schemes; error correcting output codes; multiclass classification; multiclass least square support vector machines classifiers; output coding; particle swarm optimisation; power transformers; transformer fault diagnosis;
Journal_Title :
Electric Power Applications, IET
DOI :
10.1049/iet-epa.2010.0298