Condition Assessment of Power Transformer Winding by FRA using Different AI Techniques
Author(s):
Bhatt Palak R. , L. D. COLLEGE OF ENGINEERING; Nilesh D. Rabara, L. D. COLLEGE OF ENGINEERING
Keywords:
Transformer; FRA; ANN; Winding Parameters; PNN; GRNN
Abstract:
There are many methods of fault diagnosis of Power transformer but among all these FRA is the most suitable method for electrical and /or mechanical faults of a transformer. The concept of FRA has been successfully used as a diagnostic technique to detect the winding deformation of power transformer. In FRA measurement, the nine statistical indicators are used to detect the deviation in FRA signature. The effects of different winding parameters on FRA signature is described. The artificial neural network approach has been proposed to complement these nine indicators. ANN can be used to increase the efficiency and accuracy of diagnosis system. Neural network toolbox is used to train the multilayer feed-forward neural network. The Probabilistic neural network (PNN) approach and General Regression Neural network (GRNN) has been introduced due to its higher sensitivity and accuracy over the neural network. Neural pattern recognition toolbox is used to train the multilayer probabilistic neural network. Different practical case studies and their data are used to train and test the multilayer feed-forward neural network, probabilistic neural network and general regression neural network.Among all these AI techniques PNN gives the best accuracy result. In this work Matlab-2014 is to be used.
Other Details:
Manuscript Id | : | IJSTEV1I12077
|
Published in | : | Volume : 1, Issue : 12
|
Publication Date | : | 01/07/2015
|
Page(s) | : | 220-227
|
Download Article