1. Aan approach for monitoring the arcing discharges by using image processing techniques
Authors : Mahalakshmi R, B.indhira Priyadharsini
Pages : 184-191
DOI : http://dx.doi.org/10.21172/1.73.026
Keywords : KNN, SVM, Flash over, insulator pollution arcing discharges. Abstract :Insulator flash over under pollution is one of the most important problems for power transmission. This paper is dedicated to monitor discharges activity through arcing discharges pattern recognition using a combination of efficient image processing and classification algorithms. Images are extracted from recorded videos of flash over process over a plane model insulator under various contamination levels. Then an algorithm is designed and tested from the image that we have obtained from the recorded video. The algorithm is mainly classified into four stages. First, Otsu image segmentation algorithm is initially applied on images. By means of which we obtain the segmented image with noises. In order to eliminate unwanted noises such as light reflections on the insulator model we go for morphological filtering by combining erosion and dilation operations is computed. Third step deals with labelling the connected components and obtaining the four parameters namely Nl, Np, L and W respectively. These parameters are given as input for the fourth step. Finally the fourth stage deals with image classification in which three classifier algorithms(KNN, SVM, Navie Bayes) are being used and the arcing discharge is being monitored which helps in knowing about the proper functioning of the insulator.
Citing this Journal Article :Mahalakshmi R, B.indhira Priyadharsini, "Aan approach for monitoring the arcing discharges by using image processing techniques", Summer Special Issue - - June 2016, 184-191
Click here to Submit Copyright Takedown Notice for this article.