Image Processing and Machine Learning Applied for Condition Monitoring of 11-kV Power Distribution Line Insulators using Curvelet and LTP Features

Due to massive growth in the consumption of power, the damaged insulators on the electric poles prompt the breakage of the power supply which leads to considerable loss occurring for the power industry and regular monitoring is required. So, pictures of the poles can be taken, send them to the processing unit and image processing techniques can be applied to classify the insulator health condition into healthy or risky and necessary action can be taken by the maintenance personnel. The insulator images are extracted from the acquired pole image input and then individual insulator's statistical features are obtained based on Curvelet transform based statistical features and Local Ternary Pattern (LTP) histograms. The obtained features of insulator images are given to Support Vector Machines classifier to determine the health condition of an insulator and the experiment results are validated.