Using a Pattern Recognition-Based Technique to Assess the Hydrophobicity Class of Silicone Rubber Materials

Several transmission and distribution companies worldwide have started to replace their existing outdoor ceramic insulators with silicone rubber insulators. The use of silicone rubber insulators in outdoor insulators was first introduced in the market almost 30 years ago. Various studies have looked at the characteristics of this material under contaminated conditions. Despite the numerous advantages of silicone rubber insulators, they still suffer from ageing especially under severe contamination conditions. Therefore, it is important to develop techniques that enable utility engineers to evaluate the ageing performance of silicone rubber insulators. The aim of this paper is to develop an automatic system to classify and assess the condition of silicone rubber insulators using image processing and pattern recognition techniques. In this research, several feature extraction and selection techniques have been used to extract textural and statistical features. These techniques include discrete cosine transformation, wavelet transformation, Radon transformation, contourlet transformation, gray-level co-occurrence matrices, and stepwise regression. Various classifiers were examined to evaluate the extracted features. The examined classifiers included k-nearest neighbor, neural networks, and linear classifiers. A database comprised of 358 images was collected and preprocessed representing the well-known seven hydrophobicity classes. A recognition rate of 96.5% was achieved using fused features selected by a stepwise regression and classified by a neural network classifier. The system proposed by this research can be used to help utilities assess their silicone rubber insulators automatically and effectively.