Robust Powerline Equipment Inspection System Based on a Convolutional Neural Network

Abstract

Electric power line equipment such as insulators, cut-out-switches, and lightning-arresters play important roles in ensuring a safe and uninterrupted power supply. Unfortunately, their continuous exposure to rugged environmental conditions may cause physical or electrical defects in them which may lead to the failure to the electrical system. In this paper, we present an automatic real-time electrical equipment detection and defect analysis system. Unlike previous handcrafted feature-based approaches, the proposed system utilizes a Convolutional Neural Network (CNN)-based equipment detection framework, making it possible to detect 17 different types of powerline insulators in a highly cluttered environment. We also propose a novel rotation normalization and ellipse detection method that play vital roles in the defect analysis process. Finally, we present a novel defect analyzer that is capable of detecting gunshot defects occurring in electrical equipment. The proposed system uses two cameras; a low-resolution camera that detects insulators from long-shot images, and a high-resolution camera which captures close-shot images of the equipment at high-resolution that helps for effective defect analysis. We demonstrate the performances of the proposed real-time equipment detection with up to 93% recall with 92% precision, and defect analysis system with up to 98% accuracy, on a large evaluation dataset. Experimental results show that the proposed system achieves state-of-the-art performance in automatic powerline equipment inspection.

Evaluation of Power Insulator Detection Efficiency with the Use of Limited Training Dataset

“…This article presented the comparison results for the detection of an object of the "power insulator" class while maintaining a limited training dataset consisting of five, 10,15,20,25,30,35,40,45,50,55, and 60 frames of visual material. The research aimed to assess the influence of the size of training dataset on the achieved efficiency for various deep neural network architectures.…”

“…The quality of prediction generated by convolutional neural networks depends to a large extent on the use of an appropriate machine learning dataset [8]. The dataset built to solve a specific problem should be characterized by the following features [9,10]:…”

“…In the in-depth study for testing of selected CNNs (the faster regionconvolutional neural network (faster R-CNN) and the region-based fully convolutional network (R- In the next stage, the selected images were divided into training datasets consisting of 15, 30, and 60 frames, and a test dataset consisting of 283 frames containing 2560 regions of interest (ROIs) representing a power insulator. In the in-depth study for testing of selected CNNs (the faster region-convolutional neural network (faster R-CNN) and the region-based fully convolutional network (R-FCN)), training datasets were also prepared, comprising five, 10,20,25,35,40,45,50, and 55 frames. A detailed description of the dataset preparation process with its sample elements is described in more detail in the next section.…”

“…The test dataset consisted of 283 images (2560 ROIs), and the entire training dataset contained 60 images (578 ROIs). Additionally, the training dataset was divided into smaller sets of images, i.e., five,10,15,20,25, 30, 35, 40, 45, 50, 55, and 60 frames.Appl. Sci.…”

Insulator Segmentation for Power Line Inspection Based on Modified Conditional Generative Adversarial Network

“…Siddiqui et al propose a rotation normalization and ellipse detection method. The proposed Convolutional Neural Network-(CNN-) based detection framework achieves detecting 17 different types of insulators [15]. In [16], authors improve the anchor generation method and nonmaximum suppression (NMS) in the region proposal network (RPN) of the faster R-CNN model, which enhance the accuracy and efficiency.…”