Insulator Detection Method in Inspection Image Based on Improved Faster R-CNN

Abstract

The detection of insulators in power transmission and transformation inspection images is the basis for insulator state detection and fault diagnosis in thereafter. Aiming at the detection of insulators with different aspect ratios and scales and ones with mutual occlusion, a method of insulator inspection image based on the improved faster region-convolutional neural network (R-CNN) is put forward in this paper. By constructing a power transmission and transformation insulation equipment detection dataset and fine-tuning the faster R-CNN model, the anchor generation method and non-maximum suppression (NMS) in the region proposal network (RPN) of the faster R-CNN model were improved, thus realizing a better detection of insulators. The experimental results show that the average precision (AP) value of the faster R-CNN model was increased to 0.818 with the improved anchor generation method under the VGG-16 Net. In addition, the detection effect of different aspect ratios and different scales of insulators in the inspection images was improved significantly, and the occlusion of insulators could be effectively distinguished and detected using the improved NMS.

The Recent Development of Artificial Intelligence for Smart and Sustainable Energy Systems and Applications

“…[4] # Home energy management and ambient assisted living Non-intrusive load monitoring techniques [5] Non-intrusive load monitoring for energy disaggregation Genetic algorithm; support vector machine; multiple kernel learning [6] Optimizing residential energy consumption Bacterial foraging optimization; flower pollination [7] Non-intrusive load monitoring for energy disaggregation Long short-time memory and decision tree [8] Energy efficient coverage in wireless sensor network Distributed genetic algorithm [9] Estimation of load and price of electric grid Enhanced logistic regression; enhanced recurrent extreme learning machine; classification and regression tree; relief-F and recursive feature elimination [10] Detection of the insulators in power transmission and transformation inspection images Improved faster region-convolutional neural network [11] Non-intrusive load monitoring for energy disaggregation Concatenate convolutional neural network [12] Non-intrusive load monitoring for energy disaggregation Linear-chain conditional random fields [13] Prediction of the rheological properties of calcium chloride brine-based mud Artificial neural network [14] Estimation of Static Young's Modulus for sandstone formation Artificial neural network; self-adaptive differential evolution # Review article.…”

“…Z. Zhao, Z. Zhen, L. Zhang, Y. Qi, Y. Kong, and K. Zhang have published an article "Insulator detection method in inspection image based on improved faster R-CNN" [10]. This paper proposed an improved faster region-convolutional neural network to detect the insulators in power transmission and transformation inspection images.…”

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

“…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]:…”

TL-Net: A Novel Network for Transmission Line Scenes Classification

“…Deep convolutional neural networks have been adopted in different fields, such as insulator detection [24,25] and power line inspection [26,27]. Previous researchers have done lots of work on transmission line scene classification.…”