An intelligent recognition system for insulator string defects based on dimension correction and optimized faster R-CNN
- PDF / 3,614,105 Bytes
- 9 Pages / 595.276 x 790.866 pts Page_size
- 75 Downloads / 214 Views
ORIGINAL PAPER
An intelligent recognition system for insulator string defects based on dimension correction and optimized faster R-CNN Tao Lin1 · Xiaowei Liu1 Received: 3 July 2020 / Accepted: 26 August 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract In this paper, an intelligent recognition system for insulator based on dimension correction and optimized faster region with convolutional neural network (R-CNN) is proposed. In the process of insulator pictures shooting, a laser radar is used to calculate the UAV correction vector. The position of the UAV is adjusted to ensure the consistency of the spatial dimensions of the pictures taken in different time dimensions. Based on the almost invariant spatial dimension, the faster R-CNN image recognition algorithm is optimized. When the target detection frame is generated, marked reference pictures are added to narrow the search range, improve the target detection frame generation speed, and reduce the number of pictures during training. Experiments and comparison analysis are included. They verify the optimized faster R-CNN image recognition algorithm requires less pictures and recognition time, and the recognition accuracy increased from 85.6 to 97.3%. Keywords Insulator string defects · Dimension correction · Optimized faster R-CNN · Intelligent recognition system
1 Introduction The stable and reliable operation of transmission lines is very important for smart grid. According to the statistics of State Grid Corporation, the probability of power system failure caused by various insulator faults is the largest [1–3]. As a special insulating part, insulators in transmission lines play an important role in supporting conductors and preventing current from returning to earth. If insulators fail, there will be contacts between transmission lines and transmission lines or between transmission lines and towers, and the power supply will interrupt [4, 5]. In severe cases, even a large-scale power outage will occur, causing huge property losses. It is particularly important to regularly inspect transmission lines and timely discover insulator defects to eliminate potential safety hazards. Traditional monitoring methods mainly rely on manual inspection to check the towers. However, most transmission lines are located in remote mountainous areas [6–8]. There are some objective factors such as difficulty in inspection, long time consumption, large workload, high cost and weather, etc., which makes it is impossible to effec-
B 1
Xiaowei Liu [email protected] School of Electrical Engineering and Automation, Wuhan University, Wuhan 430072, Hubei, China
tively monitor the operating state of the insulators. Therefore, unmanned aerial vehicles (UAVs) are used in the monitor and diagnosis of the operation status of the insulator [9, 10]. In the process of UAV inspection, one of the most critical steps is to identify the pictures taken by drones and then check the states of insulators [1, 11, 12]. Computer vision and digital image processing technology are
Data Loading...
