Abstract
Insulator defect detection is an important task in inspecting overhead transmission lines. However, the surrounding environment is complex, and the detection accuracy of traditional image processing algorithms is low. Therefore, insulator defect detection is still mainly performed manually. In order to improve this situation, we proposed an insulator defect detection method called INSU-YOLO based on deep neural networks. Overexposure points in the image will interfere with insulator detection, so we used image augment to reduce noise and extract the edge information of the insulator. Based on an attention mechanism, we introduced a structure called attention-block where the backbone extracts the feature map, and this aims to improve the ability of our method to detect insulators. Insulators have a variety of specifications, and the location and granularity of defects are also different. Therefore, we proposed an adaptive threat estimation method based on the area ratio between the entire insulator and the defect area. In addition, in order to solve the problem of data shortage, we established a dataset called InsuDetSet for model training. Experiments on the InsuDetSet dataset demonstrated that our model outperforms existing state-of-the-art models regarding both the detection box and speed.
Highlights
The main function of insulators is electrical insulation and line support, which are critical for power transmission
This paper proposes a missing-sheds granularity estimation of glass insulators based on deep neural networks, which can obtain insulator identification and defect degree estimation results based on a real insulator set
The model first uses an image augment module to improve the quality of the input image and to provide edge images, and uses an INSU-YOLO framework to obtain detection frames for insulators and defects
Summary
The main function of insulators is electrical insulation and line support, which are critical for power transmission. Xiao et al [37] used the difference in calorific value between normal and faulty areas of insulators, introduced the K-means clustering method to eliminate bad data, and proposed a fault detection method for insulator strings based on infrared image analysis and a probabilistic neural network. It can be inferred from the above research that the current insulator identification and defect detection methods are generally limited by a complex background and by the image quality, and the detection accuracy needs to be improved Our summary of these methods is as follows: Traditional image processing algorithms have a fast calculation speed and low resource requirements and are suitable for real-time operation on edge devices. The insulator defect detection algorithm based on deep neural networks has excellent accuracy, but the current research mainly applies state-of-the-art methods, and there are few studies on detailed analysis of the defect area. We focused on a one-stage target detection method within the deep neural network, combined with the actual background of the data and the visual characteristics of the insulator, and proposed an insulator defect detection method
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
