With the fast development of smart grid, the power line mileage and power equipments get rapid growth. The contradiction between the large number of maintenance equipments and the small number of maintenance workers becomes increasingly prominent. Meanwhile, the traditional maintenance mode has the disadvantages of over or under maintenance, which will lead to the increasing failure risk of power transmission system. Faced with these issues, to enhance the intelligence and automation level of power line inspection, many researchers have devoted much effort to the research of automatic power line inspection and some state-of-the-art techniques about power line inspection are proposed to improve the inspection efficiency and quality, such as unmanned aerial vehicle (UAV), image processing, deep architecture, and so on. In this article, we analyzed and summarized the state-of-the-art techniques on power line inspection to provide a valuable reference for the researchers engaged in the smart grid. First, the common inspection tasks on power line inspection are reviewed. Second, the existing inspection platforms are examined in this article. Also, the advantages and disadvantages of different platforms are analyzed accordingly. Third, faced with different inspection tasks, different inspection sensors are integrated into the inspection platforms for data collection. Therefore, the common sensors on inspection platforms are discussed. Finally, to realize automatic power line inspection, different inspection methods are proposed or improved, and these advanced inspection methods are surveyed and discussed.

A Review on State-of-the-Art Power Line Inspection Techniques

Locating the tiny insulator defect object with complex backgrounds in high-resolution aerial images is a challenging task. In this paper, we propose a novel method which cascades detection and segmentation networks to identify the defect from the global and local two levels: (1) The improved Faster R-CNN is carried out to capture both defects and insulators in the entire image. ResNeXt-101 is adopted as the feature extraction network so as to fully extract features, and Feature Pyramid Network (FPN) is built to enhance the ability of detecting small targets. In addition, the Online Hard Example Mining (OHEM) training strategy is applied to solve the imbalance problem of positive and negative samples. (2) All the detected insulators are extracted and fed into the improved U-Net network to futher inspect at pixel level, we utilize the pre-trained ResNeXt-50 as the encoder of U-Net, incorporate an attention module, Spatial and Channel Squeeze & Excitation Block (SCSE), into the decoding path to highlight the meaningful information. A hybrid loss which merges binary cross entropy (BCE) loss and dice coefficient loss is designed to train our network for figuring out the class imbalance issue. The missed detection can be greatly reduced with the combination of two modified network, which makes comprehensive use of the original map information and local information. On the test set of actual images, the insulator defect recognition precision and recall of the cascade network is 91.9% and 95.7%, exhibiting strong robustness and accuracy.

/pdf/insulator-defect-recognition-based-on-global-detection-and-pr9lzv6poj.pdf

Insulator Defect Recognition Based on Global Detection and Local Segmentation

The failure of an insulator may compromise the safety of the entire power transmission system. Therefore, insulator defect detection is vital for the safe operation of power systems. However, insulator defects in an insulator image may have varying sizes, and several currently available methods do not have satisfactory detection accuracy for small defects. To address this issue, we propose an improved detection network for small insulator defects with a batch normalization convolutional block attention module (BN-CBAM) and a feature fusion module. The BN-CBAM is designed to better exploit channel information and enhance the effect of different channels on the feature map. In addition, we propose a feature fusion module that fuses multi-scale features from different layers to improve small object detection performance. Moreover, to address the scarcity of aerial images, a data augmentation method based on the fusion of the target segment and background is introduced. Experiments demonstrate that the proposed method achieves better small insulator defect detection performance than other state-of-the-art approaches. In addition, data augmentation methods enrich sample diversity and enhance the generalizability of the network.

Novel Feature Fusion Module-Based Detector for Small Insulator Defect Detection

Insulator detection is an essential task for the safety and reliable operation of intelligent grids. Owing to insulator images including various background interferences, most traditional image-processing methods cannot achieve good performance. Some You Only Look Once (YOLO) networks are employed to meet the requirements of actual applications for insulator detection. To achieve a good trade-off among accuracy, running time, and memory storage, this work proposes the modified YOLO-tiny for insulator (MTI-YOLO) network for insulator detection in complex aerial images. First of all, composite insulator images are collected in common scenes and the “CCIN_detection” (Chinese Composite INsulator) dataset is constructed. Secondly, to improve the detection accuracy of different sizes of insulator, multi-scale feature detection headers, a structure of multi-scale feature fusion, and the spatial pyramid pooling (SPP) model are adopted to the MTI-YOLO network. Finally, the proposed MTI-YOLO network and the compared networks are trained and tested on the “CCIN_detection” dataset. The average precision (AP) of our proposed network is 17% and 9% higher than YOLO-tiny and YOLO-v2. Compared with YOLO-tiny and YOLO-v2, the running time of the proposed network is slightly higher. Furthermore, the memory usage of the proposed network is 25.6% and 38.9% lower than YOLO-v2 and YOLO-v3, respectively. Experimental results and analysis validate that the proposed network achieves good performance in both complex backgrounds and bright illumination conditions.

https://www.mdpi.com/1996-1073/14/5/1426/pdf

MTI-YOLO: A Light-Weight and Real-Time Deep Neural Network for Insulator Detection in Complex Aerial Images

The vision-based detection of cap missing on insulator in aerial images is an extremely challenging task. Previous approaches have achieved promising performances. However, most of them include two stages of insulator localization and cap detection, which require large-scale insulator and cap annotations. In this article, we propose a cap-count guided weakly supervised approach, which only needs insulator bounding box annotations. The proposed method first generates cap annotations automatically by giving the insulator bounding boxes and the number of caps. Then, we use a deep learning model to detect insulator strings and caps simultaneously. Finally, we design an efficient cap missing detection strategy by using caps geometric constraints to measure the position of caps. We evaluate the proposed approach on our collected large-scale aerial image dataset. The experimental results show that the proposed method can accurately detect the insulator strings and caps with any angle from an aerial image and further recognize the missing cap on insulator. The precision and recall reach 92.86% and 86.67% respectively, which achieves competitive detection results.

Cap-Count Guided Weakly Supervised Insulator Cap Missing Detection in Aerial Images

Insulators are exerting an important influence in transmission lines. The timely detection of insulator explosion defects is an important guarantee for the safe operation of power systems. This paper puts forward an algorithm that detect the insulators' self-detonation defect based on deep learning. First, a Faster R-CNN target detection network is used to quickly classify and locate the insulators on the transmission lines. Then, a semantic segmentation to the located insulators is carried out by constructing a full convolutions neural network. In the end, the finished insulator image is input into the classification network to judge whether the insulator is burst. The experimental results show that the accuracy of insulator fault explosion recognition based on deep learning reaches more than 99%, and the intelligent design effectively improves the efficiency of the power transmission system.

Jun Xue

Papers

Detection and Recognition for Fault Insulator Based on Deep Learning