Power Line-Guided Automatic Electric Transmission Line Inspection System

Xu, Chang; Li, Qingwu; Zhou, Qingkai; Zhang, Shan; Yu, Dabing; Ma, Yunpeng

doi:10.1109/tim.2022.3169555

Cited by 51 publications

(21 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…3b, the rotor wing UAV has the following advantages: easy operation, simple structure and low cost. [20][21][22][23] It usually uses wireless signals for real-time control, and can be suspended in the air. But the disadvantage is that such drones generally y slowly, lack endurance and can only be used for inspection of speci c parts.…”

Section: Airspace Patrolmentioning

confidence: 99%

Research on vision-based UAV power line detection technology

Wang

2023

Preprint

View full text Add to dashboard Cite

In order to ensure the reliability and safety of the power grid operation, the power company will carry out regular inspection of the transmission line network. The traditional inspection method is generally manual inspection by foot patrol, which is not only slow but also time-consuming and laborious. In recent years, with the development of unmanned aerial vehicle(UAV) and unmanned vehicle control technology and the improvement of inspection accuracy, UAV technology has been widely used in the intelligent inspection of power grid. In order to ensure the reliability and safety of power grid operation in the complex and huge power grid system, in order to find the fault of transmission line as soon as possible and give feedback, The UAV detection technology with image recognition technology has become an urgent need for the development of power system. The vision-based UAV power line detection technology has a wide range of application prospects. In this paper, the relevant literature in recent years is reviewed extensively, and the status quo of vi-sion-based UAV detection technology is reviewed. This paper summarizes the existing power line detection methods, the system structure of UAV power line detection and the image recognition technology of data acquisition, and focuses on the development of transmission line data processing technology based on deep learning, in order to provide a starting point for researchers to develop automatic autonomous intelligent inspection of transmission line system. Finally, the development of this field and the next possible challenges are discussed, and the future is prospected.

show abstract

Section: Airspace Patrolmentioning

confidence: 99%

Research on vision-based UAV power line detection technology

Wang

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…The UAVs with LiDAR are used for the intelligent detection of power lines [6]. The UAV system is equipped with an advanced embedded processor and binocular vision sensor to realize automatic detection of transmission lines through real-time generated guidance information [7]. Transmission line image data is collected by UAV, and automatic detection is performed by deep learning target detection network [8].…”

Section: Related Workmentioning

confidence: 99%

Live line strain clamp's DR image anomaly detection based on unsupervised learning

Haoliang

Jia

Yuting

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Due to the high‐risk working environment of high‐voltage transmission lines, defect samples of strain clamps cannot be fully and completely collected. As a result, the deep learning method based on defect sample tags cannot effectively identify all abnormalities. To solve this problem, an unsupervised anomaly detection method based on knowledge distillation is proposed, which only requires a small number of normal samples to drive the model for anomaly detection. ResNet is the framework of the teacherstudent model, and the feature activation layer after ResBlock is used for knowledge transfer. Residual‐assisted attention and pyramid‐splitting attention were used to enhance the spatial perception and multi‐scale information utilization ability of the model. This model only transmits the information of normal samples and is sensitive to abnormal samples. The proposed model outperformed the baseline by 23% and individual categories by 78% on the MVTec AD (Anomaly Detection Dataset) and outperformed the baseline by 45% and individual categories by 10% on the CIFAR10 and is also reliable for Mnist and Fashion Mnist. This method performs best (82.71%) over the existing method on the self‐built data set.

show abstract

“…Yang et al [14] offers a three-stage cascade system based on the yolov4 framework, which includes a fastener location network, feature refinement network, and defects diagnosis network. In [15], a convolutional neural network is proposed for power line detection, which can extract supplementary information from multi-scale features with multiple directions. The test results of various stages are finally fused to improve the robustness of the model.…”

Section: Introductionmentioning

confidence: 99%

An improved cascade RCNN detection method for key components and defects of transmission lines

Dong,

Zhang,

Xie

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Overhead transmission line detection based on deep learning of aerial images taken by UAVs has been widely investigated. Despite its success, it is limited by several factors, including inappropriate evaluation criteria and dramatic scaling of components in the images. To mitigate these issues, a relative mean Average Precision evaluation index is proposed to accurately measure the model's detection performance for smaller objects. A data enhancement strategy including multi‐scale transformation is adopted to alleviate the problem of drastic scaling. The existing Cascade RCNN target detection technology is enhanced by incorporating Swin‐v2 and a balanced feature pyramid to improve feature characterization capabilities, while side‐aware boundary localization is utilized to improve the positioning accuracy of the model. Experimental results demonstrate that the proposed method outperforms state‐of‐the‐art methods on CPLID and achieves 7.8%, 11.8%, and 5.5% higher detection accuracy than the baseline for mAP50, relative small and medium mAP, respectively. Additionally, the paper discusses the influence of adopted data enhancement on the robustness of the model.

show abstract

Power Line-Guided Automatic Electric Transmission Line Inspection System

Cited by 51 publications

References 68 publications

Research on vision-based UAV power line detection technology

Research on vision-based UAV power line detection technology

Live line strain clamp's DR image anomaly detection based on unsupervised learning

An improved cascade RCNN detection method for key components and defects of transmission lines

Contact Info

Product

Resources

About