A New Multilabel Recognition Framework for Transmission Lines Bolt Defects Based on the Combination of Semantic Knowledge and Structural Knowledge

Zhao, Zhenbing; Wang, Rui; Li, Yanxu; Zhai, Yongjie; Zhao, Wenqing; Zhang, Ke

doi:10.1109/tim.2022.3200103

Cited by 4 publications

(5 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In [12], a context-based graph reasoning model considering the characteristics of a hardware link structure is proposed using the network detection architecture of Faster R-CNN to improve the detection accuracy of 14 kinds of hardware on overhead transmission lines. In [13], a multilabel image recognition framework for bolt defects composed of VFSKnet, which can learn the relationship between bolt labels, and VFP-Knet, which can capture fine-grained structural features, is proposed to solve the classification problem of bolt defect images. 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.…”

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

Self Cite

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

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

Self Cite

View full text Add to dashboard Cite

show abstract

“…Zhao et al. [18]. put forward a method for identifying missing bolts based on graph knowledge reasoning that leverages a knowledge expression module for learning bolt features and mining correlations between bolt types to enable missing bolt identification.…”

Section: Introductionmentioning

confidence: 99%

“…This approach learns the interrelationships of components and integrates them into a detection model to enhance its performance. Zhao et al [18]. put forward a method for identifying missing bolts based on graph knowledge reasoning that leverages a knowledge expression module for learning bolt features and mining correlations between bolt types to enable missing bolt identification.…”

Section: Introductionmentioning

confidence: 99%

Bird's nest defect detection of transmission lines based on domain knowledge and occlusion reasoning

Dong,

Zhang,

Chen

et al. 2023

IET Generation Trans & Dist

View full text Add to dashboard Cite

Bird's nest defect is an important cause of transmission line faults. To achieve accurate detection of bird nest defects in complex scenarios, a bird nest defect detection model for transmission lines was proposed that combines domain knowledge and occlusion reasoning networks. On the one hand, the model utilized the domain knowledge of the location of the bird's nest, using edge detection to obtain tower area information to constrain the location of candidate frames. This helps to reduce the false detection caused by complex backgrounds. On the other hand, on the basis of analyzing the occlusion characteristics of bird nests, the model employed occlusion reasoning networks that randomly erase features at the feature level to simulate the occlusion of bird nests in real scenes and improve the model's detection capability for occluded targets. Additionally, a multi‐scale feature fusion algorithm was designed in this paper to adapt the model to the scale variations of bird nests in aerial images. Experimental results demonstrate that the model outperforms advanced target detection models and other bird nest defect detection methods, with an AP50 of 78.8% and an AR10 of 72.4% for defect detection.

show abstract

“…Unmanned aerial vehicles, commonly referred to as drones, provide an efficient solution to inspecting hard-to-reach structures such as bridges and wind turbines. [1][2][3][4] In addition, when combined with sensing technologies and techniques such as ultrasonics, [5][6][7][8] LiDAR, [9][10][11] and image recognition, [12][13][14][15][16][17][18][19][20][21][22] they can increase the accuracy and effectiveness of infrastructure assessments.…”

mentioning

confidence: 99%

“…Recently, inspection methods have incorporated drones and image recognition technologies. [17][18][19][20][21][22] Although these advances are effective in identifying missing parts and obvious signs of bolt loosening or corrosion, it remains difficult to identify bolts with reduced axial force. This is primarily because subtle changes in axial force often do not manifest as notable visual changes that can be captured by cameras.…”

mentioning

confidence: 99%

Displacement amplification mechanism in passive capacitive bolt axial force sensors to suppress manufacturing variations

Hasebe,

Nakamura

2024

Jpn. J. Appl. Phys.

View full text Add to dashboard Cite

We present a method of minimizing manufacturing variations in passive capacitive sensors for noncontact bolt inspection using a displacement amplification mechanism. This inspection mechanism uses electromagnetic coupling to eliminate the need for contact, making it particularly suitable for inspections using unmanned aerial vehicles. Analysis by the finite element method and prototype testing verified the capability of the mechanism to amplify displacement changes due to axial force. The prototype exhibited an 80% increase in displacement relative to the bolt head, effectively halving variation effects. Despite the design challenges, the mechanism significantly improved the effectiveness of the sensor.

show abstract

A New Multilabel Recognition Framework for Transmission Lines Bolt Defects Based on the Combination of Semantic Knowledge and Structural Knowledge

Cited by 4 publications

References 22 publications

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

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

Bird's nest defect detection of transmission lines based on domain knowledge and occlusion reasoning

Displacement amplification mechanism in passive capacitive bolt axial force sensors to suppress manufacturing variations

Contact Info

Product

Resources

About