InsuDet: A Fault Detection Method for Insulators of Overhead Transmission Lines Using Convolutional Neural Networks

Zhang, Xingtuo; Zhang, Yiyi; Liu, Jiefeng; Zhang, Chaohai; Xue, Xueyue; Zhang, Heng; Zhang, Wei

doi:10.1109/tim.2021.3120796

Cited by 61 publications

(25 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The network contains a new batch normalization convolutional block attention module (BN-CBAM) and a feature fusion network. Zhang et al 22 improved YOLOv3 and proposed the new network called InsuNet. Inspired by the densely connected network, the InsuNet introduces the densely connected idea into the feature pyramid network, which can transfer semantic information from the high level to the low level easily and hence improved the detection performance.…”

Section: Related Work 21 Insulator Defects Detectionmentioning

confidence: 99%

“…Hou et al 8 proposed the coordinate attention for mobile networks which outperforms other attention mechanism in 2021.…”

Section: Coordinate Attention In Improved Yolov7mentioning

confidence: 99%

“…Methods based on deep learning techniques have a better performance when compared with traditional ways, for they can get the features automatically. Zhang et al 8 designed the densely connected FPN to substitute the original FPN of YOLOv3 network, in which semantic information and localization information are enhanced to get a better result. Gao et al 9 refined the Faster RCNN network by adding the BN-CBAM into the backbone and concatenating three-level features in its feature fusion module.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Detection of insulator defects based on improved YOLOv7 model

Xia

Luo²,

Zhang³

et al. 2022

International Symposium on Artificial Intelligence and Robotics 2022

View full text Add to dashboard Cite

Inspection for the electric transmission system has great significance for powerline maintenance, in which defects of insulators are needed to be found in time to preserve the safety of the whole system. To improve the accuracy and efficiency of insulator defect detection, computer vision techniques are employed. However, since insulator defects on the insulator strings are small objects and usually works in complex environment, it is challenging to get satisfactory detection results. In order to solve this issue, we proposed an insulator defect detection method based on YOLOv7 which is one of the state-of-the-art object detection methods. By introducing coordinate attention mechanism into the backbone network and redesigning the feature pyramid network (FPN) to have bi-directional FPN like structure, we successfully adapt the original model to the insulator defect detection task. We used an open-source dataset called CPLID to train our model. Experiments demonstrate that our method achieve good performance for insulator defect detection and have better average precision comparing with other methods. Ablation study were also designed to verify the effectiveness of the improved component.

show abstract

Section: Related Work 21 Insulator Defects Detectionmentioning

confidence: 99%

“…Hou et al 8 proposed the coordinate attention for mobile networks which outperforms other attention mechanism in 2021.…”

Section: Coordinate Attention In Improved Yolov7mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Detection of insulator defects based on improved YOLOv7 model

Xia

Luo²,

Zhang³

et al. 2022

International Symposium on Artificial Intelligence and Robotics 2022

View full text Add to dashboard Cite

show abstract

“…Ref. [ 18 ] proposed an improved YOLOv3-based insulator detection with a new feature pyramid network, which had high detection accuracy for insulator defects. However, the network could not learn independently.…”

Section: Introductionmentioning

confidence: 99%

Research on Insulator Defect Detection Based on an Improved MobilenetV1-YOLOv4

Deng

Huang

et al. 2022

Entropy

View full text Add to dashboard Cite

Insulator devices are important for transmission lines, and defects such as insulator bursting and string loss affect the safety of transmission lines. In this study, we aim to investigate the problems of slow detection speed and low efficiency of traditional insulator defect detection algorithms, and to improve the accuracy of insulator fault identification and the convenience of daily work; therefore, we propose an insulator defect detection algorithm based on an improved MobilenetV1-YOLOv4. First, the backbone feature extraction network of YOLOv4 ‘Backbone’ is replaced with the lightweight module Mobilenet-V1. Second, the scSE attention mechanism is introduced in stages of preliminary feature extraction and enhanced feature extraction, sequentially. Finally, the depthwise separable convolution substitutes the 3 × 3 convolution of the enhanced feature extraction network to reduce the overall number of network parameters. The experimental results show that the weight of the improved algorithm is 57.9 MB, which is 62.6% less than that obtained by the MobilenetV1-YOLOv4 model; the average accuracy of insulator defect detection is improved by 0.26% and reaches 98.81%; and the detection speed reaches 190 frames per second with an increase of 37 frames per second.

show abstract

“…She [23] proposed a multiscale residual neural network for insulator surface damage identification, using three convolution kernels of different sizes to perform convolution filtering and feature map fusion to enrich the spatial correlation and channel correlation of feature maps. Aiming at the small proportion of the insulator umbrella disc shedding fault area in the entire image and the difficulty in detection, Zahng [24] introduced the densely connected feature pyramid network into the YOLOV3 [25] model to achieve high detection accuracy. Zhao [26] combined Faster R-CNN [27] and an improved FPN [28] to detect two types of insulator defects.…”

Section: Introductionmentioning

confidence: 99%

Insulator Umbrella Disc Shedding Detection in Foggy Weather

Rui

Chen

et al. 2022

Sensors

View full text Add to dashboard Cite

The detection of insulator umbrella disc shedding is very important to the stable operation of a transmission line. In order to accomplish the accurate detection of the insulator umbrella disc shedding in foggy weather, a two-stage detection model combined with a defogging algorithm is proposed. In the dehazing stage of insulator images, solving the problem of real hazy image data is difficult; the foggy images are dehazed by the method of synthetic foggy images training and real foggy images fine-tuning. In the detection stage of umbrella disc shedding, a small object detection algorithm named FA-SSD is proposed to solve the problem of the umbrella disc shedding occupying only a small proportion of an aerial image. On the one hand, the shallow feature information and deep feature information are fused to improve the feature extraction ability of small targets; on the other hand, the attention mechanism is introduced to strengthen the feature extraction network’s attention to the details of small targets and improve the model’s ability to detect the umbrella disc shedding. The experimental results show that our model can accurately detect the insulator umbrella disc shedding defect in the foggy image; the accuracy of the defect detection is 0.925, and the recall is 0.841. Compared with the original model, it improved by 5.9% and 8.6%, respectively.

show abstract

InsuDet: A Fault Detection Method for Insulators of Overhead Transmission Lines Using Convolutional Neural Networks

Cited by 61 publications

References 32 publications

Detection of insulator defects based on improved YOLOv7 model

Detection of insulator defects based on improved YOLOv7 model

Research on Insulator Defect Detection Based on an Improved MobilenetV1-YOLOv4

Insulator Umbrella Disc Shedding Detection in Foggy Weather

Contact Info

Product

Resources

About