Autonomous Diagnosis of Overheating Defects in Cable Accessories Based on Faster RCNN and Mean-Shift Algorithm

Xü, Xinsheng; Zhou, Chengke; Zhou, Wenjun; Liao, Yanqun; Wei, Yilong; Yuan, Jing

doi:10.1109/ichve49031.2020.9280056

Cited by 7 publications

(5 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This paper is an extension of a conference paper, which the authors previously published [25]. It proposed an autonomous method to analyze infrared images for the diagnosis of insulation conditions of cable accessories.…”

Section: Discussionmentioning

confidence: 99%

“…The K-Means algorithm randomly selected k pixels as clustering centers according to the given k, and then classified the remaining pixels to the most similar center before it updated the Energies 2021, 14, 4316 9 of 15 clustering centers to the mean value of each category. The above steps were repeated until the convergence condition is satisfied [24,25].…”

Section: Extraction Of Suspected Abnormal Heating Regions Based On Mean-shift Algorithmmentioning

confidence: 99%

See 1 more Smart Citation

Autonomous Analysis of Infrared Images for Condition Diagnosis of HV Cable Accessories

Mu¹,

Xü

Xia³

et al. 2021

Energies

Self Cite

View full text Add to dashboard Cite

Infrared thermography has been used as a key means for the identification of overheating defects in power cable accessories. At present, analysis of thermal imaging pictures relies on human visual inspections, which is time-consuming and laborious and requires engineering expertise. In order to realize intelligent, autonomous recognition of infrared images taken from electrical equipment, previous studies reported preliminary work in preprocessing of infrared images and in the extraction of key feature parameters, which were then used to train neural networks. However, the key features required manual selection, and previous reports showed no practical implementations. In this contribution, an autonomous diagnosis method, which is based on the Faster RCNN network and the Mean-Shift algorithm, is proposed. Firstly, the Faster RCNN network is trained to implement the autonomous identification and positioning of the objects to be diagnosed in the infrared images. Then, the Mean-Shift algorithm is used for image segmentation to extract the area of overheating. Next, the parameters determining the temperature of the overheating parts of cable accessories are calculated, based on which the diagnosis are then made by following the relevant cable condition assessment criteria. Case studies are carried out in the paper, and results show that the cable accessories and their overheating regions can be located and assessed at different camera angles and under various background conditions via the autonomous processing and diagnosis methods proposed in the paper.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Extraction Of Suspected Abnormal Heating Regions Based On Mean-shift Algorithmmentioning

confidence: 99%

Autonomous Analysis of Infrared Images for Condition Diagnosis of HV Cable Accessories

Mu¹,

Xü

Xia³

et al. 2021

Energies

Self Cite

View full text Add to dashboard Cite

show abstract

“…Given the high computational cost of processing a large number of IR images, machine learning techniques have been employed to automatically extract informative features from the original images and use the extracted features as the input of the neural network to achieve an intelligent diagnosis of equipment. For example, an automatic diagnosis method of cable defects was proposed, which used faster regions with convolutional neural network features and Mean-Shift to accurately locate the overheating region under various shooting angles and backgrounds, and subsequently, achieved automatic diagnosis of overheating defects [68]. In addition, deep learning algorithms were also applied to process a large volume of IR thermal images and identify the fault location of electrical equipment [69].…”

Section: Infrared Detectionmentioning

confidence: 99%

Review of condition monitoring and defect inspection methods for composited cable terminals

Cao

et al. 2023

High Voltage

View full text Add to dashboard Cite

Composited cable terminals are critical for reliable power delivery of traditional and traction power supply systems. During its operation, the cable terminal continually undergoes complex circumstances where humidity, temperature, field strength, mechanical stress and other factors continuously change at different levels. In extreme cases, defects or even failures may occur in the cable terminals, leading to catastrophic accidents. This makes the condition monitoring and defect detection of composited cable terminals become an imperative need for the power industry. The “state‐of‐the‐art” technology of cable terminal condition assessment is focussed and a systematic review of the current research progress of cable terminal condition assessment from the operation circumstances to failure mechanisms is provided. It covers both online/offline condition monitoring methods and defects detection approaches. In addition, challenges and future research directions for cable terminal condition assessment are also addressed. It is concluded that the non‐destructive and non‐intrusive methods like terahertz imaging and ultrasonic testing, and multi‐source information fusion methods as well as the digital twin technology have been gaining popularity for cable terminal defect inspection. It is expected the presented work can provide a global field of vision for further advancement of both scholars and industrial engineers in this field.

show abstract

“…Nowadays, the target detection algorithm of traditional machine learning algorithm has many problems and failure to meet timeliness requirements when testing equipment; the benefits of deep learning based target detection algorithms such as high recognition accuracy, recognition speed and robustness have led to traditional target detection algorithms being gradually replaced by deep learning target detection algorithms [3] . In the literature [4] , a Faster-RCNN-based algorithm for rock thermal infrared image tension-shear crack detection was proposed, which improved the ability of the model for feature extraction by introducing an attention-guided feature pyramid network to optimize the features. In the literature [5] , a YOLOv4-based algorithm is proposed to improve the detection accuracy by introducing a multiscale convolution module with data enhancement of infrared images of power equipment.…”

Section: Introductionmentioning

confidence: 99%

Research on infrared insulator image recognition based on improved YOLOv5

Lang,

Ji,

Xie

et al. 2023

Third International Conference on Advanced Algorithms and Neural Networks (AANN 2023)

View full text Add to dashboard Cite

As the scale of transmission lines is expanding, the safety of transmission line operation is getting more and more attention; insulators as an important component of transmission lines, the use of insulators greatly affects the safe operation of transmission lines. The traditional depth recognition algorithm can not achieve effective recognition of infrared images, in order to achieve rapid recognition of insulators in complex environments, this paper proposes the recognition of infrared insulator images based on the improved YOLOv5 depth neural network detection algorithm. Firstly, Ghost convolution was introduced into the backbone network to speed up detection and network lightweighting; secondly, to enhance the multi-scale convergence of networks, improved GAM attention module added behind the neck network; in addition, the network introduces an EIOU loss function for convergence; finally, validation of this improved algorithm with the collected infrared insulator dataset. The results show that the improved algorithm in this paper achieves 91.2% accuracy and 92.1% mAP on the infrared insulator dataset, which improves 2.3% and 4.1% compared with the test results of YOLOv5 model, simultaneous detection speed up to 91 FPS, which meets the real-time requirement.

show abstract

Autonomous Diagnosis of Overheating Defects in Cable Accessories Based on Faster RCNN and Mean-Shift Algorithm

Cited by 7 publications

References 6 publications

Autonomous Analysis of Infrared Images for Condition Diagnosis of HV Cable Accessories

Autonomous Analysis of Infrared Images for Condition Diagnosis of HV Cable Accessories

Review of condition monitoring and defect inspection methods for composited cable terminals

Research on infrared insulator image recognition based on improved YOLOv5

Contact Info

Product

Resources

About