Component identification and defect detection in transmission lines based on deep learning

2020 ◽  
pp. 1-12
Author(s):  
Xiangyu Zheng ◽  
Rong Jia ◽  
Aisikaer ◽  
Linling Gong ◽  
Guangru Zhang ◽  
...  
Keyword(s):  
Deep Learning ◽  
Transmission Line ◽  
Defect Detection ◽  
Transmission Lines ◽  
Power Grid ◽  
Recognition Rate ◽  
Experimental Results ◽  
Component Identification ◽  
Special Power ◽  
Component Failures

Ensuring the stable and safe operation of the power system is an important work of the national power grid companies. The power grid company has established a special power inspection department to troubleshoot transmission line components and replace faulty components in a timely manner. At present, assisted manual inspection by drone inspection has become a trend of power line inspection. Automatically identifying component failures from images of UAV aerial transmission lines is a cutting-edge cross-cutting issue. Based on the above problems, the purpose of this article is to study the component identification and defect detection of transmission lines based on deep learning. This paper expands the dataset by adjusting the size of the convolution kernel of the CNN model and the rotation transformation of the image. The experimental results show that both methods can effectively improve the effectiveness and reliability of component identification and defect detection in transmission line inspection. The recognition and classification experiments were performed using the images collected by the drone. The experimental results show that the effectiveness and reliability of the deep learning method in the identification and defect detection of high-voltage transmission line components are very high. Faster R-CNN performs component identification and defect detection. The detection can reach a recognition speed of nearly 0.17 s per sheet, the recognition rate of the pressure-equalizing ring can reach 96.8%, and the mAP can reach 93.72%.

scholarly journals Image Enhanced Mask R-CNN: A Deep Learning Pipeline with New Evaluation Measures for Wind Turbine Blade Defect Detection and Classification

2021 ◽  
Vol 7 (3) ◽  
pp. 46
Author(s):  
Jiajun Zhang ◽  
Georgina Cosma ◽  
Jason Watkins
Keyword(s):  
Deep Learning ◽  
Wind Turbine ◽  
Turbine Blade ◽  
Defect Detection ◽  
Recognition Rate ◽  
Weighted Average ◽  
Wind Turbine Blade ◽  
Evaluation Measures ◽  
Augmentation Techniques ◽  
The Mean

Demand for wind power has grown, and this has increased wind turbine blade (WTB) inspections and defect repairs. This paper empirically investigates the performance of state-of-the-art deep learning algorithms, namely, YOLOv3, YOLOv4, and Mask R-CNN for detecting and classifying defects by type. The paper proposes new performance evaluation measures suitable for defect detection tasks, and these are: Prediction Box Accuracy, Recognition Rate, and False Label Rate. Experiments were carried out using a dataset, provided by the industrial partner, that contains images from WTB inspections. Three variations of the dataset were constructed using different image augmentation settings. Results of the experiments revealed that on average, across all proposed evaluation measures, Mask R-CNN outperformed all other algorithms when transformation-based augmentations (i.e., rotation and flipping) were applied. In particular, when using the best dataset, the mean Weighted Average (mWA) values (i.e., mWA is the average of the proposed measures) achieved were: Mask R-CNN: 86.74%, YOLOv3: 70.08%, and YOLOv4: 78.28%. The paper also proposes a new defect detection pipeline, called Image Enhanced Mask R-CNN (IE Mask R-CNN), that includes the best combination of image enhancement and augmentation techniques for pre-processing the dataset, and a Mask R-CNN model tuned for the task of WTB defect detection and classification.

scholarly journals Real-Time Vehicle Make and Model Recognition with the Residual SqueezeNet Architecture

Sensors ◽  
2019 ◽  
Vol 19 (5) ◽  
pp. 982 ◽  
Author(s):  
Hyo Lee ◽  
Ihsan Ullah ◽  
Weiguo Wan ◽  
Yongbin Gao ◽  
Zhijun Fang
Keyword(s):  
Deep Learning ◽  
Real Time ◽  
Large Scale ◽  
Recognition Rate ◽  
Experimental Results ◽  
Learning Approach ◽  
Deep Model ◽  
Proposed Model ◽  
Real Time Applications ◽  
Model Recognition

Make and model recognition (MMR) of vehicles plays an important role in automatic vision-based systems. This paper proposes a novel deep learning approach for MMR using the SqueezeNet architecture. The frontal views of vehicle images are first extracted and fed into a deep network for training and testing. The SqueezeNet architecture with bypass connections between the Fire modules, a variant of the vanilla SqueezeNet, is employed for this study, which makes our MMR system more efficient. The experimental results on our collected large-scale vehicle datasets indicate that the proposed model achieves 96.3% recognition rate at the rank-1 level with an economical time slice of 108.8 ms. For inference tasks, the deployed deep model requires less than 5 MB of space and thus has a great viability in real-time applications.

scholarly journals Imbalance Modelling for Defect Detection in Ceramic Substrate by Using Convolutional Neural Network

Processes ◽  
2021 ◽  
Vol 9 (9) ◽  
pp. 1678
Author(s):  
Yo-Ping Huang ◽  
Chun-Ming Su ◽  
Haobijam Basanta ◽  
Yau-Liang Tsai
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Unsupervised Learning ◽  
Defect Detection ◽  
Ceramic Substrate ◽  
Experimental Results ◽  
Ceramic Substrates

The complexity of defect detection in a ceramic substrate causes interclass and intraclass imbalance problems. Identifying flaws in ceramic substrates has traditionally relied on aberrant material occurrences and characteristic quantities. However, defect substrates in ceramic are typically small and have a wide variety of defect distributions, thereby making defect detection more challenging and difficult. Thus, we propose a method for defect detection based on unsupervised learning and deep learning. First, the proposed method conducts K-means clustering for grouping instances according to their inherent complex characteristics. Second, the distribution of rarely occurring instances is balanced by using augmentation filters. Finally, a convolutional neural network is trained by using the balanced dataset. The effectiveness of the proposed method was validated by comparing the results with those of other methods. Experimental results show that the proposed method outperforms other methods.

scholarly journals Detection method based on improved faster R-CNN for pin defect in transmission lines

2021 ◽  
Vol 300 ◽  
pp. 01011
Author(s):  
Jun Wu ◽  
Sheng Cheng ◽  
Shangzhi Pan ◽  
Wei Xin ◽  
Liangjun Bai ◽  
...  
Keyword(s):  
Transmission Line ◽  
Defect Detection ◽  
Transmission Lines ◽  
False Positive Rate ◽  
Detection Algorithm ◽  
Detection Model ◽  
Positive Rate ◽  
Aerial Vehicle ◽  
The Stability ◽  
Small Targets

Defects such as insulator, pins, and counterweight in highvoltage transmission lines affect the stability of the power system. The small targets such as pins in the unmanned aerial vehicle (UAV) inspection images of transmission lines occupy a small proportion in the images and the characteristic representations are poor which results a low defect detection rate and a high false positive rate. This paper proposed a transmission line pin defect detection algorithm based on improved Faster R-CNN. First, the pre-training weights with higher matching degree are obtained based on transfer learning. And it is applied to construct defect detection model. Then, the regional proposal network is used to extract features in the model. The results of defect detection are obtained by regression calculation and classification of regional characteristics. The experimental results show that the accuracy of the pin defect detection of the transmission line reaches 81.25%

scholarly journals Application of Data-Driven Iterative Learning Algorithm in Transmission Line Defect Detection

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yuquan Chen ◽  
Hongxing Wang ◽  
Jie Shen ◽  
Xingwei Zhang ◽  
Xiaowei Gao
Keyword(s):  
Deep Learning ◽  
Transmission Line ◽  
Target Detection ◽  
Defect Detection ◽  
Learning Algorithm ◽  
Small Sample ◽  
Iterative Learning ◽  
Data Driven ◽  
Learning Technology ◽  
Line Defect

Deep learning technology has received extensive consideration in recent years, and its application value in target detection is also increasing day by day. In order to accelerate the practical process of deep learning technology in electric transmission line defect detection, the current work used the improved Faster R-CNN algorithm to achieve data-driven iterative training and defect detection functions for typical transmission line defect targets. Based on Faster R-CNN, we proposed an improved network that combines deformable convolution and feature pyramid modules and combined it with a data-driven iterative learning algorithm; it achieves extremely automated and intelligent transmission line defect target detection, forming an intelligent closed-loop image processing. The experimental results show that the increase of the recognition of improved Faster R-CNN network combined with data-driven iterative learning algorithm for the pin defect target is 31.7% more than Faster R-CNN. In the future, the proposed method can quickly improve the accuracy of transmission line defect target detection in a small sample and save manpower. It also provides some theoretical guidance for the practical work of transmission line defect target detection.

scholarly journals Modeling and Analysis of Progressive Ice Shedding along a Transmission Line during Thermal De-Icing

2019 ◽  
Vol 2019 ◽  
pp. 1-12 ◽  
Author(s):  
Yunyun Xie ◽  
Linyan Huang ◽  
Da Wang ◽  
Huaiping Ding ◽  
Xiaochun Yin
Keyword(s):  
Dynamic Response ◽  
Transmission Line ◽  
Transmission Lines ◽  
Dynamic Equilibrium ◽  
Propagation Speed ◽  
Experimental Results ◽  
Small Scale ◽  
Equilibrium Equations ◽  
Modeling And Analysis ◽  
Ice Shedding

Progressive ice shedding (PIS) along transmission lines is a common type of ice shedding during thermal de-icing that requires investigation to ensure the security of transmission lines. In current research, PIS is commonly analyzed using a constant speed for ice detaching from the conductor, which is not accurate for PIS simulation. Therefore, a mechanical model of PIS is established in this study to analyze PIS during thermal de-icing. First, an ice detachment model during thermal de-icing is built to determine the detachment times of the initial ice and remaining ice. Then, a two-node isoparametric truss element is employed to derive the static and dynamic equilibrium equations of an iced conductor to simulate the dynamic response of PIS. Relative to commercial software, these equations can easily accommodate the changing mass of ice with the flow of melted water. The dynamic equilibrium equations are then solved using the ice detachment model to obtain the dynamic response of PIS. Finally, small-scale and full-scale experimental results are employed to verify the proposed method. The simulation results show that the results of the proposed method are more consistent with the experimental results than are the results of existing methods that assume a constant propagation speed. The proposed method can be further applied to optimize transmission line designs and evaluate the application of thermal de-icing devices.

Analysis on Capacity of Transmission Line Based on Thermal Rating

2014 ◽  
Vol 986-987 ◽  
pp. 239-242
Author(s):  
Bo Yang ◽  
Kui Hua Wu ◽  
Yi Qun Wang ◽  
Shen Quan Yang
Keyword(s):  
Transmission Line ◽  
Real Time ◽  
Transmission Lines ◽  
Rapid Growth ◽  
Power Grid ◽  
Transmission Capacity ◽  
Grid Load ◽  
Realistic Significance

The rapid growth of power grid load put forward higher requirements on the transmission capacity of line, with the growing tension of line corridors, building new transmission lines is becoming more and more difficult. Therefore, it is of realistic significance to analyze the transmission capacity of existing transmission line and fully tap the existing power grid transmission capacity. On the basis of previous studies, and consulting a large number of references, this paper summarizes and expounds the methods of improving transmission capacity by using the thermal rating analysis, introducing static thermal rating and real-time static thermal rating. Also, this paper verifies applications of the above methods in actual running environment.

scholarly journals Monitoring Method of Transmission Line Breaking Prevention Based on Deep Learning

2021 ◽  
Vol 252 ◽  
pp. 01024
Author(s):  
Jiang Yan ◽  
Li Qiang ◽  
Wang Guanyao ◽  
Wang Ben ◽  
Deng Wei
Keyword(s):  
Deep Learning ◽  
Transmission Line ◽  
Transmission Lines ◽  
Rapid Development ◽  
Video Data ◽  
Data Sets ◽  
Monitoring Method ◽  
Monitoring Model ◽  
Public Data ◽  
3D Cnn

With the rapid development of the national economy, the national power consumption level continues to increase, which puts forward higher requirements on the power supply guarantee capacity of the power grid system. The distribution range of the transmission line is wide and densely, most lines are exposed to the unguarded field without any shielding or protective measures, which are vulnerable to man-made destruction or natural disasters. Therefore, it is very important for the early monitoring and prevention of the external force breaking of the transmission lines. The method for preventing external breakage of transmission lines based on deep learning proposed in this paper utilizes the video data collected by the cameras erected on the transmission line roads to perform feature extraction and learning through 3D CNN and LSTM networks, and obtains a monitoring model for external breakage prevention of transmission lines. The model was tested on public data sets and verified that it has a good performance in the field of transmission lines against external damage. The method in this paper makes full use of the existing video acquisition equipment, and the process does not require human intervention, which greatly reduces the cost of line monitoring and the hidden dangers of accidents.

scholarly journals Identification of line status changes using phasor measurements through deep learning networks

2021 ◽  
Vol 22 (6) ◽  
pp. 55-67
Author(s):  
N. E. Gotman ◽  
G. P. Shumilova
Keyword(s):  
Deep Learning ◽  
Transmission Lines ◽  
Power Grid ◽  
Measurement Data ◽  
Transient State ◽  
Test System ◽  
Learning Networks ◽  
Status Change ◽  
Grid Topology ◽  
High Level

THE PURPOSE. To consider the problem of detecting changes in a power grid topology that occurs as a result of the power line outage / turning on. Develop the algorithm for detecting changes in the status of transmission lines in real time by using voltage and current phasors captured by phasor measurement units (PMUs) are placed on buses. Carry out experimental research on IEEE 14-bus test system. METHODS. This paper proposes a method from the field of artificial intelligence such as machine learning in particular "Deep Learning" to solve the problem. Deep Learning arises as a computational learning technique in which high level abstractions are hierarchically modelled from raw data. One of the means to effectively extract the inherent hidden features in data are Convolutional Neural Networks (CNNs). RESULTS. The article describes the topic relevance, offers to apply the method for detecting status of lines using a CNN classifier. The combination of different CNN architectures and the number of time slices from the moment of line status change are used to detect the power grid topology. The effectiveness of the joint use of PMUs and CNN in solving this problem has been proven. CONCLUSION. A solution for the line status change detection in the transient states using a CNN classifier is proposed. A high accuracy of the line status detection was obtained despite the influence of noise on measurement data. A change in the network topology is detected at the very beginning of the transient state almost instantly. It will allow the operator several times during the first seconds to identify the line state in order to make sure that the decisions made are correct.

scholarly journals Optimal Location of IPFC That Handles Operating Constraints for Reducing Transmission Lines Utilization Levels in Electric Power Grid

2021 ◽  
Vol 6 (2) ◽  
pp. 31-39
Author(s):  
S Adetona ◽  
M Iyayi ◽  
R Salawu
Keyword(s):  
Transmission Line ◽  
Transmission Lines ◽  
Energy Demand ◽  
Reactive Power ◽  
Power Grid ◽  
Electric Energy ◽  
Load Flow ◽  
Optimal Location ◽  
Test Bed ◽  
Operating Constraints

The day-to-day increase in electric energy demand with increasing population and urbanization is causing transmission facilities to transfer load at their upper limits; therefore, the probability of failures of these facilities increases. One of the ways of mitigating failures is by constructing more transmission lines; which would serve as alternatives to reduce the transmission line utilization levels (TLUL). However, there are constraints in adopting this method; therefore, the use of Interline Power Flow Controller (IPFC) has been suggested by many researchers; but very few of these studies proposed the IPFC that has capability of handling operating constraints (IPFCthC) in solving power transmission systems issues. Some of the studies that proposed the IPFCthC use trial and error approach in identifying the optimal location for its injection in multi-buses power grid. Also, some of the studies that proposed the IPFCthC do not employ it to investigate its capability in reducing TLUL. In order to reduce the TSUL in the multi-bus grid, this paper therefore proposes optimal location for the injection of IPFCthC using Transmission Line Performance Index (TLPI) and Transmission Line Reactive Power Loss (TLRPL) in Newton-Raphson Load Flow (NRLF) algorithm. The proposed algorithm was tested on IEEE-30 Test-bed in Matlab environment. The results obtained reveal that the TLUL of each of the transmission lines of the Test-bed that is not connected to PV bus is reduced averagely by 4.00 % each, with the injection of the IPFCthC in an optimally location established by the proposed algorithm.

Sign in / Sign up

Export Citation Format

Share Document