222 Hits in 3.8 sec

Recognition Method of Digital Meter Readings in Substation Based on Connected Domain Analysis Algorithm

Ziyuan Zhang, Zexi Hua, Yongchuan Tang, Yunjia Zhang, Weijun Lu, Congfei Dai
2021 Actuators  
Aiming at the problem that the number and decimal point of digital instruments in substations are prone to misdetection and missed detection, a method of digital meter readings in a substation based on  ...  The method reduces the problem of mutual interference among categories when detecting YOLOv4. The experimental results show that the method improves the detection accuracy of the algorithm.  ...  based on deep learning [5] [6] [7] [8] [9] .  ... 
doi:10.3390/act10080170 fatcat:ciipsakgonftpluloh2mqdzloe

Computer Vision Based Automatic Recognition of Pointer Instruments: Data Set Optimization and Reading

Lu Wang, Peng Wang, Linhai Wu, Lijia Xu, Peng Huang, Zhiliang Kang
2021 Entropy  
for the target detection and reading of pointer meters.  ...  Network (Faster-RCNN) based object detection integrating with traditional computer vision.  ...  Experimental Results The detection algorithm is developed based on the deep learning language framework Torch.  ... 
doi:10.3390/e23030272 pmid:33668759 pmcid:PMC7996160 fatcat:jg2wsctl4bhj5fmo4dnsu6prja

Study of Device State Recognition Algorithm Based on Improved YOLOv3

Xiansong Bao, Gu Hao, Zhang Fan
2020 Saudi Journal of Engineering and Technology  
Foreground segmentation is to model the background information in the scene before recognizing the image, to separate the foreground target from the scene, at the same time to reduce the impact of noise  ...  In view of the timeliness and accuracy of traditional state recognition algorithms, this paper proposes an improvement measure for foreground segmentation and target recognition.  ...  Deep learning target detection technology has been widely used in recent years, and as one of the representative models of target detection, the biggest feature of the YOLOv3 algorithm models is its fast  ... 
doi:10.36348/sjet.2020.v05i08.001 fatcat:w5rvux6nhrabvnkd2bsj3wbsme

A MultiModal Detection Method for UHV Substation Faults Based on Robot Inspection and Deep Learning

Rong Meng, Zhao-lei Wang, Zhi-long Zhao, Jian-peng Li, Wei-ping Fu, Shan Zhong
2022 Journal of Robotics  
Aiming at the problem of multi-modal fault detection of different equipment in ultrahigh voltage (UHV) substations, a method for based on robot inspection and deep learning is proposed.  ...  Then, the HSV color space model based on saliency area detection is used to extract equipment defect areas, which improves the accuracy of defect image classification.  ...  Acknowledgments e authors are thankful to the science and technology project funding from State Grid Corporation of China (Project number: kj2021-059).  ... 
doi:10.1155/2022/1188617 fatcat:ju7arzzhxveujo6g2rxasvpgcm

Smear character recognition method of side-end power meter based on PCA image enhancement

Peng Luo, Xuekai Hu, Yuhao Zhao, Yi Jiang, Fanglin Lu, Jifeng Liang, Liang Xu
2022 Nonlinear Engineering  
A convolution neural network framework based on deep learning is proposed to realize the segmentation of smear characters, and the final segmented individual characters are fed into a network to identify  ...  Since it is difficult for manual recording to track the rapid change of indication of the power meter, the power meter images are collected by the camera and automatically recognized and recorded to effectively  ...  Finally, a convolutional neural network framework based on deep learning is designed to realize the perfect segmentation of instrument shadow characters.  ... 
doi:10.1515/nleng-2022-0028 fatcat:tfoqwehyanbltgbst3eq4sv3gq

Research and Application Toward the Atlas Variation Detection Technology of Soft Sensor in Substation's State Intelligence Analysis System

Tianzheng Wang, Hua Yu, Zhumao Lu, Dongdong Yang, Yutong Chen, Zhipeng Wang, Lu Bai
2017 DEStech Transactions on Engineering and Technology Research  
the video, provide a new kind of monitoring way to monitor the substation's environmental security situation, the abnormality of electrical equipment, automatic tracking of abnormal target and other monitoring  ...  requirements, and realize intelligent warning of the substation's fault information.  ...  This system establishes a typical scene database around the multimedia recognition and stream processing technology, thus forming an effective learning mechanism and perfect reasoning mechanism based on  ... 
doi:10.12783/dtetr/iceta2016/7051 fatcat:spoqxeyw5nbmxb22eh2yifbvee

Thinking and Prospect of Power Chip Specificity

Fuqi Ma, Min Li, Xuzhu DONG, Bo WANG, Yinyu ZHOU, Jincan Li, Lei FENG, Mohamed A. Mohamed
2021 International Journal of Photoenergy  
The contradiction between the demand of massive intelligent scene caused by the interconnection of things in power system and the bottleneck of the chip itself is becoming more and more serious.  ...  Therefore, this paper analyzes the demand for power chips in power system and discusses the scene specificity of power chips.  ...  The intelligent inspection robot is used in the substation for equipment inspection, taking photos and archiving for key parts and meters, detecting meter scale, and real-time infrared monitoring of equipment  ... 
doi:10.1155/2021/1512629 doaj:2c1faad0ea5c401e916a5cf5deace8db fatcat:tj26lb2wzfgvzfkyu35e6yw2em

Recognition Method of Knob Gear in Substation Based on YOLOv4 and Darknet53-DUC-DSNT

Ronglin Qin, Zexi Hua, Ziwei Sun, Rujiang He
2022 Sensors  
For the above problems, we propose a three-stage knob gear recognition method based on YOLOv4 and Darknet53-DUC-DSNT models for the first time and apply key point detection of deep learning to knob gear  ...  However, in the actual scene of the substation, the recognition method of a knob gear has low accuracy. The main reasons are as follows.  ...  The second method is based on deep learning. Mengan Shi et al.  ... 
doi:10.3390/s22134722 pmid:35808219 pmcid:PMC9269388 fatcat:qbhgqdfzobfr7ie6necwaanvmm

CI-dataset and DetDSCI methodology for detecting too small and too large critical infrastructures in satellite images: Airports and electrical substations as case study

Francisco PerezHernandez, Jose Rodriguez-Ortega, Yassir Benhammou, Francisco Herrera, Siham Tabik
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
Our experiments show that DetDSCI methodology achieves up to 37.53% F1 improvement with respect to Faster R-CNN, one of the most influential detection models.  ...  However, the detection of such infrastructures is complex as they have highly variable shapes and sizes, i.e., some infrastructures, such as electrical substations, are too small while others, such as  ...  expression and detection model based on deep transferable CNNs.  ... 
doi:10.1109/jstars.2021.3128994 fatcat:klvswivjobhqlnhciyysfng2le

Table of contents

2021 2021 International Conference on Power System Technology (POWERCON)  
and distribution price system PowerCon 2021CP0165 Research on Peak-valley Time Division Method of TOU Electricity Price Based on Density Clustering Term Wind Power Prediction of Regions Based on Deep  ...  Method Based on the Legality of Action Messages in Process Layer of Smart Substation •••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••••  ...  and generation method of virtual terminals in smart substation based on reinforcement learning and semantic analysis Container-Based Microservice Modeling and Computing Resource Scheduling Method for  ... 
doi:10.1109/powercon53785.2021.9697405 fatcat:ssuov6syuzeojjgzalbmkozecq

Analysis and Prospect of the Application of Wireless Sensor Networks in Ubiquitous Power Internet of Things

Li Cao, Zhengzong Wang, Yinggao Yue, Rodolfo E. Haber
2022 Computational Intelligence and Neuroscience  
, security protection of power system, and deep-seated ubiquitous power Internet of Things.  ...  The application of wireless sensor networks is prospected from the aspects of network development of relay protection, application research of smart substation, application research of power grid catastrophe  ...  Based on sensor network technology and RFID radio frequency identification technology, the system realizes the supervision function of the patrol personnel arriving at the scene and patrolling according  ... 
doi:10.1155/2022/9004942 pmid:35755756 pmcid:PMC9217569 fatcat:pp3wq5hwlvbermgxqsearrv2oe

Research and application of power grid intelligent inspection management system based on physical ID

Limin Qu, Chao Wang, Jian Zhang, Hang Zhang, Wei Sun, Jie Sheng, M.S. Nazir, H.A. Aziz
2021 E3S Web of Conferences  
system based on physical ID.  ...  By using big data mining and unsupervised clustering machine learning algorithm, the problems of poor accuracy and slow calculation speed of a large number of alarm data area division are fundamentally  ...  Research on identification method of hidden danger in transmission channel Using deep learning algorithm as the basis of scene recognition algorithm, a large number of candidate target area boxes are generated  ... 
doi:10.1051/e3sconf/202125701027 fatcat:ybqdzoekmrbyfhkr2fllhjowse

Using Game Engines In Lightning Shielding: The Application Of The Rolling Spheres Method On Virtual As-Built Power Substations

Yuri A. Gruber, Matheus Rosendo, Ulisses G. A. Casemiro, Klaus De Geus, Rafael T. Bee
2018 Zenodo  
The use of traditional methods of longitudinal cutting analysis based on 2D CAD tools makes the process laborious and the results obtained may not guarantee satisfactory protection of electrical equipment  ...  In order to mitigate this problem, a meticulous planning of the power substation protection system is of vital importance.  ...  ., under the auspices of the R&D Program of Agência Nacional de Energia Elétrica (ANEEL).  ... 
doi:10.5281/zenodo.1316075 fatcat:s5mmw6ro4fhivaa5cbc7mxmdae

DALES: A Large-scale Aerial LiDAR Data Set for Semantic Segmentation [article]

Nina Varney, Vijayan K. Asari, Quinn Graehling
2020 arXiv   pre-print
Large annotated point cloud data sets have become the standard for evaluating deep learning methods.  ...  This data set gives a critical number of expert verified hand-labeled points for the evaluation of new 3D deep learning algorithms, helping to expand the focus of current algorithms to aerial data.  ...  deep learning applications.  ... 
arXiv:2004.11985v1 fatcat:adbqj4lpgrdunnsc7u3v5owpii

A Comprehensive Survey for Deep-Learning-Based Abnormality Detection in Smart Grids with Multimodal Image Data

Fangrong Zhou, Gang Wen, Yi Ma, Hao Geng, Ran Huang, Ling Pei, Wenxian Yu, Lei Chu, Robert Qiu
2022 Applied Sciences  
Traditional approaches are also summarized together with their performance comparison with deep-learning-based approaches, based on which the necessity, seen in the surveyed literature, of adopting image-data-based  ...  In addition, several key methodologies and conditions for applying these techniques to abnormality detection are identified to help determine whether to use deep learning and which kind of learning techniques  ...  YNKJXM20191246), which focuses on the construction of satellite remote-sensing technology for power applications and wide-area intelligent monitoring of environments.  ... 
doi:10.3390/app12115336 fatcat:ot7ptci7bzafng3ytwhkk53ole
« Previous Showing results 1 — 15 out of 222 results