Research on Key Technologies of Intelligent Detection of Substation Equipment Based on Cloud Edge Collaboration
Authors: 
Ke Chang, Min Zheng, Chunpeng WuAuthors Info & Claims
Ke Chang, Min Zheng, Chunpeng WuAuthors Info & ClaimsArticle No.: 35, Pages 1 - 5
Abstract
Abstract: The traditional manual inspection has some problems, such as strong subjectivity, time consuming and poor efficiency. With the remarkable progress of artificial intelligence, advanced communication and other technologies, and the wide application of deep learning models, the intensity of daily work has been reduced, but at the same time, new problems have been created. At present, the memory and computing power of the terminal hardware are limited, and when the model is deployed to the terminal side, the processing efficiency of the model is slow and the accuracy is low due to the limited hardware conditions. Aiming at the limited memory and computing power of the edge hardware, the lightweight network structure and model compression strategy are studied, and a channel structured pruning algorithm is proposed. A lightweight deep learning network model based on structured pruning of VGG-16 model was constructed. Experiments show that the optimized pruning model can obtain the same detection performance as the original model, and can reduce the size of the model by about 55.3% and increase the speed of 33FPS when the average accuracy mAP is lost by 8.1%, which provides effective support for the intelligent detection of substation equipment.
Keywords: Cloud edge collaboration; VGG-16; Model compression; Model pruning
References
[1]
He Chuang. Research on thermal fault diagnosis method of substation equipment based on Convolutional neural network [D]. The northeast agricultural university, 2023. /, dc nki. Gdbnu. 2023.000887
[2]
Figure convolution Jiang Jingbo. Based on the improved neural network fault diagnosis method of transformer [D]. Anhui university of science and technology, 2023. The /, dc nki. GHNGC. 2023.000068
[3]
Kan Qian, Meng An-Xin, Chen Li-Mu. Research on Key technologies of Road Intelligent Patrol based on Cloud Edge Collaboration [J]. Traffic and Transportation,2023,36(S1):195-200+208.
[4]
Wang Lei-Yu. Research on infrared image recognition technology of substation equipment based on Convolutional neural network [D]. The northeast agricultural university, 2023. /, dc nki. Gdbnu. 2023.000791
[5]
Li Ang, Sun Shijie, ZHANG Zhaoyang Research on Lightweight of Track Obstacle Detection Model improved by YOLOv5s [J]. Computer Engineering and Applications,2023,59(04):197-207.
[6]
Zhang Shang, WANG Hengtao, RAN Xiukang. Lightweight traffic sign detection method based on YOLOv5 [J]. Journal of electronic measurement technology, 2022, (8) : 129-135. The / j.carol carroll nki emt. 2108726
[7]
Liu Mochen, Gao Tiantian, Ma Zongxu Field maize weed detection model based on MSRCR-YOLOv4-tiny [J]. Transactions of the Chinese Society for Agricultural Machinery, 2002,53(02):246-255+335.
[8]
Zeng Huan Qiang, Hu Haolin, Lin Xiangwei Compression depth of neural network and accelerating review [J]. Journal of signal processing, 2022, 38 (01) : 183-194. The / j.i SSN. 1003-0530.2022.01.021
[9]
Yang Xiaogang, Gao Fan, LU Ruitao Lightweight aircraft target detection method based on improved YOLOv5 [J]. Journal of information and control, 2022 ploidy (03) : 361-368. The / j.carol carroll nki xk. 2021.1240
[10]
Compression Chen Siang. Convolution of the neural network model and the hardware accelerated research [D]. Zhejiang university, 2021. The /, dc nki. GZJDX. 2021.001680
[11]
Sun Yanli, Ye Jiongyao. Convolutional Neural network compression method based on pruning and quantization [J]. Computer Science, 2019,47(08):261-266. (in Chinese)
[12]
Peng Dongliang, WANG Tianxing. Pruning algorithm based on GoogLeNet model [J]. Control and decision, 2019, (6) : 1259-1264. The / j.k. zyjc. 2017.1556
[13]
Kong Yinghui, Zhu Chengcheng, Che Rattle. Flower recognition and model pruning based on MobileNets in complex background [J]. Science Technology and Engineering,2018,18(19):84-88.
[14]
Liu Haohan, Fan Yiming, He Huaiqing Improved Lightweight Model of YOLOv7-tiny for Object Detection [J]. Computer Engineering and Applications, 2019,59(14):166-175. (in Chinese)
[15]
Li Ang, Sun Shijie, ZHANG Zhaoyang Research on Lightweight of Track Obstacle Detection Model improved by YOLOv5s [J]. Computer Engineering and Applications,2023,59(04):197-207.
[16]
Li wenjing. Image recognition of medium and small sample study method and the model of lightweight research [D]. University of science and technology of China, 2021. The /, dc nki. Gzkju. 2021.000336
[17]
Wang Jun, FENG Suncheng, CHENG Yong. Depth study of the lightweight structure of neural network research review [J]. Computer engineering, 2021,47 (08) : 1-13. / j.i SSN. 1000-3428.0060931
[18]
Yuan Zheming, Yuan Hongjie, Yan Yuxuan Based on deep learning lightweight insects in the field of recognition and classification model [J]. Journal of jilin university (engineering science), 2021 ploidy (03) : 1131-1139. The / j.carol carroll nki jdxbgxb20200116.
Recommendations
Research on the Development of Key Technologies of Tactical Edge Cloud
ICISE '21: Proceedings of the 6th International Conference on Information Systems EngineeringIn view of the current situation that the traditional centralized cloud service architecture cannot meet the high requirements of tactical edge for data processing and storage, this paper introduces an emerging tactical cloud service model——tactical ...
Research and Application of Intelligent Detection Technology Based on Deep Learning Algorithm
AIAM2021: 2021 3rd International Conference on Artificial Intelligence and Advanced ManufactureWith the development of computer and information technology, the advancement of sensor technology, the level of intelligent detection technology continues to improve. Manual detection is gradually eliminated, and deep learning algorithms are gradually ...
Intelligent task prediction and computation offloading based on mobile-edge cloud computing
AbstractEdge computing overcomes the high communication delay shortcoming of traditional cloud computing and provides computing services with high reliability and high bandwidth for mobile devices. At present, edge computing has become the ...
Highlights- The paper designs an intelligent computation offloading based MEC architecture.
Comments
Information & Contributors
Information
Published In
January 2024
506 pages
ISBN:9798400718199
DOI:10.1145/3653804
Copyright © 2024 ACM.
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected].
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 01 June 2024
Check for updates
Qualifiers
- Research-article
- Research
- Refereed limited
Conference
CVDL 2024
CVDL 2024: The International Conference on Computer Vision and Deep Learning
January 19 - 21, 2024
Changsha, China
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 4Total Downloads
- Downloads (Last 12 months)4
- Downloads (Last 6 weeks)1
Reflects downloads up to 15 Oct 2024
Other Metrics
Citations
View Options
Get Access
Login options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign inFull Access
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML Format