[1]廖晓辉,谢子晨,路铭硕.基于 YOLOv5s 和 Android 部署的电气设备识别[J].郑州大学学报(工学版),2024,45(01):122-128.[doi:10.13705/j.issn.1671-6833.2024.01.004]
　LIAO Xiaohui,XIE Zichen,LU Mingshuo.Electrical Equipment Identification Based on YOLOv5s and Android Deployment[J].Journal of Zhengzhou University (Engineering Science),2024,45(01):122-128.[doi:10.13705/j.issn.1671-6833.2024.01.004]
点击复制

基于 YOLOv5s 和 Android 部署的电气设备识别()
分享到：

《郑州大学学报(工学版)》[ISSN:1671-6833/CN:41-1339/T]

卷:
45
期数:
2024年01期
页码:
122-128
栏目:
出版日期:
2024-01-19

文章信息/Info

Title:
Electrical Equipment Identification Based on YOLOv5s and Android Deployment
作者:
廖晓辉;  谢子晨;  路铭硕
郑州大学 电气与信息工程学院,河南 郑州 450001
Author(s):
LIAO Xiaohui;  XIE Zichen;  LU Mingshuo
School of Electrical and Information Engineering, Zhengzhou University, Zhengzhou 450001, China
关键词:
电气设备;  改进 YOLOv5s;  Android;  TensorFlow Lite;  图像识别
Keywords:
electrical equipment;  improved of YOLOv5s;  Android;  TensorFlow Lite;  image identification
DOI:
10.13705/j.issn.1671-6833.2024.01.004
文献标志码:
A
摘要:
针对变电站多种电气设备实时检测的需求,提出了一种基于改进 YOLOv5s 的电气设备识别方法,并设计 基于 Android 部署的电气设备识别 APP,以便对电气设备进行识别与学习。 以电力变压器、绝缘子串等 6 种常见变 电站电气设备为例构建图像数据集。 数据集进行图像预处理后对 YOLOv5s 算法进行改进。 通过引入 C2f 模块提 高小目标检测精度,采用 Soft-NMS 提高检测框筛选能力,减少漏检和误检的情况,使用改进后的算法对数据集进行 模型训练。 将训练好的识别网络模型通过 TensorFlow Lite 框架进行模型部署,设计电气设备识别 APP。 经验证,改 进后的变电站电气设备识别网络模型 mAP 稳定在 91. 6%,与原模型相比提高了 3. 3 百分点。 部署后的 APP 具有 设备识别和设备介绍等界面,使用移动端进行识别时每张图片识别时间都小于 1 s,具有较快的识别速度和较高的 识别精度,可以高效地实现变电站电气设备的实时检测与设备学习。
Abstract:
Aiming at the requirement of real-time detection of various electrical equipment in substation, an electrical equipment identification method based on improved YOLOv5s was proposed, and an electrical equipment identification APP based on Android was designed to recognize and learn electrical equipment. Six common electrical equipments of substation, such as power transformer and insulator string, were taken as examples to construct image data set. After image preprocessing of data set, YOLOv5s algorithm was improved, introducing C2f module to improve the detection accuracy of small targets, and using Soft-NMS to improve the screening ability of detection frame, so as to reduce the phenomenon of missing and false detection. The improved algorithm was used to train the model of data set. The trained identification network model was deployed through the TensorFlow Lite framework, and the electrical equipment identification APP was designed. It was verified that the mAP value of the improved substation electrical equipment identification network model was stable at 91. 6%, which was 3. 3 percentage points higher than that of the original model. After deployment, the APP had the interface of equipment recognition and equipment introduction, and the recognition time of each image was less than 1 s when using mobile terminal, which had a fast recognition speed and high recognition accuracy, and could effectively realize the real-time detection and equipment learning of electrical equipment in substation.

参考文献/References:

[1] 钱金戈, 徐丹, 史豪杰. 图像识别技术在变电站屏柜运检中的应用[J].工业控制计算机, 2021, 34(3)： 7-8, 11.QIAN J G, XU D, SHI H J. Application of operation and maintenance of substation cabinet based on image recognition[J].Industrial Control Computer, 2021, 34(3)：7-8, 11.

[2] LOWE D G. Object recognition from local scale-invariant features[C]∥Proceedings of the Seventh IEEE International Conference on Computer Vision. Piscataway： IEEE, 2002： 1150-1157.
[3] DALAL N, TRIGGS B. Histograms of oriented gradients for human detection[C]∥2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR′05). Piscataway： IEEE, 2005： 886-893.
[4] OJALA T, PIETIKAINEN M, MAENPAA T. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2002, 24(7)： 971-987.
[5] GIRSHICK R, DONAHUE J, DARRELL T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]∥2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway： IEEE, 2014： 580-587.
[6] GIRSHICK R. Fast R-CNN[C]∥2015 IEEE International Conference on Computer Vision (ICCV). Piscataway： IEEE, 2015： 1440-1448.
[7] 李文璞, 谢可, 廖逍, 等. 基于Faster RCNN变电设备红外图像缺陷识别方法[J].南方电网技术, 2019, 13(12)： 79-84.LI W P, XIE K, LIAO X, et al. Intelligent diagnosis method of infrared image for transformer equipment based on improved Faster RCNN[J].Southern Power System Technology, 2019, 13(12)：79-84.
[8] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once： unified, real-time object detection[C]∥2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway： IEEE, 2016： 779-788.
[9] 吕禾丰, 陆华才. 基于YOLOv5算法的交通标志识别技术研究[J].电子测量与仪器学报, 2021, 35(10)： 137-144.LYU H F, LU H C. Research on traffic sign recognition technology based on YOLOv5 algorithm[J].Journal of Electronic Measurement and Instrumentation, 2021, 35(10)： 137-144.
[10] 张晓鹏, 许志远, 曲胜, 等. 基于改进YOLOv5深度学习的海上船舶识别算法[J].大连海洋大学学报, 2022, 37(5)：866-872.ZHANG X P, XU Z Y, QU S, et al. Recognition algorithm of marine ship based on improved YOLOv5 deep learning[J].Journal of Dalian Ocean University, 2022, 37(5)：866-872.
[11] 周逸博, 马毓涛, 赵艳茹. 基于YOLOv5s和Android的苹果树皮病害识别系统设计[J].广东农业科学, 2022, 49(10)：155-163.ZHOU Y B, MA Y T, ZHAO Y R. Design of mobile APP recognition system for apple bark disease based on YOLOv5s and Android[J].Guangdong Agricultural Sciences, 2022, 49(10)：155-163.
[12] 院老虎, 常玉坤, 刘家夫. 基于改进YOLOv5s的雾天场景车辆检测方法[J].郑州大学学报(工学版), 2023, 44(3)： 35-41.YUAN L H, CHANG Y K, LIU J F. Vehicle detection method based on improved YOLOv5s in foggy scene[J].Journal of Zhengzhou University (Engineering Science), 2023, 44(3)： 35-41.
[13] 唐靓, 余明慧, 武明虎, 等. 基于改进YOLOv5的绝缘子缺陷检测算法[J].华中师范大学学报(自然科学版), 2022, 56(5)： 771-780.TANG J, YU M H, WU M H, et al. Insulator defect detection algorithm based on improved YOLOv5[J].Journal of Central China Normal University (Natural Sciences), 2022, 56(5)： 771-780.
[14] 曾水玲, 唐敏之. 基于模糊推理的电气设备红外图像分割[J].红外技术, 2023, 45(5)： 446-454.ZENG S L, TANG M Z. Infrared image segmentation for electrical equipment based on fuzzy inference[J].Infrared Technology, 2023, 45(5)： 446-454.
[15] 任杰, 高岭, 于佳龙, 等. 面向边缘设备的高能效深度学习任务调度策略[J].计算机学报, 2020, 43(3)： 440-452.REN J, GAO L, YU J L, et al. Energy-efficient deep learning task scheduling strategy for edge device[J].Chinese Journal of Computers, 2020, 43(3)：440-452.
[16] OR AN I L, SEICULESCU C, C LEANU C D. Benchmarking TensorFlow Lite quantization algorithms for deep neural networks[C]∥2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI). Piscataway： IEEE, 2022： 221-226.
[17] SHIN D J, KIM J J. A deep learning framework perfor-mance evaluation to use YOLO in Nvidia Jetson platform[J].Applied Sciences, 2022, 12(8)： 3734.
[18] 李双峰. TensorFlow Lite： 端侧机器学习框架[J].计算机研究与发展, 2020, 57(9)： 1839-1853.LI S F. TensorFlow Lite： on-device machine learning framework[J].Journal of Computer Research and Deve-lopment, 2020, 57(9)： 1839-1853.

相似文献/References:

[1]许珉,王侠,李耀,等.实用短路计算与电气设备选择一体化程序研究[J].郑州大学学报(工学版),2005,26(02):39.[doi:10.3969/j.issn.1671-6833.2005.02.010]
　Xu Min,Wang Xia,LI Yao,et al.Research on the integration of practical short circuit calculation and electrical equipment selection[J].Journal of Zhengzhou University (Engineering Science),2005,26(01):39.[doi:10.3969/j.issn.1671-6833.2005.02.010]

更新日期/Last Update: 2024-01-25