Please wait a minute...
工程设计学报  2024, Vol. 31 Issue (6): 750-756    DOI: 10.3785/j.issn.1006-754X.2024.03.406
【特约专栏】“双碳”背景下新型能源装备设计、制造、运维关键技术及其应用     
基于Fast R-CNNDeepLabV3+的变电站仪表盘示数自动识别方法
王飞1(),陈向俊2,3()
1.蓝卓数字科技有限公司,浙江 宁波 315000
2.浙江省特种设备科学研究院,浙江 杭州 310020
3.浙江省特种设备检验技术研究重点实验室,浙江 杭州 310020
Automatic recognition method for substation meter panel readings based on Fast R-CNN and DeepLabV3+
Fei WANG1(),Xiangjun CHEN2,3()
1.Bluetron Digital Technology Ltd. , Ningbo 315000, China
2.Zhejiang Academy of Special Equipment Science, Hangzhou 310020, China
3.Zhejiang Key Laboratory of Special Equipment Inspection Technology Research, Hangzhou 310020, China
 全文: PDF(2474 KB)   HTML
摘要:

随着新型能源系统的不断发展,变电站的自动化水平对于电网稳定运行和仪表设备维护具有至关重要的影响。准确获取仪表盘示数是实现变电站自动化的关键环节之一,这对变电站仪表设备的状态监测和故障诊断具有重要意义。然而,由于仪表盘示数复杂多变以及多种环境因素(如光线、角度等)的影响,实现仪表盘示数的自动识别具有较大挑战性。为了解决这一问题,提出了一种基于Fast R-CNN(regional convolutional neural network,区域卷积神经网络)和DeepLabV3+的变电站仪表盘示数自动识别方法。首先,对基于Fast R-CNN的目标检测技术进行了理论分析,并利用变电站仪表盘数据集详细阐述了其训练过程。然后,设计了基于DeepLabV3+的仪表盘语义分割模型以及示数计算方法。最后,开展变电站仪表盘示数自动识别实验,验证了所提出方法的有效性和准确性。实验结果表明,该方法可实现对变电站仪表盘示数的高效、准确识别,且具有很好的鲁棒性。基于Fast R-CNN和DeepLabV3+的仪表盘示数自动识别方法能够提高变电站的工作效率、安全性和降低运维成本,可进一步推动电力系统的智能化进程。

关键词: 仪表设备目标检测示数识别Fast R-CNNDeepLabV3+    
Abstract:

With the continuous development of new energy systems, the automation level of substation has a crucial impact on the stable operation of the power grid and the maintenance of metering equipment. The accurate acquisition of meter panel readings is one of the key links of achieving substation automation, which is of great significance to the status monitoring and fault diagnosis of substation metering equipment. However, due to the complexity of meter panel readings and the impact of various environmental factors such as light and angle, the automatic recognition of meter panel readings presents significant challenges. In order to solve this problem, an automatic recognition method for substation meter panel readings based on Fast R-CNN (regional convolutional neural network) and DeepLabV3+ was proposed. Firstly, the target detection technology based on Fast R-CNN was analyzed theoretically, and its training process was described in detail by using the data set of substation meter panel. Then, the semantic segmentation model of meter panel based on DeepLabV3+ and the reading calculation method were designed. Finally, the experiments of automatic identification of substation meter panel readings were conducted to verify the effectiveness and accuracy of the proposed method. The experimental results showed that the proposed method could recognize the readings of substation meter panel efficiently and accurately, and had good robustness. The automatic identification method for meter panel readings based on Fast R-CNN and DeepLabV3+ can improve the working efficiency, safety and reduce the operation and maintenance cost of substations, and further promote the intelligent process of power systems.

Key words: metering equipment    target detection    reading recognition    Fast R-CNN    DeepLabV3+
收稿日期: 2023-11-21 出版日期: 2024-12-31
CLC:  TP 391  
通讯作者: 陈向俊     E-mail: ictedu168@163.com;chenxj@zjtj.org
作者简介: 王 飞(1988—),男,工程师,硕士,从事智能制造、工业互联网及数字孪生等研究,E-mail: ictedu168@163.com,https://orcid.org/0009-0004-6726-0568
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
王飞
陈向俊

引用本文:

王飞,陈向俊. 基于Fast R-CNNDeepLabV3+的变电站仪表盘示数自动识别方法[J]. 工程设计学报, 2024, 31(6): 750-756.

Fei WANG,Xiangjun CHEN. Automatic recognition method for substation meter panel readings based on Fast R-CNN and DeepLabV3+[J]. Chinese Journal of Engineering Design, 2024, 31(6): 750-756.

链接本文:

https://www.zjujournals.com/gcsjxb/CN/10.3785/j.issn.1006-754X.2024.03.406        https://www.zjujournals.com/gcsjxb/CN/Y2024/V31/I6/750

图1  不同环境下的变电站仪表设备
图2  基于Canny边缘检测算法的仪表盘提取结果
图3  基于DeepLabV3+的仪表盘语义分割结果
图4  不同模型训练过程中的损失值变化曲线
图5  仪表盘检测与提取结果
图6  仪表盘示数识别结果
1 魏志涛. 基于机器视觉的仪表读数识别研究与应用[D]. 无锡: 江南大学, 2022.
WEI Z T. Research and application of meter reading recognition based on machine vision[D]. Wuxi: Jiangnan University, 2022.
2 李旺, 刘厚才, 康辉民, 等. 基于图和体分解的异型零件加工特征识别方法[J]. 工程设计学报, 2023, 30(5): 545-553.
LI W, LIU H C, KANG H M, et al. Machining feature recognition method of special-shaped parts based on graph and volume decomposition[J]. Chinese Journal of Engineering Design, 2023, 30(5): 545-553.
3 潘盛湖, 谢林成, 刘云强, 等. 基于表面评估的工件轮廓识别方法研究[J]. 工程设计学报, 2023, 30(1): 13-19.
PAN S H, XIE L C, LIU Y Q, et al. Research on workpiece contour recognition method based on surface evaluation[J]. Chinese Journal of Engineering Design, 2023, 30(1): 13-19.
4 郭航瑞. 基于仪表模糊示数的识别算法研究与应用[D]. 成都: 电子科技大学, 2023.
GUO H R. Research and application of recognition algorithm based on blured digital meter readings[D]. Chengdu: University of Electronic Science and Technology of China, 2023.
5 李宝志, 倪洪启, 林思雨, 等. 基于图像识别的波纹补偿器轴向尺寸检测方法[J]. 工程设计学报, 2022, 29(1): 10-19.
LI B Z, NI H Q, LIN S Y, et al. Axial dimension detection method of corrugated compensator based on image recognition[J]. Chinese Journal of Engineering Design, 2022, 29(1): 10-19.
6 SRINIVAS V L, WU J Z. Topology and parameter identification of distribution network using smart meter and µPMU measurements[J]. IEEE Transactions on Instrumentation and Measurement, 2022, 71: 9004114.
7 WANG F, LU X X, CHANG X Q, et al. Household profile identification for behavioral demand response: a semi-supervised learning approach using smart meter data[J]. Energy, 2022, 238: 121728.
8 孙孟姣, 周斌, 马金辉. 基于轻量化深度学习的仪表数字识别研究[J]. 科技创新与生产力, 2023, 44(7): 117-121.
SUN M J, ZHOU B, MA J H. Research on instrument digital recognition based on lightweight deep learning[J]. Sci-Tech Innovation and Productivity, 2023, 44(7): 117-121.
9 王琳. 井上变电站智能巡检仪表识别系统的设计与研究[J]. 自动化应用, 2023, 64(13): 165-167.
WANG L. Design and research of intelligent inspection instrument identification system for inoue substation[J]. Automation Application, 2023, 64(13): 165-167.
10 曲海成, 张旺. 基于YOLOv7+U2-Net的指针式仪表检测与识别[J]. 计算机系统应用, 2023, 32(11): 276-285.
QU H C, ZHANG W. Detection and recognition of pointer instruments based on YOLOv7+U2-Net[J]. Computer Systems & Applications, 2023, 32(11): 276-285.
11 李重阳, 廖存燚, 郑毅, 等. 海港码头冷藏集装箱仪表盘类型与温度示数识别方法研究[J]. 机器人技术与应用, 2023(3): 42-48.
LI C Y, LIAO C Y, ZHENG Y, et al. Research on identification method of instrument panel type and temperature indication of refrigerated container in seaport terminal[J]. Robot Technique and Application, 2023(3): 42-48.
12 陶金, 林文伟, 曾亮, 等. 基于YOLOv4-tiny和Hourglass的指针式仪表读数识别[J]. 电子测量与仪器学报, 2023, 37(5): 1-10.
TAO J, LIN W W, ZENG L, et al. Pointer meter reading recognition based on YOLOv4-tiny and Hourglass[J]. Journal of Electronic Measurement and Instrumentation, 2023, 37(5): 1-10.
13 王欣然, 张斌, 湛敏, 等. 基于改进的Faster RCNN的仪表自动识别方法[J]. 机电工程, 2024, 41(3): 532-539.
WANG X R, ZHANG B, ZHAN M, et al. Automatic instrument identification based on improved Faster RCNN[J]. Journal of Mechanical & Electrical Engineering, 2024, 41(3): 532-539.
14 赵伟达, 陈海文, 郭陆阳, 等. 基于YOLO-E与改进OCRNet图像分割的变电站仪表读数自适应识别方法[J]. 电力建设, 2023, 44(11): 75-85.
ZHAO W D, CHEN H W, GUO L Y, et al. Substation meter readings and dial information identification method based on YOLO-E and enhanced OCRNet image segmentation[J]. Electric Power Construction, 2023, 44(11): 75-85.
15 刘晏, 李玉梅, 张涛, 等. 基于改进的YOLOv5s指针式仪表检测与读数识别[J]. 北京信息科技大学学报(自然科学版), 2023, 38(3): 9-14.
LIU Y, LI Y M, ZHANG T, et al. Detection and reading recognition of pointer instrument based on improved YOLOv5s[J]. Journal of Beijing Information Science & Technology University, 2023, 38(3): 9-14.
16 金爱萍, 袁亮, 周德勤, 等. 基于YOLOv5和U-Net的指针式仪表读数识别方法[J]. 仪表技术与传感器, 2022(11): 29-33.
JIN A P, YUAN L, ZHOU D Q, et al. Identification method for reading of pointer instruments based on YOLOv5 and U-Net[J]. Instrument Technique and Sensor, 2022(11): 29-33.
17 ZHANG H F, CHEN Q Q, LEI L T. A YOLOv3-based industrial instrument classification and reading recognition method[J]. Mobile Information Systems, 2022, 2022(1): 7817309.
18 ZHOU D K, YANG Y, ZHU J, et al. Intelligent reading recognition method of a pointer meter based on deep learning in a real environment[J]. Measurement Science and Technology, 2022, 33(5): 055021.
19 赵永强, 饶元, 董世鹏, 等. 深度学习目标检测方法综述[J]. 中国图象图形学报, 2020, 25(4): 629-654. doi:10.11834/jig.190307
ZHAO Y Q, RAO Y, DONG S P, et al. Survey on deep learning object detection[J]. Journal of Image and Graphics, 2020, 25(4): 629-654.
doi: 10.11834/jig.190307
20 王植, 贺赛先. 一种基于Canny理论的自适应边缘检测方法[J]. 中国图象图形学报, 2004, 9(8): 957-962. doi:10.11834/jig.200408183
WANG Z, HE S X. An adaptive edge-detection method based on Canny algorithm[J]. Journal of Image and Graphics, 2004, 9(8): 957-962.
doi: 10.11834/jig.200408183
21 王俊强, 李建胜, 周华春, 等. 基于DeepLabV3+与CRF的遥感影像典型要素提取方法[J]. 计算机工程, 2019, 45(10): 260-265, 271.
WANG J Q, LI J S, ZHOU H C, et al. Typical element extraction method of remote sensing image based on DeepLabV3+ and CRF[J]. Computer Engineering, 2019, 45(10): 260-265, 271.
[1] 张旭辉, 闫建星, 麻兵, 鞠佳杉, 沈奇峰, 吴雨佳. 基于改进YOLOv5s的护帮板异常检测方法研究[J]. 工程设计学报, 2022, 29(6): 665-675.