Deep learning-based method for automatic verification of platen status in distribution cabinet

doi:10.3969/j.issn.1000-5641.2026.04.006

Abstract

Abstract:

In a substation, the platen is a core component on the distribution cabinet. In case of failure or unintentional human operation, the state verification of the platen of the distribution cabinet is important in the manual inspection of the substation as platen is prone to misinvestment and misreturn. Therefore, a new deep learning-based automatic checking method is proposed for the status of switchgear platen. First, the template platen frame data are extracted from the Excel-formatted panel diagram, in which every switchgear cabinet corresponds to a panel diagram. The panel diagram is an electronic record of the components in the switchgear cabinet, which contains the correct casting and retiring status of each platen, the name of the platen, and other information, i.e., the template platen frame data. Then the YOLOv5s algorithm is used to detect the platen target on the captured image to obtain the predicted platen detection frame data. The connectionist temporal classification (CTC) probability of paddle-to-paddle optical character recognition (PP-OCRv4) is used as the text similarity measure between the predicted and stencil platen names. Finally, based on the relationship between the spatial location of the platen, the matching probability scores of predicted and stencil platen frames are calculated from the row-column dimensions and combined with a correction strategy. Based on maximizing the row and column probability, a one-to-one correspondence is realized between the predicted platen frame in the captured image and stencil platen frame recorded in the disk diagram. Subsequently, the cast-in and cast-out status of the platen is checked, and the staff is notified with an alarm if the status is inconsistent. In the image dataset captured in the field scene of the substation, there were a total of 2685 platens, and the proposed platen checking method successfully matched the predicted platen frames with the stencil platen frames with 100% accuracy. Thus, the method is robust and can be used in the actual platen checking of the substation switchboard cabinets to improve manpower efficiency.

Key words: platen status verification, intelligent patrol inspection, object detection, text detection and recognition

CLC Number:

TP391

Ning CHEN, Rongsheng LIN, Cheng YUAN, Jin SHANG, Fan BAI, Dingjiang HUANG. Deep learning-based method for automatic verification of platen status in distribution cabinet[J]. J* E* C* N* U* N* S*, 2026, 2026(4): 51-62.

Figures/Tables 12

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Fig.7

Fig.8

Fig.9

Table 1

Table 2

Table 3

References 20

1	Ren S Q, He K M, Girshick R, et al.. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39 (6): 1137- 1149.
2	Liu W, Anguelov D, Erhan D, et al. SSD: single shot MultiBox detector [C]// Computer Vision – ECCV 2016. 2016: 21-37.
3	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. IEEE, 2016: 779-788.
4	Neubeck A, Van Gool L. Efficient non-maximum suppression [C]// 18th International Conference on Pattern Recognition. IEEE, 2006: 850-855.
5	付文龙, 谭佳文, 吴喜春, 等.. 基于图像处理与形态特征分析的智能变电站保护压板状态识别. 电力自动化设备, 2019, 39 (7): 203- 207.
6	潘成成, 卢泉, 胡立坤, 等.. 基于颜色分离与形态特征分析的保护压板定位及状态识别研究. 电测与仪表, 2023, 60 (4): 71- 77.
7	Li P, Chen Y X, Li H X, et al. Saturation high light removal of pressure plate image based on feature matching [C]// 2021 6th Asia Conference on Power and Electrical Engineering. IEEE, 2021: 94-98.
8	许超, 陈昊, 刘少情, 等.. 基于模型聚类匹配和形态特征识别的保护压板状态辨识技术. 陕西电力, 2017, 45 (1): 32- 36.
9	Ren J B, Li T C, Zhao Y H, et al. Research on operation and maintenance technology of relaying plate based on image recognition and model-based clustering matching [C]// 2020 7th International Forum on Electrical Engineering and Automation. IEEE, 2020: 669-674.
10	汪洋, 黎恒烜, 鄂士平, 等.. 基于深度学习的变电站硬压板状态检测与识别算法. 沈阳工业大学学报, 2020, 42 (6): 676- 680.
11	王伟, 张彦龙, 翟登辉, 等.. 基于OpenCV + SSD深度学习模型的变电站压板状态智能识别. 电测与仪表, 2022, 59 (1): 106- 112.
12	周克, 杨倩文, 王耀艺, 等.. 一种改进的压板状态识别SSD算法. 电测与仪表, 2021, 58 (1): 69- 76.
13	Li X H, Fan D H, Meng C X, et al. Embedded implementation of YOLO nano algorithm for on-site recognition of relay pressure board status [C]// Applied Mathematics, Modeling and Computer Simulation. 2022: 9-18.
14	Nan Y, Xi W. Classification of press plate image based on attention mechanism [C]// 2019 2nd International Conference on Safety Produce Informatization. IEEE, 2019: 129-132.
15	Li X H, Luo H X, Zeng L C, et al.. Faster R-CNN algorithm based relay protection platen state identification method. Journal of Physics: Conference Series, 2022, 2160 (1): 012078.
16	Liu Y, Jing Z B.. Power system relay protection based on faster R-CNN algorithm. International Journal of Information Technology and Web Engineering, 2023, 18 (1): 1- 15.
17	Graves A, Fernández S, Gomez F, et al. Connectionist temporal classification: Labelling unsegmented sequence data with recurrent neural networks [C]// Proceedings of the 23rd International Conference on Machine Learning. ACM, 2006: 369-376.
18	Li Y J, Liu B.. A normalized levenshtein distance metric. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007, 29 (6): 1091- 1095.
19	Gunawan D, Sembiring C A, Budiman M A.. The implementation of cosine similarity to calculate text relevance between two documents. Journal of Physics: Conference Series, 2018, 978, 012120.
20	Singh R, Singh S.. Text similarity measures in news articles by vector space model using NLP. Journal of the Institution of Engineers (India): Series B, 2021, 102 (2): 329- 338.

精确率	召回率	$ {{\mathrm{mAP}}}_{0.5} $	$ {{\mathrm{mAP}}}_{0.5:0.95} $
0.99919	0.99964	0.99478	0.84441

算法	准确率	重复率
编辑距离	0.748	0.154
余弦文本相似度	0.718	0.177
Jaccard文本相似度	0.726	0.155
CTC文本相似度	0.872	0.073

算法	准确率	重复率
CTC文本相似度	0.872	0.073
CTC文本相似度 + 路径概率最大	0.929	0.064
CTC文本相似度 + 路径概率最大 + 匹配修正	1.000	0.000

[1]	Yinshuai JI, Jinhua XU. Surface-height- and uncertainty-based depth estimation for Mono3D [J]. J* E* C* N* U* N* S*, 2025, 2025(1): 72-81.
[2]	Yang ZHANG, Yejing LAI, Dingjiang HUANG. Device component state recognition method of power distribution cabinet based on a residual networks [J]. Journal of East China Normal University(Natural Science), 2023, 2023(2): 132-142.
[3]	Zejie WANG, Chaomin SHEN, Chun ZHAO, Xinmei LIU, Jie CHEN. Recognition of classroom learning behaviors based on the fusion of human pose estimation and object detection [J]. Journal of East China Normal University(Natural Science), 2022, 2022(2): 55-66.
[4]	YU Ruo-nan, HUANG Ding-jiang, DONG Qi-wen. Survey on scene text detection based on deep learning [J]. Journal of East China Normal University(Natural Sc, 2018, 2018(5): 1-16.