Device component state recognition method of power distribution cabinet based on a residual networks

doi:10.3969/j.issn.1000-5641.2023.02.014

Abstract

Abstract:

With the continuous development of industrial intelligent inspection technology, the equipment element state recognition system based on digital image processing is widely used. In order to improve the accuracy of power distribution cabinet(PDC) equipment element state recognition in a distribution room, a ResNet(residual networks)-based equipment element state recognition method is proposed. Firstly, the data acquisition system is set up and the data set is constructed. Then, for the PDC image, the preset device component target area is cropped to generate the device component image. For device component images, a ResNet-based component state recognition model was constructed and trained, and the trained model was used to identify component states. Taking the data set for power distribution cabinet equipment element in substation distribution rooms as the research object, a network of single prediction heads is adopted as the component with complex features, and the network of multiple prediction heads is adopted as the component with simple features. Then, the compact and pruning model compression method is used to reduce the number of parameters and the calculation amount under the condition of less accuracy loss. Finally, the architecture design of the inspection system is introduced. A JetSon Nano edge terminal is used as the running hardware of the algorithm module to reduce the communication cost.

Key words: intelligent patrol inspection, residual networks (ResNet), image recognition, model compression

CLC Number:

TP391

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.

Figures/Tables 13

Fig.1

Fig.2

Fig.3

Fig.4

Fig.5

Fig.6

Table 1

Table 2

Table 3

Table 4

Table 5

Table 6

Fig.7

References 16

1	张燕东, 田磊, 李茂清, 等. 智能巡检机器人系统在火力发电行业的应用研发及示范. 中国电力, 2017, 50 (10): 1- 7.
2	李梁. 变电站巡检机器人视频监控系统设计与实现 [D]. 上海: 上海交通大学, 2013.
3	赵小鱼, 徐正飞, 付渊. 一种适用于智能变电站巡检机器人的异物检测算法研究. 现代电子技术, 2015(10), 132- 135.
4	殷强, 张应忠, 陆滔, 等. 基于图像处理与SNMP的通信状态告警系统设计与实现. 通信技术, 2019, 52 (8): 2060- 2066.
5	丁四海, 刘玉雪, 路林吉. 数字图像处理技术在电气控制柜开关状态识别中的应用. 微型电脑应用, 2013, 30 (5): 39- 40.
6	杨光, 周鹏举, 张宋彬, 等. 基于卷积神经网络的变电站巡检机器人图像识别 [J]. 软件, 2017, 38(12): 190-192.
7	HE K M, ZHANG X Y, REN S Q, et al. Deep residual learning for image recognition [C]// 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2016: 770-778.
8	LECUN Y, BOTTOU L, BENGIO Y, et al. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 1998, 86 (11): 2278- 2324.
9	KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks. Communications of the ACM, 2017, 60 (6): 84- 90.
10	ZEILER M D, FERGUS R. Visualizing and understanding convolutional networks [C]// European Conference on Computer Vision, ECCV 2014, Lecture Notes in Computer Science, vol 8689. Cham: Springer, 2014: 818-833.
11	SIMONYAN K, ZISSERMAN A. Very deep convolutional networks for large-scale image recognition [EB/OL]. (2015-04-10)[2021-07-02]. https://arxiv.org/abs/1409.1556.
12	SZEGEDY C, LIU W, JIA Y Q, et al. Going deeper with convolutions [C]// 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, 2015: 1-9. DOI: 10.1109/CVPR.2015.7298594.
13	GOODFELLOW I, BENGIO Y, COURVILLE A, et al. Deep Learning [M]. Cambridge, MA, USA: MIT Press, 2016: 281-283.
14	IOFFE S, SZEGEDY C. Batch normalization: Accelerating deep network training by reducing internal covariate shift [C]// Proceedings of the 32nd International Conference on International Conference on Machine Learning-Volume 37. JMLR, 2015: 448-456.
15	LIN M, CHEN Q, YAN S C. Network in network [EB/OL]. (2014-03-04)[2012-07-02]. https://arxiv.org/abs/1312.4400.
16	HOWARD A G, ZHU M H, CHEN B, et al. Mobilenets: Efficient convolutional neural networks for mobile vision applications [EB/OL]. (2017-04-17)[2021-07-02]. https://arxiv.org/abs/1704.04861.

模型	训练集准确率/%	验证集准确率/%	params(M)	FLOPS(G)
7 预测头模型	99.99	99.83	11.184720	0.230243904
指示器单预测头模型	99.97	99.97	11.178564	0.230237760
指示灯单预测头模型	100.00	99.98	11.177538	0.230236736

模型	训练集准确率/%	验证集准确率/%	params(M)	FLOPS(G)
储能状态模型	99.99	99.93	11.177538	0.230236736
压板模型	99.99	99.99	11.177538	0.230236736
开关模型	99.99	99.94	11.177538	0.230236736

模型	训练集准确率/%	验证集准确率/%	params(M)	FLOPS(G)
按钮模型	99.99	99.92	11.177538	0.230236736
旋钮1模型	99.99	99.88	11.178051	0.230237248
旋钮2模型	99.99	99.89	11.178051	0.230237248
箭头模型	99.99	99.93	11.177538	0.230236736

模型	训练集准确率/%	验证集准确率/%	params(M)	FLOPS(G)
7 预测头模型	99.99	98.02	7.010448	0.146089984
指示器单预测头模型	100.00	99.98	7.004292	0.146083840
指示灯单预测头模型	100.00	99.99	7.003266	0.146082816

模型	训练集准确率/%	验证集准确率/%	params(M)	FLOPS(G)
7 预测头模型	99.99	91.50	9.708624	0.176797760
指示器单预测头模型	100.00	99.98	9.702468	0.176791616
指示灯单预测头模型	100.00	99.99	9.701442	0.176790592