Infrared Image Recognition Method of Substation Equipment Based on Improved YOLOv7
-
摘要:
变电站电气设备红外图像识别是其进行缺陷与故障诊断的重要前提，能保障电力系统的安全稳定运行。为达到变电站设备高精准、高效率的识别效果，本文提出了一种基于改进YOLOv7网络的变电站设备红外图像识别方法。变电站采集到的红外图像作为YOLOv7网络的输入，在红外图像的识别中，采用CoordConv卷积层增加图像坐标信息，增强网络层的信息细节，丰富图像特征内容；引入注意力机制排除其他信息干扰，增强模型的特征表达能力，提高网络训练精度；为进一步提高识别精度，不同于传统损失函数的构建，采用WIoU损失函数加速网络收敛，提高模型的准确性。通过对变电站采集的实际红外图像进行分析，实验结果表明，所提出的基于改进YOLOv7网络的变电站设备红外图像识别模型识别精度能达到97.1%。相较于YOLOv7网络和其他几种典型网络，所提模型具有较高的准确性和鲁棒性，可以有效应用于变电站设备的智能监测和维护，为后续故障诊断工作提供基础条件。
Abstract:Infrared image recognition of substation electrical equipment is an important prerequisite for defect and fault diagnosis to ensure the safe and stable operation of power systems. To realize high-precision and high-efficiency recognition of substation equipment, in this study, an infrared image recognition method of substation equipment is proposed based on an improved YOLOv7 network. The infrared image acquired by the substation is used as the input for the YOLOv7 network. In the recognition of infrared images, a CoordConv convolution layer is used to increase the image coordinate information, enhance the information details of the network layer, and enrich the image feature content. The attention mechanism is introduced to eliminate other information interference, enhance the feature expression ability of the model, and improve the accuracy of network training. To further improve the recognition accuracy, unlike the traditional loss function, the WIoU loss function is used to accelerate the network convergence and improve the model accuracy. By analyzing the actual infrared images acquired by the substation, the experimental results show that the recognition accuracy of the infrared image recognition model of the substation equipment based on the improved YOLOv7 network can reach 97.1%. Compared with the YOLOv7 network and other typical networks, the proposed model has higher accuracy and robustness and can be effectively applied to intelligent monitoring and maintenance of substation equipment, providing basic conditions for subsequent fault diagnosis.
-
Keywords:
- substation equipment /
- infrared image recognition /
- YOLOv7 /
- CoordConv /
- attention mechanisms /
- WIoU
-
-
表 1 变电站设备红外数据集构成
Table 1 Composition of infrared data set of substation equipment
Target equipment Number/sheet Ratio/% Transformer HV bushing 308 18.7 Current transformer 351 21.3 Voltage transformer 287 17.4 Lightning arrester 336 20.4 Insulator 365 22.2 
下载: 导出CSV
表 2 各类设备识别结果
Table 2 Identification results of various types of equipment
Type of equipment P/% R/% mAP/% Lightning arrester 93.5 95.6 95.5 Transformer HV bushing 94.5 89.6 96.3 Current transformer 96.9 95.3 98.4 Voltage transformer 96.9 93.1 98.4 Insulator 87.5 95.5 97.0 All types 92.8 94.2 97.1
下载: 导出CSV
表 3 消融实验
Table 3 Ablation experiment
Models CoordConv C3CA WIoU P/% mAP/% FPS YOLOv7 86.0 87.3 35.7 YOLOv7-A √ 90.4 95.2 28.5 YOLOv7-B √ 93.5 94.9 30.1 YOLOv7-C √ 89.8 91.9 36.7 YOLOv7-D √ √ 91.4 95.1 31.8 Improved-YOLOv7 √ √ √ 92.8 97.1 32.7
下载: 导出CSV
表 4 不同注意力机制对比实验结果
Table 4 Comparative experimental results of different attention mechanisms
Attention mechanisms P/% R/% mAP0.5/% SE 89.1 81.4 89.8 CBAM 89.3 83.5 90.5 ECA 90.8 87.7 92.1 C3CA 93.5 90.2 94.9
下载: 导出CSV
表 5 不同方法对比实验结果
Table 5 Comparison of experimental results by different methods
Target detection methods P/% R/% mAP0.5/% SSD 92.1 72.1 89.7 Faster R-CNN 62.8 93.9 92.4 YOLOv5 83.1 67.8 83.3 YOLOv7 86.0 80.8 87.3 YOLOv7-tiny 90.9 90.8 93.1 YOLOv7-W6 92.3 92.5 94.5 Ours 92.8 94.2 97.1
下载: 导出CSV
-
[1] 李文璞, 毛颖科, 廖逍, 等. 基于旋转目标检测的变电设备红外图像电压致热型缺陷智能诊断方法[J]. 高电压技术, 2021, 47(9): 3246-3253. LI Wenpu, MAO Yingke, LIAO Xiao, et al. Intelligent diagnosis method of infrared image for substation equipment voltage type thermal defects based on rotating target detection[J]. High Voltage Engineering, 2021, 47(9): 3246-3253.
[2] 邹辉, 黄福珍. 基于FAsT-Match算法的电力设备红外图像多目标定位[J]. 中国电机工程学报, 2017, 37(2): 591-599. ZOU Hui, HUANG Fuzhen. Multi-target localization for infrared images of electrical equipment based on improved FAST-Match algorithm[J]. Proceeding of the CSEE, 2017, 37(2): 591-599.
[3] 马鹏, 樊艳芳. 基于深度迁移学习的小样本智能变电站电力设备部件检测[J]. 电网技术, 2020, 44(3): 1148-1159. MA Peng, FAN Yanfang. Small sample smart substation power equipment component detection based on deep transfer learning[J]. Power System Technology, 2020, 44(3): 1148-1159.
[4] LIU Wei, Anguelov D, Erhan D, et al. SSD: single shot multibox detector[C]//Proceedings of the 14th European Conference on Computer Vision, 2016: 21-37.
[5] Redmon J, DivvalaI S, Girshick R, et al. You only look once: unified, real-time object detection [C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition, 2016: 779-788.
[6] Girshick R, Donahue J, Darrell T, et al. Rich feature hierarchies for accurate object detection and semantic segmentation[C]//Proceedings of 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014: 580-587.
[7] Girshick R. Fast R-CNN[C]//Proceedings of 2015 IEEE International Conference on Computer Vision, 2015: 1440-1448.
[8] REN Shaoqing, HE Kaiming, Girshick R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[C]//Proceedings of the 28th International Conference on Neural Information Processing Systems, 2015: 91-99.
[9] 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 Wenpu, XIE Ke, LIAO Xiao, 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.
[10] 谭宇璇, 樊绍胜. 基于图像增强与深度学习的变电设备红外热像识别方法[J]. 中国电机工程学报, 2021, 41(23): 7990-7998. TAN Yuxuan, FAN Shaosheng. Infrared thermal image recognition of substation equipment based on image enhancement and deep learning[J]. Proceedings of the CSEE, 2021, 41(23): 7990-7998.
[11] 王媛彬, 李媛媛, 段誉, 等. 基于轻量骨干网络和注意力结构的变电设备红外图像识别[J]. 电网技术, 2023, 47(10): 4358-4369. WANG Yuanbin, LI Yuanyuan, DUAN Yu, et al. Infrared image recognition of substation equipment based on lightweight backbone network and attention mechanism[J]. Power System Technology, 2023, 47(10): 4358-4369.
[12] WANG C Y, Bochkovskiy A, LIAO H Y M. YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors[J]. arXiv preprint arXiv: 2207.02696, 2022.
[13] LIU R, Lehman J, Molino P, et al. An intriguing failing of convolutional neural networks and the coordconv solution[J]. Advances in Neural Information Processing Systems, 2018, 31(18): 9628-9639.
[14] HOU Q, ZHOU D, FENG J. Coordinate attention for efficient mobile network design[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021: 13713-13722.
[15] HU J, SHEN L, SUN G. Squeeze-and-excitation networks[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, 10: 7132-7141.
[16] WANG Q, WU B, ZHU P, et al. ECA-Net: Efficient channel attention for deep convolutional neural networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, 11: 11534-11542.
[17] Woo S, Park J, Lee J Y, et al. Cbam: Convolutional block attention module[C]//Proceedings of the European Conference on Computer Vision (ECCV). 2018, 16: 3-19.
[18] TONG Z, CHEN Y, XU Z, et al. Wise-IoU: bounding box regression loss with dynamic focusing mechanism[J]. arXiv preprint arXiv: 2301.10051, 2023.
[19] Rezatofighi H, Tsoi N, Gwak J Y, et al. Generalized intersection over union: A metric and a loss for bounding box regression[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 658-666.
[20] ZHENG Z, WANG P, LIU W, et al. Distance-IoU loss: faster and better learning for bounding box regression[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(7): 12993-13000.
计量
- 文章访问数: 64
- HTML全文浏览量: 7
- PDF下载量: 30
