基于Mask-RCNN的牵引供电设备红外智能诊断

林珊; 邓树; 谌小莉; 王林; 程宏波

doi:10.13890/j.issn.1000-128X.2022.04.008

您当前的位置：

首页 >

文章列表页 >

基于Mask-RCNN的牵引供电设备红外智能诊断

电力牵引与控制 | 更新时间：2024-08-02

- 基于Mask-RCNN的牵引供电设备红外智能诊断
- Intelligent infrared diagnosis method for traction power supply equipment based on Mask-RCNN
- 机车电传动 2022年第4期页码：55-61
- 作者机构：
  
  1.广州地铁设计研究院股份有限公司，广东广州　　510010
  2.华东交通大学，电气与自动化工程学院，江西南昌;330013
- 作者简介：
  
  程宏波（1979—），男，教授，博士，主要从事轨道交通牵引供电系统健康管理及电网智能控制方面的研究； E-mail: hbcheng@ecjtu.edu.cn
- 基金信息：
  
  江西省重点研发计划项目(20202BBEL53008);江西省自然科学基金重点项目(2021ACB204004)
- DOI：10.13890/j.issn.1000-128X.2022.04.008
  中图分类号： TP391.41;TM507
- 纸质出版日期：2022-07-10，
  
  收稿日期：2022-04-04，
  
  修回日期：2022-06-12，
- 稿件说明：
扫描看全文
林珊, 邓树, 谌小莉, 等. 基于Mask-RCNN的牵引供电设备红外智能诊断[J]. 机车电传动, 2022,(4):55-61.

LIN Shan, DENG Shu, CHEN Xiaoli, et al. Intelligent infrared diagnosis method for traction power supply equipment based on Mask-RCNN[J]. Electric drive for locomotives, 2022,(4):55-61.
林珊, 邓树, 谌小莉, 等. 基于Mask-RCNN的牵引供电设备红外智能诊断[J]. 机车电传动, 2022,(4):55-61. DOI： 10.13890/j.issn.1000-128X.2022.04.008.

LIN Shan, DENG Shu, CHEN Xiaoli, et al. Intelligent infrared diagnosis method for traction power supply equipment based on Mask-RCNN[J]. Electric drive for locomotives, 2022,(4):55-61. DOI： 10.13890/j.issn.1000-128X.2022.04.008.

摘要

牵引供电设备的状态诊断存在红外图像人工处理效率低下，智能化程度不高的问题，因此提出一种基于Inception-V3和Mask-RCNN的双层网络模型，通过Inception-V3网络实现电力设备类型识别，在此基础上，利用Mask-RCNN模型实现不同设备结构区域的自动划分，并根据划分的结构区域坐标提取不同区域的最高温度，构造温度特征量，依据设备类型调用不同的判据对设备状态进行自动诊断。试验结果表明，利用双层改进网络模型进行电力设备结构划分的整体mAP值可达0.907 2，进行设备故障诊断的效率比人工提高95.41%，模型精度高、识别效果好，无需依赖故障样本，提升了设备红外图像处理诊断的效率、降低了工作人员的劳动强度。

Abstract

Aiming at the low efficiency of the manual infrared image processing and the low intelligence degree in the state diagnosis of traction power supply equipment

a two-layer network model based on Inception-V3 and Mask-RCNN was proposed in this paper. In this diagnosis method

the first step was to identify power equipment types through Inception-V3 network; on this basis

Mask-RCNN was used to realize automatic division of different equipment structural regions; according to the coordinates of the divided structural regions

the highest temperatures of different regions were extracted

the temperature characteristic quantities were constructed

and the equipment status was automatically diagnosed by invoking different criteria according to the type of equipment. The experimental results show that the overall mAP value of power equipment structural division by using the double-layer improved network model can reach 0.907 2

and the efficiency of equipment fault diagnosis can be improved by 95.41% compared with manual processing. The model featuring a high accuracy and good recognition effect

works independent of fault samples

which improves the efficiency of infrared image processing in equipment diagnosis and reduces the labor intensity.

关键词

牵引供电设备深度学习红外检测故障诊断

Keywords

traction power supply equipmentdeep learninginfrared detectionfault diagnosis

references

SZEGEDY C, IOFFE S, VANHOUCKE V, et al. Inception-v4, inception-ResNet and the impact of residual connections on learning[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2017, 3(1): 4278-4284.

REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//IEEE. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas: IEEE, 2016: 779-788.

LIU Wei, ANGUELOV D, ERHAN D, et al. SSD: single shot multibox detector[C]//Springer. European Conference on Computer Vision - ECCV 2016. Cham: Springer, 2016: 21-37.

REN Shaoqing, HE Kaiming, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.

HE Kaiming, GKIOXARI G, DOLLÁR P, et al. Mask R-CNN[C]//IEEE. 2017 IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, 2017: 2980-2988.

任新辉. 基于红外技术的变电站设备识别与热故障诊断[D]. 成都: 西南交通大学, 2016.

REN Xinhui. Substation equipment identification and thermal fault diagnosis based on infrared technology[D]. Chengdu: Southwest Jiaotong University, 2016.

余永维, 韩鑫, 杜柳青. 基于Inception-SSD算法的零件识别[J]. 光学精密工程, 2020, 28(8): 1799-1809.

YU Yongwei, HAN Xin, DU Liuqing. Target part recognition based Inception-SSD algorithm[J]. Optics and Precision Engineering, 2020, 28(8): 1799-1809.

陈铁明, 付光远, 李诗怡, 等. 基于YOLO v3的红外末制导典型目标检测[J]. 激光与光电子学进展, 2019, 56(16): 155-162.

CHEN Tieming, FU Guangyuan, LI Shiyi, et al. Typical target detection for infrared homing guidance based on YOLO v3[J]. Laser & Optoelectronics Progress, 2019, 56(16): 155-162.

ABU A, DIAMANT R. CFAR detection algorithm for objects in sonar images[J]. IET Radar Sonar & Navigation, 2020, 14(11): 1757-1766.

刘云鹏, 裴少通, 武建华, 等. 基于深度学习的输变电设备异常发热点红外图片目标检测方法[J]. 南方电网技术, 2019, 13(2): 27-33.

LIU Yunpeng, PEI Shaotong, WU Jianhua, et al. Deep learning based target detection method for abnormal hot spots infrared images of transmission and transformation equipment[J]. Southern Power System Technology, 2019, 13(2): 27-33.

全国高电压试验技术标准化分技术委员会. 带电设备红外诊断应用规范: DL/T 664—2016[S]. 北京：中国电力出版社, 2016.

National High Voltage Test Technical Standard Sub-Technical Committee. Application rules of infrared diagnosis for live electrical equipment: DL/T 664—2016[S]. Beijing: China Electric Power Press，2016.

陈良, 高成敏. 快速离散化双线性插值算法[J]. 计算机工程与设计, 2007(15): 3787-3790.

CHEN Liang, GAO Chengmin. Fast discrete bilinear interpolation algorithm[J]. Computer Engineering and Design, 2007(15): 3787-3790.

凌晨, 张鑫彤, 马雷. 基于Mask R-CNN算法的遥感图像处理技术及其应用[J]. 计算机科学, 2020, 47(10): 151-160.

LING Chen, ZHANG Xintong, MA Lei. Remote sensing image processing technology and its application based on Mask R-CNN algorithms[J]. Computer Science, 2020, 47(10): 151-160.

LIN T Y, DOLLÁR P, GIRSHICK R, et al. Feature pyramid networks for object detection[C]//IEEE. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 936-944.

刘子全, 付慧, 李玉杰, 等. 基于Mask-RCNN迁移学习的红外图像电力设备检测[J]. 数据采集与处理, 2021, 36(1): 176-183.

LIU Ziquan, FU Hui, LI Yujie, et al. Electrical equipment detection in infrared images based on transfer learning of Mask-RCNN[J]. Journal of Data Acquisition & Processing, 2021, 36(1): 176-183.

李大军, 何维龙, 郭丙轩, 等. 基于Mask-RCNN的建筑物目标检测算法[J]. 测绘科学, 2019, 44(10): 172-180.

LI Dajun, HE Weilong, GUO Bingxuan, et al. Building target detection algorithm based on Mask-RCNN[J]. Science of Surveying and Mapping, 2019, 44(10): 172-180.

SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//IEEE. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Vegas: IEEE, 2016: 2818-2826.

SZEGEDY C, LIU Wei, JIA Yangqing, et al. Going deeper with convolutions[C]//IEEE. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Boston: IEEE, 2015: 1-9.

徐凯, 梁志坚, 张镱议, 等. 基于GoogLeNet Inception-V3模型的电力设备图像识别[J]. 高压电器, 2020, 56(9): 129-135.

XU Kai, LIANG Zhijian, ZHANG Yiyi, et al. Image recognition of power equipment based on GoogLeNet Inception-V3 Model[J]. High Voltage Apparatus, 2020, 56(9): 129-135.

赵文清, 严海, 邵绪强. 改进的非极大值抑制算法的目标检测[J]. 中国图象图形学报, 2018, 23(11): 1676-1685.

ZHAO Wenqing, YAN Hai, SHAO Xuqiang. Object detection based on improved non-maximum suppression algorithm[J]. Journal of Image and Graphics, 2018, 23(11): 1676-1685.

浏览量

下载量

CSCD

CNKI被引量

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于三维点云与图像融合的轨道交通场景行人检测方法

基于电机振动的动车组牵引逆变器故障诊断研究

基于阶跃激励响应的牵引电机定子早期匝间短路故障诊断方法

基于低秩分解的YOLO轻量化目标检测模型

基于双通道特征融合的轴承故障诊断方法