Login Register Cart 0
Generic placeholder image

Recent Patents on Mechanical Engineering

Editor-in-Chief

ISSN (Print): 2212-7976
ISSN (Online): 1874-477X

Back
Journal Home About Journal Editorial Board Journal Insight Current Issue Volumes/Issues
Subscribe
Research Article

Railroad Catenary Insulator Fault Detection Based on Improved Faster R-CNN

Author(s): Lingzhi Yi, Tengfei Dong, Yahui Wang*, Haixiang She, Chuyang Yi and Guo Yu

Volume 17, Issue 4, 2024

Published on: 11 March, 2024

Page: [243 - 259] Pages: 17

DOI: 10.2174/0122127976286140240222055507

Price: $65

Abstract

Background: The railroad catenary insulator, which is a crucial component of the catenary system and is situated between the pillar and wrist arm, is crucial for electrical conductor isolation, electrical equipment insulation, mechanical load bearing, anti-fouling, and anti-leakage. The catenary insulators will experience tarnished flash, breakage, insulation strength deterioration, and other issues as a result of the long-term outside unfavorable working circumstances. The train electrical system's ability to operate normally is greatly hampered by these problems. Although there are many patents and articles related to insulator fault detection, the precision is not high enough. Therefore, it is crucial to improve the precision of catenary insulator fault detection.

Objective: An improved region-based convolutional neural networks (Faster R-CNN)-based fault detection method for railway catenary insulators is proposed in response to the long detection time of the conventional railroad catenary insulator fault, the low precision of the catenary insulator fault detection for occlusion and truncation, the poor performance of multi-scale object detection, and the processing of class unbalance problem.

Methods: The Faster R-CNN is optimized from four perspectives: feature extraction, feature fusion, candidate box screening, and loss function, in accordance with the properties of the catenary insulator. First, to solve the problem of multi-scale catenary insulator fault detection, convolutional block attention module (CBAM) and feature pyramid network (FPN) are used to fuse the deep feature and shallow features of the image. This results in a feature map with more critical semantic information and higher resolution. After that, the weighted non-maximum suppression (WNMS) algorithm improved by distance-intersection over union (DIOU) and Gaussian weighting function is used instead of the traditional NMS algorithm, which effectively introduces the overlap of detection frames into the confidence level and makes full use of the effective information of the detection frames. Finally, the improved Focal loss is used as the classification loss, and the focusing parameter and the balance factor of the Focal Loss are adjusted dynamically to solve the problem of sample imbalance and difficult sample identification in the model better.

Results: The effects of SSD, YOLOV3, traditional Faster R-CNN and improved Faster R-CNN models are tested on the contact network insulator fault detection dataset constructed in this paper, and the experimental results show that the improved Faster R-CNN has higher precision, recall, and mAP compared to the other detection models, which reach 94.31%, 96.68% and 95.22%, respectively.

Conclusion: The results of the experiments demonstrate that this method may successfully detect the faults in different scale catenary insulators. It can effectively detect truncated, obscured faulty catenary insulators. It has higher precision and recall and provides a reliable reference for maintaining faulty insulators in railway catenary.

Next »
[1]
Zhang H, Zhou H, Zhao D, et al. Harmonic characteristics and negative sequence analysis of regenerative braking for high-speed railway. Recent Pat Mech Eng 2023; 16(3): 214-21.
[http://dx.doi.org/10.2174/2212797616666230612162748]
[2]
Lingzhi Y, Guo Y, Yahui W, Tengfei D, Huang Y, Haixiang S. Abnormal status detection of catenary based on TSNE dimensionality reduction method and IGWO-LSSVM model. Recent Pat Mech Eng 2023; 16(3): 188-202.
[http://dx.doi.org/10.2174/2212797616666230505151008]
[3]
Wu Q, An J, Lin B. A texture segmentation algorithm based on PCA and global minimization active contour model for aerial insulator images. IEEE J Sel Top Appl Earth Obs Remote Sens 2012; 5(5): 1509-18.
[http://dx.doi.org/10.1109/JSTARS.2012.2197672]
[4]
Zhai Y, Chen R, Yang Q, Li X, Zhao Z. Insulator fault detection based on spatial morphological features of aerial images. IEEE Access 2018; 6: 35316-26.
[http://dx.doi.org/10.1109/ACCESS.2018.2846293]
[5]
Zhang G, Liu Z, Han Y. Automatic recognition for catenary insulators of high-speed railway based on contourlet transform and Chan–Vese model. Optik 2016; 127(1): 215-21.
[http://dx.doi.org/10.1016/j.ijleo.2015.10.049]
[6]
Zhu Y, Wang W. Insulator target recognition method based on improved Mask R-CNN. Microelectron Comp 2020; 37(2): 69-74.
[7]
Zhang D, Gao S, Yu L, Kang G, Wei X, Zhan D. DefGAN: Defect detection GANs with latent space pitting for high-speed railway insulator. IEEE Trans Instrum Meas 2021; 70(70): 1-10.
[http://dx.doi.org/10.1109/TIM.2020.3038008]
[8]
Li B, Qu LY, Zhu XS, et al. Insulator defect detection based on multi-scale feature fusion. J Electr 2023; 38(01): 60-70.
[9]
Tang X, Huang J, Feng J, et al. Insulator image segmentation and defect detection based on U-net and YOLOv4. JSCUT 2020; 52(6): 15-21.
[10]
Wang B, Dong M, Ren M, et al. Automatic fault diagnosis of infrared insulator images based on image instance segmentation and temperature analysis. IEEE Trans Instrum Meas 2020; 69(8): 5345-55.
[http://dx.doi.org/10.1109/TIM.2020.2965635]
[11]
Qi Y, Li Y, Du A. Research on an insulator defect detection method based on improved YOLOv5. Appl Sci 2023; 13(9): 5741.
[http://dx.doi.org/10.3390/app13095741]
[12]
Wen-Wen LIN, Bin DENG, Lan-Ying YU, et al. A railroad insulator recognition method based on color and related reference features. Electr Porcel Surg Arrest 2016; 2016(06): 40-4.
[13]
Zhao Z, Zhen Z, Zhang L, Qi Y, Kong Y, Zhang K. Insulator detection method in inspection image based on improved faster R-CNN. Energies 2019; 12(7): 1204.
[http://dx.doi.org/10.3390/en12071204]
[14]
Cheng H, Zhai Y, Rui C, Rui Chen. Insulator recognition in aerial images based on Faster R-CNN. Mod Electron Technol 2019; 42(2): 98-102.
[15]
Liu Y, Huang X. Research on insulator burst detection and localization based on YOLOv4 and improved watershed algorithm. Grid and Clean Energy 2021; 37(7): 51-7.
[16]
Tao X, Zhang D, Wang Z, Liu X, Zhang H, Xu D. Detection of power line insulator defects using aerial images analyzed with convolutional neural networks. IEEE Trans Syst Man Cybern Syst 2020; 50(4): 1486-98.
[http://dx.doi.org/10.1109/TSMC.2018.2871750]
[17]
Zhai YJ, Wang D, Wu Y, et al. Step-by-step recognition method for aerial insulator images based on skeleton extraction. J North China Electric Power Uni 2015; 42(3): 105-10.
[18]
Zuo G, Lei M. Insulator detection method based on cross-connected convolutional neural network. Power Syst Auto 2019; 43(4): 101-6.
[19]
Kang B, Hou C, Xu Z, Ding G, Wang Z, Zhang X. GIS infrared feature recognition system and method based on improved YOLOv5. CN Patent 116342894A, 2023.
[20]
Wang H, Li F, Mo W, et al. Novel cloud-edge collaborative detection technique for detecting defects in PV components, based on transfer learning. Energies 2022; 15(21): 7924.
[http://dx.doi.org/10.3390/en15217924]
[21]
Zhang Y, Song C, Zhang D. Small-scale aircraft detection in remote sensing images based on Faster-RCNN. Multimedia Tools Appl 2022; 81(13): 18091-103.
[http://dx.doi.org/10.1007/s11042-022-12609-5]
[22]
Can Z, Xu Z, Dawei T, Ying W. Small object detection using deep convolutional networks: Applied to garbage detection system. J Electron Imaging 2021; 30(4): 043013.
[23]
Li T, Zhu H, Hu C, Zhang J. An attention-based prototypical network for forest fire smoke few-shot detection. J For Res 2022; 33(5): 1493-504.
[http://dx.doi.org/10.1007/s11676-022-01457-6]
[24]
Xie J, Pang Y, Nie J, Cao J, Han J. Latent feature pyramid network for object detection. IEEE Trans Multimed 2023; 25: 2153-63.
[http://dx.doi.org/10.1109/TMM.2022.3143707]
[25]
Zhou P, Yu W, Shu L, Wei S, Jiang C, Zheng H. Research progress on the human behavior recognition based on machine learning methods. Recent Pat Mech Eng 2023; 16(1): 32-44.
[http://dx.doi.org/10.2174/2212797615666220827164210]
[26]
Sheng W, Yu X, Lin J, Chen X. Faster RCNN target detection algorithm integrating CBAM and FPN. Appl Sci 2023; 13(12): 6913.
[http://dx.doi.org/10.3390/app13126913]
[27]
Jiao L, Haodong S, Yang Q, Zhongyu L, Sijie R. Design of hand detection based on attention and feature enhancement pyramids. J Electron Imaging 2022; 31(3): 033005.
[28]
Ma H, Li T. Fusion feature recommendation method based on attention mechanism. CN Patent 115422446A, 2022.
[29]
Zhao H, Wang J, Dai D, Lin S, Chen Z. D-NMS: A dynamic NMS network for general object detection. Neurocomputing 2022; 512: 225-34.
[http://dx.doi.org/10.1016/j.neucom.2022.09.080]
[30]
Li HY, Ma Y, Li HJ, et al. Deformable convolutional skin lesion recognition algorithm based on improved AlexNet. J Beijing Inst Technol 2022; 42(3): 297-303.
[31]
Wang WH. UT classification algorithm based on improved focal loss and EDA technique. Comput Simul 2023; 40(4): 346-349+396.
[32]
Sun P, Yao H, Yuan C. Research on wheel out-of-round fault diagnosis based on vibration data images. Recent Pat Mech Eng 2023; 16(2): 129-37.
[http://dx.doi.org/10.2174/2212797616666230330105028]

Rights & Permissions Print Cite
© 2024 Bentham Science Publishers | Privacy Policy