Abstract
In this paper, an intelligent recognition system for insulator based on dimension correction and optimized faster region with convolutional neural network (R-CNN) is proposed. In the process of insulator pictures shooting, a laser radar is used to calculate the UAV correction vector. The position of the UAV is adjusted to ensure the consistency of the spatial dimensions of the pictures taken in different time dimensions. Based on the almost invariant spatial dimension, the faster R-CNN image recognition algorithm is optimized. When the target detection frame is generated, marked reference pictures are added to narrow the search range, improve the target detection frame generation speed, and reduce the number of pictures during training. Experiments and comparison analysis are included. They verify the optimized faster R-CNN image recognition algorithm requires less pictures and recognition time, and the recognition accuracy increased from 85.6 to 97.3%.
Similar content being viewed by others
References
Frizzo SS, Bartnik GR et al (2020) Optimized ensemble extreme learning machine for classification of electrical insulators conditions. IEEE Trans Ind Electron 67(6):5170–5178
Tao X, Zhang D et al (2020) Detection of power line insulator defects using aerial images analyzed with convolutional neural networks. IEEE Trans Syst Man Cybern Syst 50(4):1486–1498
Lei X, Sui Z (2019) Intelligent fault detection of high voltage line based on the faster R-CNN. Measurement 138:379–385
Koo J-H, Shin W-J et al (2017) Comparison of surface flashover characteristics of rod and rib type post insulator for extra-high voltage superconducting fault current limiter. IEEE Trans Appl Supercond 27(4):1–5
Rocha PHV, Costa EG et al (2019) Inspection in overhead insulators through the analysis of the irradiated RF spectrum. Int J Electr Power Energy Syst 113:355–361
Pu Z, Xiong Y et al (2019) Design and construction of a new insulator detection robot for application in 500 kV strings: electric field analysis and field testing. Electr Power Syst Res 173:48–55
Cao B, Wang L et al (2019) A low-cost evaluation and correction method for the soluble salt components of the insulator contamination layer. IEEE Sens J 19(13):5266–5273
Datsios ZG, Mikropoulos PN, Tsovilis TE (2019) Effects of lightning channel equivalent impedance on lightning performance of overhead transmission lines. IEEE Trans Electromagn Compat 61(3):623–630
Liu X, Wang L, Wang J, Li X (2016) Research on automatic detection technology for faulty porcelain insulators on AC transmission lines. Electr Meas Instrum 53(11):110–115
Bushra J, Riccardo LG et al (2019) Fault detection in power equipment via an unmanned aerial system using multi modal data. Sensors 19(13):3014
Velasquez A, Manuel R (2019) Insulation failure caused by special pollution around industrial environments. Eng Fail Anal 102:123–135
Gu Z-L, Li K, Li J-X (2019) Quantum cluster approach to the topological invariants in correlated Chern insulators. New J Phys 21(7):73016
Ting F, Zhao YB et al (2013) An improved meanshift insulator image segmentation algorithm. Adv Mater Res 634–638:3945–3949
Huang XN, Zhang ZL (2010) A method to extract insulator image from aerial image of helicopter patrol. Power Syst Technol 34(1):194–197
Yao CY, Jin LJ, Yan SJ (2012) Recognition of insulator string in power grid patrol images. J Syst Simul 24(9):1818–1822
Zhai Y, Cheng H et al (2018) Multi-saliency aggregation-based approach for insulator flashover fault detection using aerial images. Energies 11(2):340
Li B, Wu D et al (2012) A method of insulator detection from video sequence. In: International symposium on information science & engineering
Zhai Y, Chen R et al (2018) Insulator fault detection based on spatial morphological features of aerial images. IEEE Access 6:35316–35326
Yuan J, Cui K, Li B (2015) Identification and location of insulator video images based on ASIFT algorithm. Electr Meas Instrum 52(7):106–112
Park K-C, Motai Y et al (2017) Acoustic fault detection technique for high-power insulators. IEEE Trans Ind Electron 64(12):9699–9708
Zhai Y, Wang D et al (2017) Fault detection of insulator based on saliency and adaptive morphology. Multimed Tools Appl 76(9):12051–12064
Girshick R (2015) Fast R-CNN. In: Computer ence
Ren S, He K, Girshick R et al (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39(6):1137–1149
Acknowledgements
The authors acknowledge the financial support from China Southern Power Grid Company Limited.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lin, T., Liu, X. An intelligent recognition system for insulator string defects based on dimension correction and optimized faster R-CNN. Electr Eng 103, 541–549 (2021). https://doi.org/10.1007/s00202-020-01099-z
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00202-020-01099-z