Abstract
Metal parts in substations corrode over time. The corrosion defects in the substation should be inspected to reduce potential safety risks. Traditional detection methods for corrosion defects rely on manual features and have poor robustness and generalization ability. Because the semantic information of the target corrosion area is not significant, the defect detection methods based on deep learning cannot accurately distinguish the corrosion defect. This paper proposes segmentation-detection ensembled network (SDEN) to improve corrosion detection performance. SDEN integrates the semantic segmentation model and target detection model. The semantic segmentation model predicts pixel-level corroded areas. The target detection model predicts the target location. The two networks share backbone and feature pyramid networks and perform prediction independently. The target box containing the rusted area is identified as the rust defect target. By decoupling rust zones from target prediction, SDEN improves the detection performance of targets containing fewer corroded pixels. Experiments on real datasets validate the effectiveness of the propose SDEN.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Zhang, T., Dai, J.: Electric power intelligent inspection robot: a review. J. Phys. Conf. Ser. 1750(1), 012023 (2021)
Yuan, C., Xiong, B., Li, X., et al.: A novel intelligent inspection robot with deep stereo vision for three-dimensional concrete damage detection and quantification. Struct. Health Monit. 21(3), 788–802 (2022)
Guan, H., Sun, X., Su, Y., et al.: UAV-lidar aids automatic intelligent powerline inspection. Int. J. Electr. Power Energy Syst. 130, 106987 (2021)
Bai, J., Zhao, R., Gu, F., et al.: Multi-target detection and fault recognition image processing method. High Voltage Eng. 45(11), 3504–3511 (2019)
Song, W., Zuo, D., Deng, B., et al.: Corrosion defect detection of earthquake hammer for high voltage transmission line. Chin. J. Sci. Instrum. 37(S1), 113–117 (2016)
Shen, H.K., Chen, P.H., Chang, L.M.: Automated rust defect recognition method based on color and texture feature. Autom. Constr. 31, 338–356 (2012)
Dai, Y., Lv, D., Guo, S.: Transmission line rusted area detection scheme based on color and texture features. Indus. Control Comput. 31(9), 39–40, 43 (2018)
Wang, K., Zhang, J., Ni, H., et al.: Thermal defect detection for substation equipment based on infrared image using convolutional neural network. Electronics 10(16), 1986 (2021)
Guan, X., Gao, W., Peng, H., et al.: Image based incipient fault classification of electrical substation equipment by transfer learning of deep convolutional neural network. IEEE Canadian J. Elect. Comput. Eng. 45(1), 1–8 (2021)
Hui, L., Ping, Z., Yujing, D., et al.: Study on detection method of transmission line rusty based on deep learning. Electronic Measurem. Technol. 41(22), 54–59 (2018)
Zhang, X., Zhai, D.: Corrosion on detection method of transmission line rusty based on deep learning. Distribut. Utilizat. 37(12), 87–92 (2020)
Acknowledgement
This work is supported by Science and technology project of State Grid Jiangxi Electric Power Co., LTD (Project No. 521823220006).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 Beijing Paike Culture Commu. Co., Ltd.
About this paper
Cite this paper
Zhong, C., Xu, B. (2023). Segmentation-Detection Ensembled Network for Corrosion Defect Detection. In: Yang, Q., Li, J., Xie, K., Hu, J. (eds) The Proceedings of the 17th Annual Conference of China Electrotechnical Society. ACCES 2022. Lecture Notes in Electrical Engineering, vol 1012. Springer, Singapore. https://doi.org/10.1007/978-981-99-0357-3_120
Download citation
DOI: https://doi.org/10.1007/978-981-99-0357-3_120
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-0356-6
Online ISBN: 978-981-99-0357-3
eBook Packages: EngineeringEngineering (R0)