ABSTRACT
With the large-scale construction of new substations and the intelligent upgrading of existing substations, higher requirements have been put forward for efficient and intelligent maintenance of substations. In practical applications, the substation work ticket forms are complex and diverse, and the current mainstream work ticket key information extraction algorithms cannot meet the work needs. This paper proposed an intelligent recognition system for extracting safety measures from a work ticket in a substation. Based on the traditional text detection algorithm, a Multi-task network for text detection, frame extraction and form classification structure was proposed. The text recognition network used CRNN+CTC to train and tested the multi-model text recognition network on the work ticket interface text image data set. Advanced functions such as automatic generation, automatic execution, calibration and restoration of operation steps from a work ticket to safety measures in the substation were realized. In order to prove the effectiveness of the algorithm, an experimental study was carried out, and a comparative experiment was carried out in text detection and text recognition. The module has been tested in Yangzhou Power Supply Company of State Grid, and the results show that the scheme has good feasibility and effectively improves the work efficiency of operation and maintenance personnel.
- Luo Zhikai. Research on secondary professional safety measures of intelligent substation [J]. Electrical Technology, 2019, (15): 144-146.Google Scholar
- Zhao Zihan, Liu Xin, Ye Xiang, Research on the automatic generation method of "one-button" safety measures for the secondary system of intelligent substation [J]. Electrical Measurement and Instrumentation, 2018, 56(4): 21-26.Google Scholar
- Li Xin, He Zhiqiang, Wang Lirong, Application research of overvoltage intelligent identification system in 110kV substation [J]. Electric Porcelain Arrester, 2016, (2):7.Google Scholar
- Zhao Zihan, Liu Xin, Ye Xiang, Research on automatic generation method of "one-click" substation work ticket in smart substation system [J]. Electrical Measurement and Instrumentation, 2018, 56(4): 21-26.Google Scholar
- Yang Gaofeng, Xie Bing, Zeng Zhian, Research on Inter-bay Maintenance Technology of Smart Substation Based on SCD and CCD Calibration [J]. Power System Protection and Control, 2019, 47(2): 175-181.Google Scholar
- Peng Shaobo, Zheng Yongkang, Zhou Bo, Research on optimization of secondary safety measures for maintenance of 220 kV smart substations [J]. Power System Protection and Control, 2014, 42(23): 143-148.Google Scholar
- Xu Xiaochun, Tang Tongfeng, Zhao Yutian, Design and Implementation of Substation Work Ticket Rules Database for Equipment Maintenance of Smart Substation [J]. Power System Protection and Control, 2017, 45(2): 111-116.Google Scholar
- Peng Zhiqiang, Zhou Hang, Han Yu. Construction and Application of Transparent Operation and Maintenance System for Smart Substation Automation Equipment [J]. Power System Protection and Control, 2020, 48(13): 156-163.Google Scholar
- Liu Hongjun, Gao Xu, Du Liyan, Modular design of SCD file management and control system for smart substations [J]. Power System Protection and Control, 2019, 47(3): 154-159.Google Scholar
- Kong Shengli, Han Wei, Shi Chen, Intelligent Substation Substation System with Visual Panorama Function [J]. Electrical Measurement and Instrumentation, 2018, 55(19): 72-77.Google Scholar
- Huang Shaorui, Zhu Tingting. Design and Analysis of Maintenance Mechanism of Intelligent Substation Based on IEC61850 Standard [J]. Electrical Automation, 2015, 37(2): 70-72, 81.Google Scholar
- Xu Qin, Yang Zhen, Liu Xi, Research and application of safety isolation measures in smart substations [J]. Electrical Technology, 2015, (12): 3-4, 8.Google Scholar
- Y.Baek, B.Lee, D.Han, S.Yun, H.Lee.Character Region Awareness for Text Detection, IEEE International Conference on Computer Vision, 2019.Google ScholarCross Ref
- G.Huang, Z.Liu, L.Maaten.Densely Connected Convolutional Networks, IEEE International Conference on Computer Vision, 2017.Google ScholarCross Ref
- Zhi T, Huang W, Tong H, Detecting Text in Natural Image with Connectionist Text Proposal Network, European Conference on Computer Vision. Springer, Cham, 2016.Google Scholar
- Zhou X, Yao C, Wen H, EAST: An Efficient and Accurate Scene Text Detector. IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE, 2017.Google Scholar
- Zhi T, Huang W, Tong H, Detecting Text in Natural Image with Connectionist Text Proposal Network, European Conference on Computer Vision. Springer, Cham, 2016.Google Scholar
Index Terms
- Substation work ticket identification and extraction algorithm based on multi-task model
Recommendations
Application of WLAN Technology in the Intelligent Substation Network
ICCECT '12: Proceedings of the 2012 International Conference on Control Engineering and Communication TechnologyConsulting the promulgation of the IEC61850 standard communication system, it explores the application of WLAN technology in the intelligent substation network, from the technical requirements, 802.11 protocols, implementation steps, combination mode ...
The Research and Application of Process Layer Network Technology in Intelligent Substation
ICINIS '13: Proceedings of the 2013 6th International Conference on Intelligent Networks and Intelligent SystemsThe operation stability of process layer network is related directly to the safe and stable operation of intelligent substation. This paper puts forward three typical process layer network scheme, based on the analysis of theory, composition and basic ...
Research of Remote Communication Unit for Smart Substation
MACE '12: Proceedings of the 2012 Third International Conference on Mechanic Automation and Control EngineeringSo far, IEC61850 is the most perfect communication standards, identified as the base of the smart substation and the foundation of the seamless communication system in the future, whereas, the protocol which is specifically applied to the power remote ...
Comments