International Journal of Mechanical Engineering and Applications

| Peer-Reviewed |

A Prediction Method for Galloping of Transmission Lines Based on Improved Neural Network

Received: 07 November 2018    Accepted:     Published: 08 November 2018
Views:       Downloads:

Share This Article

Abstract

The traditional back-propagation neural network (BP) have the disadvantages including the random generation of initial weights and thresholds, easy to fall into the local optimization, and the convergence speed is slow, and it’s hard to confirm the number of neurons in hidden layer. In this paper, the Genetic Algorithm (GA) is utilized to optimize the initial weights and thresholds space of the BP neural network. To obtain the optimal weight matrix and threshold matrix, the error-forward-feedback neural network training is carried out by using the data of transmission line galloping. The trial and error method are used to reduce the number of hidden layer neurons and find the optimal number of neurons. An optimized GA-BP neural network model is established to warn the occurrence of transmission line galloping. The historical data of the transmission lines galloping in the related areas is analyzed by the optimized GA-BP neural network model. The validity and practicability of the proposed GA-BP neural network model is tested and verified. The simulation results show that the GA-BP neural network module could predict the galloping situation of transmission lines more accurately and effectively. As a result, it provides a strong guarantee for preventing large-scale grid fault disasters, and further improves the power grid's ability to withstand natural disasters.

DOI 10.11648/j.ijmea.20180604.15
Published in International Journal of Mechanical Engineering and Applications (Volume 6, Issue 4, August 2018)
Page(s) 126-133
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.

Copyright

Copyright © The Author(s), 2024. Published by Science Publishing Group

Keywords

Genetic Algorithm, BP Neural Network, Machine Learning Method, Hidden Layer, Transmission Line Galloping

References
[1] GUO Yinglong, Yan Li, Bao Wujun, et al. Research on Transmission Wire Galloping [J]. Journal of Wuhan University (Engineering Science), 1995 (5): 506-509.
[2] LIANG Zhifeng. Statistical Analysis of Transmission Trips of Transmission Lines of State Grid Corporation of China from 2011 to 2013 [J]. East China Electric Power, 2014, 42 (11): 2265-2270.
[3] ZHU Kuanjun, Liu Bin, Liu Chaoqun, et al. Anti-dancing research of UHV transmission lines [J]. High Voltage Engineering, 2007, 33 (11): 12-20.
[4] HUANG Xinbo, Sun Qindong, Cheng Ronggui, et al. Mechanical Analysis of Wire Icing and Online Monitoring System for Ice Coating [J]. Automation of Electric Power Systems, 2007, 31 (14): 98-101.
[5] YU Junqing, Guo Yinglong, Xiao Xiaohui. Computer Simulation of Transmission Wire Galloping [J]. Journal of Wuhan University (Engineering Science), 2002, 35 (1): 39-43.
[6] LIU Hongwei, Li Junfeng, Wang Changfei. Application of Online Monitoring and Management Platform for 1000kV UHV Transmission Lines [J]. Automation of Electric Power Systems, 2009, 33 (23): 98-102.
[7] HUANG Yining, Xu Jiahao, Yang Chengshun, et al. Prediction of Transmission Line Ice Coating Based on Data Driven Algorithm and LS-SVM [J]. Automation of Electric Power Systems, 2014, 38 (15): 81-86.
[8] LIAO Wei, Xiong Xiaofu, Li Xin, et al. Early warning method of transmission line galloping based on BP neural network [J]. Power System Protection and Control, 2017, 45 (19): 154-161.
[9] YANG Wei, Ni Yidong, Wu Junji. Research on Initial Value and Convergence of Weights in BP Neural Networks [J]. Journal of Electric Power Systems and Automation, 2002, 14 (1): 20-22.
[10] SHEN Huayu, Wang Zhaoxia, Gao Chengyao, et al. Determination of the number of hidden layer elements in BP neural network [J]. Journal of Tianjin University of Technology, 2008, 24 (5): 13-15.
[11] SHI Kunpeng, Qiao Ying, Zhao Wei, et al. Short-term wind power prediction based on historical data entropy-related information mining [J]. Automation of Electric Power Systems, 2017, 41 (3): 13-18.
[12] ZHAI Wenxiang, Wang Wentian. Genetic Algorithm and Its Application [J]. Systems Engineering and Electronics, 1998, 23 (7): 9-10.
[13] TIAN Xuguang, Song Wei, Liu Yuxin. Optimization of BP neural network structure and parameters by genetic algorithm [J]. Journal of Computer Applications and Software, 2004, 21 (6): 69-71.
[14] Den Hartog J P. Transmission line vibration due to sleet [J]. Electrical Engineering, 2013, 51 (6):413-413.
[15] Nigol O, Clarke G J, Nigol O, et al. CONDUCTOR GALLOPING AND CONTROL BASED ON TORSIONAL MECHANISM [J]. IEEE Transactions on Power Apparatus & Systems, 1974, PA93 (6):1729-1729.
[16] Blevins RD. The Galloping Response of a Two-Degree-of-Freedom System [J]. Journal of Applied Mechanics, 1974, 41 (4):1113.
[17] HUANG Jingya. Analysis and Research on Conductor Galloping of Overhead Transmission Lines [J]. China Electric Power, 1995 (2): 21-26.
[18] FAN Qinshan, Guan Fei, Zhao Kunmin et al. Mechanism analysis and dynamic simulation of ice-covered wire dancing [J]. Journal of Tsinghua University: Natural Science Edition, 1995 (2): 34-40.
[19] ZHU Kuanjun, Liu Bin, Liu Chaoqun, et al. Anti-dancing research of UHV transmission lines [J]. High Voltage Engineering, 2007, 33 (11): 12-20.
[20] JIN Xidong. Genetic Algorithm and Its Application [D]. Southwest Jiaotong University, 1996.
[21] LI Xiaofeng, Xu Yiping, Wang Yinqing, et al. Establishment and Application of BP Artificial Neural Network Adaptive Learning Algorithm [J]. Systems Engineering - Theory & Practice, 2004, 24 (5): 1-8.
Author Information
  • China Electric Power Research Institute, Beijing, China

  • China Electric Power Research Institute, Beijing, China

  • China Electric Power Research Institute, Beijing, China

  • China Electric Power Research Institute, Beijing, China

Cite This Article
  • APA Style

    Yongfeng Cheng, Jingshan Han, Bin Liu, Danyu Li. (2018). A Prediction Method for Galloping of Transmission Lines Based on Improved Neural Network. International Journal of Mechanical Engineering and Applications, 6(4), 126-133. https://doi.org/10.11648/j.ijmea.20180604.15

    Copy | Download

    ACS Style

    Yongfeng Cheng; Jingshan Han; Bin Liu; Danyu Li. A Prediction Method for Galloping of Transmission Lines Based on Improved Neural Network. Int. J. Mech. Eng. Appl. 2018, 6(4), 126-133. doi: 10.11648/j.ijmea.20180604.15

    Copy | Download

    AMA Style

    Yongfeng Cheng, Jingshan Han, Bin Liu, Danyu Li. A Prediction Method for Galloping of Transmission Lines Based on Improved Neural Network. Int J Mech Eng Appl. 2018;6(4):126-133. doi: 10.11648/j.ijmea.20180604.15

    Copy | Download

  • @article{10.11648/j.ijmea.20180604.15,
      author = {Yongfeng Cheng and Jingshan Han and Bin Liu and Danyu Li},
      title = {A Prediction Method for Galloping of Transmission Lines Based on Improved Neural Network},
      journal = {International Journal of Mechanical Engineering and Applications},
      volume = {6},
      number = {4},
      pages = {126-133},
      doi = {10.11648/j.ijmea.20180604.15},
      url = {https://doi.org/10.11648/j.ijmea.20180604.15},
      eprint = {https://download.sciencepg.com/pdf/10.11648.j.ijmea.20180604.15},
      abstract = {The traditional back-propagation neural network (BP) have the disadvantages including the random generation of initial weights and thresholds, easy to fall into the local optimization, and the convergence speed is slow, and it’s hard to confirm the number of neurons in hidden layer. In this paper, the Genetic Algorithm (GA) is utilized to optimize the initial weights and thresholds space of the BP neural network. To obtain the optimal weight matrix and threshold matrix, the error-forward-feedback neural network training is carried out by using the data of transmission line galloping. The trial and error method are used to reduce the number of hidden layer neurons and find the optimal number of neurons. An optimized GA-BP neural network model is established to warn the occurrence of transmission line galloping. The historical data of the transmission lines galloping in the related areas is analyzed by the optimized GA-BP neural network model. The validity and practicability of the proposed GA-BP neural network model is tested and verified. The simulation results show that the GA-BP neural network module could predict the galloping situation of transmission lines more accurately and effectively. As a result, it provides a strong guarantee for preventing large-scale grid fault disasters, and further improves the power grid's ability to withstand natural disasters.},
     year = {2018}
    }
    

    Copy | Download

  • TY  - JOUR
    T1  - A Prediction Method for Galloping of Transmission Lines Based on Improved Neural Network
    AU  - Yongfeng Cheng
    AU  - Jingshan Han
    AU  - Bin Liu
    AU  - Danyu Li
    Y1  - 2018/11/08
    PY  - 2018
    N1  - https://doi.org/10.11648/j.ijmea.20180604.15
    DO  - 10.11648/j.ijmea.20180604.15
    T2  - International Journal of Mechanical Engineering and Applications
    JF  - International Journal of Mechanical Engineering and Applications
    JO  - International Journal of Mechanical Engineering and Applications
    SP  - 126
    EP  - 133
    PB  - Science Publishing Group
    SN  - 2330-0248
    UR  - https://doi.org/10.11648/j.ijmea.20180604.15
    AB  - The traditional back-propagation neural network (BP) have the disadvantages including the random generation of initial weights and thresholds, easy to fall into the local optimization, and the convergence speed is slow, and it’s hard to confirm the number of neurons in hidden layer. In this paper, the Genetic Algorithm (GA) is utilized to optimize the initial weights and thresholds space of the BP neural network. To obtain the optimal weight matrix and threshold matrix, the error-forward-feedback neural network training is carried out by using the data of transmission line galloping. The trial and error method are used to reduce the number of hidden layer neurons and find the optimal number of neurons. An optimized GA-BP neural network model is established to warn the occurrence of transmission line galloping. The historical data of the transmission lines galloping in the related areas is analyzed by the optimized GA-BP neural network model. The validity and practicability of the proposed GA-BP neural network model is tested and verified. The simulation results show that the GA-BP neural network module could predict the galloping situation of transmission lines more accurately and effectively. As a result, it provides a strong guarantee for preventing large-scale grid fault disasters, and further improves the power grid's ability to withstand natural disasters.
    VL  - 6
    IS  - 4
    ER  - 

    Copy | Download

  • Sections