Skip to main content

ORIGINAL RESEARCH article

Front. Mech. Eng.
Sec. Mechatronics
Volume 10 - 2024 | doi: 10.3389/fmech.2024.1496377

Fault Detection of Transmission Tower Bolts Based on GP-BP Neural Network Algorithm

Provisionally accepted
Ziqiang Lu Ziqiang Lu *Pengjie He Pengjie He Huiwei Liu Huiwei Liu Jie Li Jie Li Ziying Lu Ziying Lu
  • State Grid UHV Transmission Co. of SEPC, Taiyuan, China

The final, formatted version of the article will be published soon.

    In the power system, identifying the health status of transmission towers is a necessary daily task.And bolt loosening fault is a common damage mode in the main materials of transmission towers.When bolt loosening damage occurs, it will weaken the bearing capacity of the transmission tower.If not detected and intervened in a timely manner, serious adverse events such as tower collapse may occur, endangering the normal operation of the power system. Based on this, to enhance the accuracy of bolt loosening fault identification without affecting the normal operation of transmission towers, GP-BP neural network algorithm was applied in the detection process. The feasibility of the algorithm is understood through the quantitative analysis of different damage degrees.The results are as follows: 1) Except the average accuracy rate of substructure 7 is 89.74%, the identification effect of other substructures is more than 90%, indicating that GA-BP algorithm has a good effect on the identification of single damage degree of the tower bolt loose main material; 2) The identification effect of double damage substructure is more than 90%, indicating that GA-BP algorithm has a good effect on the identification of double damage degree of the tower bolt loosening main material. In summary, it can be concluded that both the single damage degree condition and the double damage degree condition have a relatively considerable recognition effect. In addition, the recognition effect of the algorithm under the condition of double damage degree is better than that of single damage degree. Therefore, it can be applied in practical projects under the condition of double damage degree to improve the recognition effect of bolt loosening fault and provide reliable technical support for the safe operation of transmission equipment.

    Keywords: GP-BP neural network algorithm, Bolt loosening failure, detection, Power transmission and inspection, electrical automation

    Received: 14 Sep 2024; Accepted: 23 Dec 2024.

    Copyright: © 2024 Lu, He, Liu, Li and Lu. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence: Ziqiang Lu, State Grid UHV Transmission Co. of SEPC, Taiyuan, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.