Real-Time Online Prediction Method for Structural Strength of Transmission Towers

CHEN Yan; YAN Bo; WANG Qingshan; LU Jun; LIANG Ming

doi:10.13204/j.gyjzG22072603

Volume 52 Issue 10

Oct. 2022

Turn off MathJax

Article Contents

Article Navigation > INDUSTRIAL CONSTRUCTION > 2022 > 52(10): 246-252,241

CHEN Yan, YAN Bo, WANG Qingshan, LU Jun, LIANG Ming. Real-Time Online Prediction Method for Structural Strength of Transmission Towers[J]. INDUSTRIAL CONSTRUCTION, 2022, 52(10): 246-252,241. doi: 10.13204/j.gyjzG22072603

Citation:

CHEN Yan, YAN Bo, WANG Qingshan, LU Jun, LIANG Ming. Real-Time Online Prediction Method for Structural Strength of Transmission Towers[J]. INDUSTRIAL CONSTRUCTION, 2022, 52(10): 246-252,241. doi: 10.13204/j.gyjzG22072603

Citation:

PDF( 10057 KB)

Real-Time Online Prediction Method for Structural Strength of Transmission Towers

doi: 10.13204/j.gyjzG22072603

1. College of Aerospace Engineering, Chongqing University, Chongqing 400044, China;
2. State Grid Economic and Technological Research Institute Co., Ltd., Beijing 102200, China;
3. CPECC Southwest Electric Power Design Institute Co., Ltd., Chengdu 610021, China

Received Date: 2022-07-26
Available Online: 2023-03-22

Abstract

Abstract

Taking a 220 kV double-circuit suspension tower as the research object, this study built a finite-element tower-line system model to parametrically analyze the deformations and stresses of the tower lines in the cases of settlement and slip of the foundation as well as uniform and non-uniform icing. A dataset was created by extracting the displacements of the pivot points on the tower and those of the hanging points of the conductors and ground wires, as well as the stresses of the members. With the pivot points on the tower and the hanging points as the monitoring points, a surrogate model for calculating the stress of the tower was built with the displacements of the monitoring points as the inputs by utilizing the dataset created and the back-propagation (BP) neural network algorithm. A method of predicting the structural strength of the tower in real time by rapidly outputting the stresses of all the members of the tower on the basis of the displacements of the monitoring points and the surrogate model was proposed to pave the way for real-time perception of the operation status of transmission lines and safety early warning technologies.
- transmission tower,
- BP neural network,
- stress distribution,
- surrogate model,
- structural strength

FullText(HTML)

References(22)

References

[1]	YANG F L, LI Q, YANG J B, et al. Assessment on the stress state and the maintenance schemes of the transmission tower above goaf of coal mine[J]. Engineering Failure Analysis, 2013, 31:236-247.
[2]	姜太荣, 张翼虎, 王永泉, 等. 不均匀沉降条件下输电塔线体系安全性研究[J]. 施工技术, 2018, 47(4):132-136.
[3]	田家栋. 不均匀沉降下干字型输电塔倒塌分析与倾斜监测方法研究[D]. 哈尔滨:哈尔滨工业大学, 2019.
[4]	刘正伟, 底尚尚, 张丽娟, 等. 基础水平位移对输电杆塔受力影响及限值研究[J]. 山东大学学报(工学版), 2022, 52(2):1-8.
[5]	陆佳政, 刘纯, 陈红冬, 等. 500 kV输电塔线覆冰有限元计算[J]. 高电压计算, 2007, 33(10):167-169.
[6]	刘磊. 基于不同覆冰状态的输电塔线体系倒塔力学特性研究[D]. 西安:西安工程大学, 2015.
[7]	毕承财. 输电塔线耦合体系中杆塔的强度研究[D]. 重庆:重庆大学, 2015.
[8]	PRASAD R N, SAMUEL K G M, MOHAN S J, et al. Studies on failure of transmission line towers in testing[J]. Engineering Structures, 2012, 35:55-70.
[9]	WANG J, XIONG X F, ZHOU N, et al. Early warning method for transmission line galloping based on SVM and AdaBoost bilevel classifiers[J]. IET Generation, Transmission & Distribution, 2016, 10(14):3499-3507.
[10]	MOU Z Y, YAN B, LIN X, et al. Prediction method for galloping features of transmission lines based on FEM and machine learning[J]. Cold Regions Science and Technology, 2020, 173:103031.
[11]	MOU Z Y, YAN B, YANG H X, et al. Prediction model for aerodynamic coefficients of iced quad bundle conductors based on machine learning method[J]. Royal Society Open Science, 2021, 8(10):210568.
[12]	文楠, 严波, 林翔, 等. 基于BP神经网络的导线脱冰跳跃高度预测模型[J]. 振动与冲击, 2021, 40(1):199-204.
[13]	WEN N, YAN B, MOU Z Y, et al. Prediction models for dynamic response parameters after ice-shedding based on machine learning method[J]. Electric Power Systems Research, 2022, 202:107580.
[14]	眭嘉里, 严波, 林翔, 等. 基于BP神经网络的悬垂绝缘子串风偏角预测模型[J]. 重庆大学学报, 2021, 44(8):114-124.
[15]	LIANG L, LIU M, MARTIN C, et al. A deep learning approach to estimate stress distribution:a fast and accurate surrogate of finite-element analysis[J]. Journal of The Royal Society Interface, 2018, 15(138):20170844.
[16]	NIE Z, JIANG H, KARA L B. Stress field prediction in cantilevered structures using convolutional neural networks[J]. Journal of Computing and Information Science in Engineering, 2020, 20(1):1-16.
[17]	SHI C, ZHAO Q L, LI M, et al. Precise orbit determination of Beidou Satellites with precise positioning[J]. Science China (Earth Sciences), 2012, 55(7):1079-1086.
[18]	丛犁, 杜秋实, 窦增, 等. 基于北斗RTK技术的电力铁塔变形监测技术研究[J]. 电力信息与通信技术, 2015, 13(12):24-29.
[19]	黄红兵, 张辰, 刘俊毅, 等. 基于北斗定位技术的输电杆塔运行状态监测研究与应用[J]. 数字通信世界, 2018(5):51-53.
[20]	武立平, 马维青, 杨海飞, 等. 北斗监测数据在输电线路杆塔的位移和形变方面的监测与研究[J]. 计算机测量与控制, 2020, 28(3):79-83.
[21]	欧郁强, 张飞, 郭小龙, 等. 北斗通讯在智能电网状态监测中的应用[J]. 中国电力, 2015, 48(12):39-42.
[22]	电力规划设计总院. 重覆冰架空输电线路设计技术规:DL/T 5440-2020[S].中国计划出版社, 2020.