Damage detection in power transmission towers using machine learning algorithms

被引:16
作者
Kouchaki, Mehdi [1 ]
Salkhordeh, Mojtaba [1 ]
Mashayekhi, Mohammadreza [1 ]
Mirtaheri, Masoud [1 ]
Amanollah, Hessam [2 ]
机构
[1] KN Toosi Univ Technol, Dept Civil & Environm Engn, Tehran, Iran
[2] Univ Tehran, Coll Engn, Sch Civil Engn, Tehran, Iran
关键词
Power transmission tower; Damage detection; Machine learning; Structural health monitoring; Classification; GENETIC ALGORITHMS; TRUSS STRUCTURES; OPTIMAL-DESIGN; OPTIMIZATION;
D O I
10.1016/j.istruc.2023.104980
中图分类号
TU [建筑科学];
学科分类号
0813 ;
摘要
The purpose of this study is to utilize machine learning techniques to detect any damages that occurred in power transmission towers. In the first step, various machine learning algorithms were employed for a structural model with a small number of members so that the most efficient algorithm was selected based on the accuracy cri-terion. Then, the selected method was evaluated using acceleration responses obtained from larger power transmission towers in various states. It is worth mentioning that the parameters of the learning algorithms have been optimized by the Bayesian Optimization (BO) algorithm. Responses of three case studies, including 25-, 36-, and 160-member structures, under environmental vibrations, were polluted to 10% noise to simulate the field condition. Studies conducted on selecting the best classifier in detecting damages in these structures indicate that the Support Vector Machine (SVM) algorithm, with an approximate average of 96%, has the highest accuracy among different utilized algorithms. Moreover, the Linear Discriminant Analysis (LDA) algorithm, with an approximate average of 94%, is the second most accurate algorithm, and its computational cost is lower than the SVM algorithm. The results stemming from investigations of case studies show that the chosen features and method seem appropriate for identifying power transmission towers' damages. Finally, a study was conducted to investigate the impact of the number of input records on accuracy.
引用
收藏
页数:19
相关论文
共 53 条
[31]   Probabilistic reconstruction for spatiotemporal sensor data integrated with Gaussian process regression [J].
Ma, Yafei ;
He, Yu ;
Wang, Lei ;
Zhang, Jianren .
PROBABILISTIC ENGINEERING MECHANICS, 2022, 69
[32]   A rapid machine learning-based damage detection algorithm for identifying the extent of damage in concrete shear-wall buildings [J].
Mahmoudi, Hossein ;
Bitaraf, Maryam ;
Salkhordeh, Mojtaba ;
Soroushian, Siavash .
STRUCTURES, 2023, 47 :482-499
[33]   Structural damage detection and localization using decision tree ensemble and vibration data [J].
Mariniello, Giulio ;
Pastore, Tommaso ;
Menna, Costantino ;
Festa, Paola ;
Asprone, Domenico .
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING, 2021, 36 (09) :1129-1149
[34]   Investigation into machine learning with impedance SHM for damage detection and classification within simulated total knee replacements [J].
Miller, Brandon A. ;
Anton, Steven R. .
JOURNAL OF INTELLIGENT MATERIAL SYSTEMS AND STRUCTURES, 2022, 33 (19) :2405-2421
[35]   A System Identification-Based Damage-Detection Method for Gravity Dams [J].
Mirtaheri, Masoud ;
Salkhordeh, Mojtaba ;
Mohammadgholiha, Masoud .
SHOCK AND VIBRATION, 2021, 2021
[36]   A computationally efficient crack detection approach based on deep learning assisted by stockwell transform and linear discriminant analysis [J].
Nguyen, Andy ;
Nguyen, Canh Long ;
Gharehbaghi, Vahidreza ;
Perera, Ruveen ;
Brown, Jason ;
Yu, Yang ;
Kalbkhani, Hashem .
STRUCTURES, 2022, 45 :1962-1970
[37]   A fast and robust method for damage detection of truss structures [J].
Nobahari, M. ;
Ghasemi, M. R. ;
Shabakhty, N. .
APPLIED MATHEMATICAL MODELLING, 2019, 68 :368-382
[38]   Two-Step Method for Instability Damage Detection in Tower Body of Transmission Structures [J].
Qu, Weilian ;
Song, Wanjun ;
Xia, Yong ;
Xu, Youlin ;
Qin, Wenke ;
Jiang, Zhicai .
ADVANCES IN STRUCTURAL ENGINEERING, 2013, 16 (01) :219-232
[39]   Genetic algorithms-based methodologies for design optimization of trusses [J].
Rajeev, S ;
Krishnamoorthy, CS .
JOURNAL OF STRUCTURAL ENGINEERING-ASCE, 1997, 123 (03) :350-358
[40]   Mine blast algorithm for optimization of truss structures with discrete variables [J].
Sadollah, Ali ;
Bahreininejad, Ardeshir ;
Eskandar, Hadi ;
Hamdi, Mohd .
COMPUTERS & STRUCTURES, 2012, 102 :49-63