To address the issues of high concealment and difficult positioning of loose bolts in transmission towers, this paper proposes a new method for locating loose bolts in transmission towers. In this method, we divide the vibration response of the transmission tower into low-frequency signals of 2–25 Hz and high-frequency signals of 25–75 Hz. For the low-frequency signals, the single signal component is obtained by adaptive Chirp mode decomposition and uses the general demodulation transformation to deeply denoise the non-modal information. Since frequency characteristics themselves do not contain time information, considering the importance of time information for positioning, we propose a low-frequency time-varying frequency feature that preserves time characteristics based on synchronous wavelet transform and peak search. For the high-frequency signals, we use singular value decomposition to remove signal outliers caused by pulse excitation and eliminate forced vibrations through wavelet packet transform. Without altering its inherent characteristics, this method enables high-frequency time-domain signals to better represent the nonlinear characteristics of transmission towers. Furthermore, based on the powerful capabilities of Timesnet and Transformer in dealing with time series data, we propose a fault diagnosis model, which ultimately achieves the positioning of loose bolts in transmission towers. The bolt node model proves that this approach can better represent the loose bolt characteristics, and the transmission tower model verifies the effectiveness of this approach in locating loose bolts in transmission towers. Finally, bolt-loosening tests were conducted on a 110 kV transmission tower, and the accuracy of the positioning results reached 92.8%, demonstrating the effectiveness and efficiency of this method in practical positioning applications.
LaoWCuiCZhangD, et al. Computer vision-based autonomous method for quantitative detection of loose bolts in bolted connections of steel structures. Struct Control Health Monit2023; 2023: 8817058.
2.
HuynhTCParkJHJungHJ, et al. Quasi-autonomous bolt-loosening detection method using vision-based deep learning and image processing. Autom Constr2019; 105: 102844.
3.
HuynhTC. Vision-based autonomous bolt-looseness detection method for splice connections: design, lab-scale evaluation, and field application. Autom Constr2021; 124: 103591.
4.
NguyenTTTaQBHoDD, et al. A method for automated bolt-loosening monitoring and assessment using impedance technique and deep learning. Dev Built Environ2023; 14: 100122.
5.
NordTSPetersenØWHendrikseH. Stochastic subspace identification of modal parameters during ice–structure interaction. Phil Trans R Soc A2019; 377(2155): 20190030.
6.
WuXCaiYShiR, et al. Intelligent fault diagnosis of three-trans towers’ bolts based on EMD and LS-SVM. In: 2019 IEEE innovative smart grid technologies-Asia (ISGT Asia), Chengdu, China, 2019, pp. 3543–3548.
7.
HeBMengXQGuJJ, et al. HHT for vibration signal analysis in tower bolt looseness detection. In: 2020 International conference on wireless communications and smart grid (ICWCSG), Hangzhou, China, 2020, pp. 28–31.
8.
ZhaoYXiaoYWangH, et al. Effect of bolt tightening force on the transmission tower modal parameters and a method for looseness identification. Energy Rep2021; 7: 842–849.
9.
JiBXiongQXingP, et al. Bolt loosening localization at flange joints using wind-induced response for high-rise tower. Int J Steel Struct2021; 21(5): 1790–1803.
10.
LuoYLiuXZhouB, et al. State identification of three-trans towers’ bolts based on quadratic wavelet transform and KNN. In: Recent featured applications of artificial intelligence methods. LSMS 2020 and ICSEE 2020 Workshops, Shanghai, China2020, pp. 169–183.
11.
WenGZhaoLLiuZ, et al. Research on loose bolt localization technology for transmission towers. Struct Health Monit2024: 14759217231218175.
12.
DangHVRazaMNguyenTV, et al. Deep learning-based detection of structural damage using time-series data. Struct Infrastruct Eng2021; 17(11): 1474–1493.
13.
LimongelliMPManoachEQuqaS, et al. Vibration response-based damage detection. Struct Health Monit Damage Detection Syst Aerospace2021; 133: https://doi.org/10.1007/978-3-030-72192-3.
14.
ZuoHGuoH. Nonlinear damage identification method of transmission tower structure based on general expression for linear and nonlinear autoregressive model and Itakura distance. Struct Health Monit2023; 22(1): 19–38.
15.
HouRXiaY. Review on the new development of vibration-based damage identification for civil engineering structures: 2010–2019. J Sound Vibr2021; 491: 115741.
16.
ZhangCMousaviAAMasriSF, et al. Vibration feature extraction using signal processing techniques for structural health monitoring: a review. Mech Syst Signal Process2022; 177: 109175.
17.
WangXShahzadMM. A novel structural damage identification scheme based on deep learning framework. Structures2021; 29: 1537–1549.
18.
AvciOAbdeljaberOKiranyazS, et al. A review of vibration-based damage detection in civil structures: from traditional methods to machine learning and deep learning applications. Mech Syst Signal Process2021; 147: 107077.
19.
SoleimanpourRSoleimaniSMMohammadNK. Damage detection and localization in loose bolted joints. Procedia Struct Integr2022; 37: 956–963.
20.
SonySGamageSSadhuA, et al. Vibration-based multiclass damage detection and localization using long short-term memory networks. Structures2022; 35: 436–451.
21.
ZhangSLiCMYeW. Damage localization in plate-like structures using time-varying feature and one-dimensional convolutional neural network. Mech Syst Signal Process2021; 147: 107107.
22.
ZouXMuHQuL, et al. Localization and assessment of breakage defect in cables based on time–frequency domain reflectometry. Energy Rep2022; 8: 1474–1481.
23.
AndreausUCasiniPVestroniF. Non-linear dynamics of a cracked cantilever beam under harmonic excitation. Int J Non-Linear Mech2007; 42(3): 566–575.
24.
FanGLiJHaoH. Vibration signal denoising for structural health monitoring by residual convolutional neural networks. Measurement2020; 157: 107651.
25.
JinZHeDWeiZ. Intelligent fault diagnosis of train axle box bearing based on parameter optimization VMD and improved DBN. Eng Appl Artif Intell2000; 110: 104713.
26.
ChenSDongXPengZ, et al. Nonlinear chirp mode decomposition: a variational method. IEEE Trans Signal Process2017; 65(22): 6024–6037.
27.
OlhedeSWaldenAT. A generalized demodulation approach to time-frequency projections for multicomponent signals. Proc R Soc A: Math Phys Eng Sci2005; 461(2059): 2159–2179.
28.
SinghPSadhuA. A hybrid time-frequency method for robust drive-by modal identification of bridges. Eng Struct2022; 266: 114624.
29.
XuLChattertonSPennacchiP. Rolling element bearing diagnosis based on singular value decomposition and composite squared envelope spectrum. Mech Syst Signal Process2021; 148: 107174.
30.
SunHSiQChenN, et al. HHT-based feature extraction of pump operation instability under cavitation conditions through motor current signal analysis. Mech Syst Signal Process2020; 139: 106613.
31.
Rohani BastamiABashariA. Rolling element bearing diagnosis using spectral kurtosis based on optimized impulse response wavelet. J Vibr Control2020; 26(3–4): 175–185.
32.
TarinejadRDamadipourM. Modal identification of structures by a novel approach based on FDD-wavelet method. J Sound Vibr2014; 333(3): 1024–1045.
33.
ZhouJLiZChenJ. Application of two dimensional Morlet wavelet transform in damage detection for composite laminates. Compos Struct2023; 318: 117091.
WuHHuTLiuY, et al. Timesnet: temporal 2D-variation modeling for general time series analysis. arXiv preprintarXiv: 2210.02186, 2022.
42.
HuangJLiuJGongH, et al. A comprehensive review of loosening detection methods for threaded fasteners. Mech Syst Signal Process2022; 168: 108652.
43.
DuanXFengZ. Time-varying filtering for nonstationary signal analysis of rotating machinery: principle and applications. Mech Syst Signal Process2023; 192: 110204.
44.
ZhaoLWenGLiuZ, et al. Method for extracting the free vibration response of transmission tower. Meas Sci Technol2023; 35(2): 025017.
45.
LvPWuXZhaoY, et al. Noise removal for semi-airborne data using wavelet threshold and singular value decomposition. J Appl Geophys2022; 201: 104622.
46.
CacceseVMewerRVelSS. Detection of bolt load loss in hybrid composite/metal bolted connections. Eng Struct2004; 26(7): 895–906.
47.
ZhaoYXiaoYWangH, et al. Effect of bolt tightening force on the transmission tower modal parameters and a method for looseness identification. Energy Rep2021; 7: 842–849.
48.
Jia-XiangLJin-PengCChaoZ, et al. Seismic response study of a steel lattice transmission tower considering the hysteresis characteristics of bolt joint slippage. Eng Struct2023; 281: 115754.
49.
LeeCYHuangNEChernCC, et al. A study on the dynamic characteristics and ultimate capacity of steel transmission towers. J Chin Inst Eng2013; 36(3): 273–294.
50.
LiuZHuangXZhaoL, et al. Research on online monitoring technology for transmission tower bolt looseness. Measurement2023; 223: 113703.
51.
HuynhTCParkYHParkJH, et al. Effect of temperature variation on vibration monitoring of prestressed concrete girders. Shock Vibr2015; 2015: 741618.
52.
HuangXZhaoYZhaoL, et al. A method for settlement detection of the transmission line tower under wind force. Sensors2018; 18(12): 4355.
53.
HuangTZhangQTangX, et al. A novel fault diagnosis method based on CNN and LSTM and its application in fault diagnosis for complex systems. Artif Intell Rev2022; 55: 1289–1315.
54.
ZhangYZhouTHuangX, et al. Fault diagnosis of rotating machinery based on recurrent neural networks. Measurement2021; 171: 108774.
55.
WangXLiuXWangJ, et al. Improved variational mode decomposition and one-dimensional CNN network with parametric rectified linear unit (PReLU) approach for rolling bearing fault diagnosis. Appl Sci2022; 12(18): 9324.
56.
GaoSLiTZhangY, et al. Fault diagnosis method of rolling bearings based on adaptive modified CEEMD and 1DCNN model. ISA Trans2023; 140: 309–330.
57.
CuiHGuanYChenH. Rolling element fault diagnosis based on VMD and sensitivity MCKD. IEEE Access2021; 9: 120297–120308.
