[1]马骥腾,徐佳文,吕卫民.玻璃幕墙紧固件松动实时监测方法[J].华侨大学学报(自然科学版),2025,46(5):606-612.[doi:10.11830/ISSN.1000-5013.202505045]
　MA Jiteng,XU Jiawen,LYU Weimin.Real-Time Monitoring Method of Fastener Looseness in Glass Curtain Walls[J].Journal of Huaqiao University(Natural Science),2025,46(5):606-612.[doi:10.11830/ISSN.1000-5013.202505045]
点击复制

玻璃幕墙紧固件松动实时监测方法()
分享到：

《华侨大学学报（自然科学版）》[ISSN:1000-5013/CN:35-1079/N]

卷:
第46卷
期数:
2025年第5期
页码:
606-612
栏目:
出版日期:
2025-09-20

文章信息/Info

Title:
Real-Time Monitoring Method of Fastener Looseness in Glass Curtain Walls
文章编号:
1000-5013(2025)05-0606-07
作者:
马骥腾1;  徐佳文2;  吕卫民1
1. 海军航空大学, 山东 烟台 264001;2. 东南大学 仪器科学与工程学院, 江苏 南京 210096
Author(s):
MA Jiteng1;  XU Jiawen2;  LYU Weimin1
1. Naval Aviation University, Yantai 264001, China; 2. School of Instrument Science and Engineering, Southeast University, Nanjing 210096, China
关键词:
紧固件松动;  玻璃幕墙监测;  压电阻抗法;  卷积神经网络;  迁移学习
Keywords:
fastener looseness;  glass curtain wall monitoring;  piezoelectric impedance method;  convolutional neural network;  transfer learning
分类号:
TH703
DOI:
10.11830/ISSN.1000-5013.202505045
文献标志码:
A
摘要:
为实现对玻璃幕墙螺栓紧固件持续且通用监测,采用压电阻抗法获得玻璃幕墙不同螺栓松动状态下的结构阻抗数据,再利用卷积神经网络提取玻璃幕墙源域的结构特征,最后把该特征迁移到新玻璃幕墙目标域的方法对其进行健康状态的识别。结果表明:在样本较小的情况下,基于1D-CNN模型的迁移学习方法,显著提高玻璃螺栓结构的螺栓松动识别的准确性,准确率最高可达100%;该方法有利于玻璃幕墙故障状态的实时、准确与有效的诊断。
Abstract:
To achieve continuous and universal monitoring of bolts fasteners in glass curtain walls, the piezoelectric impedance method is adopted to obtain structural impedance data under different bolt loosening states. A convolutional neural network is then used to extract the structural features from the source domain of the glass curtain wall, which are subsequently transferred to the target domain of a new glass curtain wall for health status identification. The results show that, even with a small number of samples, the transfer learning method based on the 1D-CNN model significantly improves the accuracy of bolt loosening identification for glass bolt structures, achieving a maximum accuracy of 100%. This method enables real-time, accurate, and effective diagnosis of fault states in glass curtain walls.

参考文献/References:

[1] BOUDEN C.Influence of glass curtain walls on the building thermal energy consumption under Tunisian climatic conditions: The case of administrative buildings [J].Renewable Energy,2007,32(1):141-156.DOI:10.1016/j.renene.2006.01.007.
[2] 冯若强,武岳,沈世钊.考虑玻璃参与工作的单层平面索网幕墙结构静力性能研究[J].建筑结构学报,2005,26(4):99-106.DOI:10.3321/j.issn:1000-6869.2005.04.016.
[3] DI Peng,YU Chenlong.Safety analysis of point supported glass curtain wall panels[C]//Proceedings of the International Conference on Sustainable Energy & Environmental Engineering.Shenzhen:Atlantis Press,2016:1140-1144.DOI:10.2991/icseee-15.2016.202.
[4] WONGI S N,JONGDAE B A.Review of the piezoelectric electromechanical impedance based structural health monitoring ttechnique for engineering structures [J].Sensors,2018,18(5):1307.DOI:10.3390/s18051307.
[5] QING Xiaolong,LI Wenzhen,WANG Yongsheng,et al.Piezoelectric transducer-based structural health monitoring for aircraft applications [J].Sensors,2019,19(3):545.DOI:10.3390/s19030545.
[6] NEGI P,CHAKRABORTY T,KAUR N,et al.Investigations on effectiveness of embedded PZT patches at varying orientations for monitoring concrete hydration using EMI technique[J].Construction and Building Materials,2018,169:489-498.DOI:10.1016/j.conbuildmat.2018.03.006.
[7] CAO Pei,SHUAI Qi,TANG Jiong.Structural damage identification using piezoelectric impedance measurement with sparse inverse analysis[J].Smart Materials & Structures,2018,27(3):035020.DOI:10.1088/1361-665X/aaacba.
[8] 徐云飞,孙永顺,丁晓喜,等.基于Lamb波的数据传输与缺陷检测同步实现方法[J].仪器仪表学报,2022,43(3):24-31.DOI: 10.19650/j.cnki.cjsi.J2108407.
[9] MICHAELS J E,MICHAELS T E.Guided wave signal processing and image fusion for in situ damage localization in plates [J].Wave Motion,2007,44(6):482-492.DOI:10.1016/j.wavemoti.2007.02.008.
[10] KODURU J P,ROSE J L.Transducer arrays for omnidirectional guided wave mode control in plate like structures [J].Smart Materials and Structures,2013,22(1):015010.DOI:10.1088/0964-1726/22/1/015010.
[11] MORI N,BIWA S,KUSAKA T.Damage localization method for plates based on the time reversal of the mode-converted Lamb waves [J].Ultrasonics,2019,91:19-29.DOI:10.1016/j.ultras.2018.07.007.
[12] 叶亮,张有忱,丁克勤,等.基于压电阻抗法的机械螺栓组松动监测及识别[J].科学技术与工程,2013,13(18):5172-5176.DOI:10.3969/j.issn.1671-1815.2013.18.017.
[13] WANG Furui,HO S C M,HUO Linsheng,et al.A novel fractal contact-electromechanical impedance model for quantitative monitoring of bolted joint looseness[J].IEEE Access,2018,6:40212-40220.DOI:10.1109/ACCESS.2018.2855693.
[14] ZHANG Xin,WANG Hui,HOU Borui,et al.1D-CNN-based damage identification method based on piezoelectric impedance using adjustable inductive shunt circuitry for data enrichment[J].Structural Health Monitoring,2022,21(5):1992-2009.DOI:10.1177/14759217211049720.
[15] NA W S.Distinguishing crack damage from debonding damage of glass fiber reinforced polymer plate using a piezoelectric transducer based nondestructive testing method [J].Composite Structures,2017,159:517-527.DOI:10.1016/j.compstruct.2016.10.005.
[16] LI Lili,LIU Gang,ZHANG Liangliang,et al.FS-LSTM-based sensor fault and structural damage Isolation in SHM [J].IEEE Sensors Journal,2021,21(3):3250-3259.DOI:10.1109/JSEN.2020.3022099.
[17] LI Ziqi,LI Dongsheng,SUN Tianshu.A transformer-based bridge structural response prediction framework [J].Sensors,2022,22(8):3100.DOI: 10.3390/s22083100.
[18] DE OLIVEIRA M A,MONTEIRO A V,FILHO J V.A new structural health monitoring strategy based on PZT sensors and convolutional neural network[J].Sensors,2018,18(9):2955.DOI:10.3390/s18092955.
[19] 于洋,何明,刘博,等.基于TL-LSTM的轴承故障声发射信号识别研究[J].仪器仪表学报,2019,40(5):51-59.
[20] SHAO Weihan,SUN Hu,WANG Yishou,et al.A multi-level damage classification technique of aircraft plate structures using Lamb wave-based deep transfer learning network[J].Smart Materials and Structures,2022,31(7):075019.DOI:10.1088/1361-665X/ac726f.
[21] HESSER D F,MOSTAFAVI S,KOCUR G K,et al.Identification of acoustic emission sources for structural health monitoring applications based on convolutional neural networks and deep transfer learning[J].Neurocomputing,2021,453:1-12.DOI:10.1016/j.neucom.2021.04.108.
[22] WANG X,TANG J.Damage detection using piezoelectric admittance approach with inductive circuitry[J].Journal of Intelligent Material Systems and Structures,2010,21(7):667-676.DOI:10.1177/1045389X10364863.
[23] KIM J,WANG K W.An enhanced impedance-based damage identification method using adaptive piezoelectric circuitry [J].Smart Materials and Structures,2014,23(9):095041.DOI:10.1088/0964-1726/23/9/095041.
[24] KRIZHEVSKY A,SUTSKEVER I,HINTON G E.Imagenet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60(6):84-90.DOI:10.1145/3065386.
[25] 王震,黄如意,李霁蒲,等.一种用于故障分类与预测的多任务特征共享神经网络[J].仪器仪表学报,2019,40(7):169-177.DOI:10.19650/j.cnki.cjsi.J1905096.
[26] PAN S J,YANG Qiang.A Survey on transfer learning [J].IEEE Transactions on Knowledge and Data Engineering,2010,22(10):1345-1359.DOI: 10.1109/TKDE.2009.191.
[27] WEI Fengmei,ZHANG Jianpei,YAN Chu,et al.FSFP: Transfer learning from long texts to the short [J].Applied Mathematics and Information Sciences,2014,8(4):2033-2040.DOI:10.12785/amis/080462.

备注/Memo

备注/Memo:
收稿日期: 2025-05-04
通信作者: 徐佳文(1986-),男,副教授,博士,博士生导师,主要从事机械设备故障诊断的研究。E-mail:jiawen.xu@seu.edu.cn。
基金项目: 国家自然科学基金资助项目(52472442)
更新日期/Last Update: 2025-09-20