Threaded fasteners are widely applied in mechanical systems, providing the functions of connection, fastening, and sealing. However, loosening is vulnerable to occurring in harsh environment. The importance of loosening detection cannot be emphasized. Percussion-based loosening detection method has attracted much attention due to the convenience and low cost. However, the simultaneous loosening detection of multiple-threaded fasteners based on percussion method is still a challenging issue that needs to be addressed. This study proposes a novel multi-bolt loosening detection method combining percussion method, and deep learning. The method consists of three integrated modules, that is, signal preprocessing, loosening information enhancement, and loosening detection modules. In the first module, variational mode decomposition is used to decompose the original signal into a series of intrinsic mode function to eliminate the interference of noise. In the second module, compressive sampling matching pursuit is applied to represent the denoised signal sparsely, and the sparse signal is fused with the denoised signal to enhance loosening information in the signal. Last, DenseNet-CBAM network structure combining attention mechanism is proposed for multiple classification task. Experimental results showed that the proposed method achieved the detection accuracy of more than 97% in three different types of mechanical structures with multiple-threaded fasteners, indicating its great potentials in engineering applications.
LinQZhaoYSunQ. Reliability evaluation method of anti-loosening performance of bolted joints. Mech Syst Signal Pr2022; 162: 108067.
2.
GongHDengXLiuJ. Quantitative loosening detection of threaded fasteners using vision-based deep learning and geometric imaging theory. Automat Constr2022; 133: 104009.
3.
HuZTariqSZayedT. A comprehensive review of acoustic based leak localization method in pressurized pipelines. Mech Syst Signal Pr2021; 161: 107994.
4.
LiCJiangYQiaoR, et al. Modeling and parameters identification of the connection interface of bolted joints based on an improved micro-slip model. Mech Syst Signal Pr2021; 153: 107514.
5.
QinXPengCZhaoG, et al. Full life-cycle monitoring and earlier warning for bolt joint loosening using modified vibro-acoustic modulation. Mech Syst Signal Pr2022; 162: 108054.
6.
EcclesW. Tribological aspects of the self-loosening of threaded fasteners. PhD Thesis, University of Central Lancashire, 2010.
7.
GongHDingXLiuJ, et al. Review of research on loosening of threaded fasteners. Friction2022, 10: 335–359.
8.
HuangJHuaJGongH, et al. A comprehensive review of loosening detection methods for threaded fasteners. Mech Syst Signal Pr2022; 168: 108652.
9.
GongHHuangJHuaJ, et al. Proof-of-concept study of high-order sideband for bolt loosening detection using vibroacoustic modulation method. Mech Syst Signal Pr2022; 16: 108639.
10.
ZhangXWangHHouB. 1D-CNN-based damage identification method based on piezoelectric impedance using adjustable inductive shunt circuitry for data enrichment. Struct Health Monitor2022; 21(5):1992–2009.
11.
ChenMXuB. Bolted joint looseness damage detection using electro-mechanical impedance measurements by PZT sensors. In: Proceedings of SPIE – The International Society for Optical Engineering, Shenzhen, China, 2011, vol. 8409, 2012, 840925.
12.
RyuJYHuynhTCKimJT. Tension force estimation in axially loaded members using wearable piezoelectric interface technique. Sensors2018; 19(1): 47.
13.
HuynhTCNguyenTDHoDD. Sensor fault diagnosis for impedance monitoring using a piezoelectric-based smart interface technique. Sensors2020; 20(2): 510.
14.
SunQYuanBMuX. Bolt preload measurement based on the acoustoelastic effect using smart piezoelectric bolt. Smart Mater Struct2019; 28(5): 055005.
15.
WangTLiuSShaoJ. Health monitoring of bolted joints using the time reversal method and piezoelectric transducers. Smart Mater Struct2016; 25(2): 025010.
16.
HongXSongGRuanJ. Active monitoring of pipeline tapered thread connection based on time reversal using piezoceramic transducers. Smart Struct Syst2016; 18(4): 643–662.
17.
LiangYLiDKongQ. Load monitoring of the pin-connected structure using time reversal technique and piezoceramic transducers—A feasibility study. IEEE Sens J2016; 16(22): 7958–7966.
18.
ZhangZLiuMSuZ, et al. Quantitative evaluation of residual torque of a loose bolt based on wave energy dissipation and vibro-acoustic modulation: a comparative study. J Sound Vib2016; 383: 156–170.
19.
ZhangZXuHLiaoY. Vibro-acoustic modulation (VAM)-inspired structural integrity monitoring and its applications to bolted composite joints. Compos Struct2017; 176: 505–515.
20.
ZhangZLiuMLiaoY. Contact acoustic nonlinearity (CAN)-based continuous monitoring of bolt loosening: hybrid use of high-order harmonics and spectral sidebands. Mech Syst Signal Pr2018; 103: 280–294.
21.
ZhouWShenYXiaoL, et al. Application of nonlinear-modulation technique for the detection of bolt loosening in frame structure. J Test Eval2016; 44(2): 967–975.
22.
WangF. Multi-bolt looseness detection using a new acoustic emission strategy. Struct Health Monit2022; 22(3): 1543–1553.
23.
FierroGMeoM. IWSHM 2017: structural health monitoring of the loosening in a multi-bolt structure using linear and modulated nonlinear ultrasound acoustic moments approach. Struct Health Monit2018; 17(6): 1349–1364.
ParkJHHuynhTCChoiSH. Vision-based technique for bolt-loosening detection in wind turbine tower. Wind Struct2015; 21(6): 709–726.
26.
HuynhTC. Vision-based autonomous bolt-looseness detection method for splice connections: design, lab-scale evaluation, and field application. Autom Constr2021; 124: 103591.
27.
HuynhTCParkJHJungHJ. Quasi-autonomous bolt-loosening detection method using vision-based deep learning and image processing. Automat Constr2019; 105: 102844.
28.
WangCWangNHoSC. Design of a new vision-based method for the bolts looseness detection in flange connections. IEEE T Ind Electron2019; 67(2): 1366–1375.
29.
ZhaoXZhangYWangN. Bolt loosening angle detection technology using deep learning. Struct Health Monit2019; 26(1): e2292.1–e2292.14.
30.
YangZHuoL. Bolt preload monitoring based on percussion sound signal and convolutional neural network (CNN). Nondestruct Test Eva2022; 37(4): 464–481.
31.
ZhouYWangSZhouM, et al. Percussion-based bolt looseness identification using vibration-guided sound reconstruction. Struct Control Health2022; 29(2): e2867.
32.
ZhangYZhaoXSuW. Audio-based bolt-loosening detection technique of bolt joint. In: Nondestructive characterization and monitoring of advanced materials. Aerospace, Civil Infrastructure, and Transportation XII, International Society for Optics and Photonics, 2018.
33.
KongQZhuJHoSCM. Tapping and listening: a new approach to bolt looseness monitoring. Smart Mater. Struct2018; 27(7): 07LT02.
34.
YuanRLvYKongQ. Percussion-based bolt looseness monitoring using intrinsic multiscale entropy analysis and BP neural network. Smart Mater. Struct2019; 28(12): 125001.
35.
WangFSongG. 1D-TICapsNet: an audio signal processing algorithm for bolt early looseness detection. Struct Health Monit2020; 20(5): 2828–2839.
36.
WangFSongG. Bolt-looseness detection by a new percussion-based method using multifractal analysis and gradient boosting decision tree. Struct Health Monit2020; 19(6): 2023–2032.
37.
WangFChenXSongG. Percussion-based detection of bolt looseness using speech recognition technology and least square support vector machine. In: 2020 IEEE International Conference on Networking, Sensing and Control (ICNSC), Nanjing, China, 30 October–2 November 2020, IEEE.
38.
ZhangYZhaoXSunX. Bolt loosening detection based on audio classification. Adv Struct Eng2019; 22(13): 2882–2891.
39.
WangFHoSCMSongG. Modeling and analysis of an impact-acoustic method for bolt looseness identification. Mech Syst Signal Pr2019; 133: 106249.
40.
WangFMobinyANguyenHV. If structure can exclaim: a novel robotic-assisted percussion method for spatial bolt-ball joint looseness detection. Struct Health Monit2020; 20(4): 1597–1608.
41.
WangFSongG. A novel percussion-based method for multi-bolt looseness detection using one-dimensional memory augmented convolutional long short-term memory networks. Mech Syst Signal Pr2021; 161: 107955.
42.
DragomiretskiyKZossoD. Variational mode decomposition. IEEE T Signal Proces2014; 62(3): 531–544.
43.
DonohoDL. Compressed sensing. IEEE T Inform Theory2006; 52(4): 1289–1306.
44.
NeedellDTroppJA. CoSaMP: iterative signal recovery from incomplete and inaccurate samples. Appl Comput Harmon A2009; 26(3): 301–321.
45.
HuangGLiuZLaurensVDM, et al. Densely connected convolutional networks. In: 30th IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, Hawaii, 21 July–26 July 2017, pp. 2261–2269.
46.
WOOSPAPKJLEEJ-Y, et al. CBAM: convolutional block attention module. In: 15th European Conference on Computer Vision (ECCV), Munich, Germany, 8 September–14 September 2018, pp. 3–19.
47.
RabinerLRSamburMR. The algorithm for determing the endpoints of isolated utterances. Bell Syst Techn J1975; 54(2): 297–315.
48.
HuangNYuanCCaiG, et al. Hybrid short term wind speed forecasting using variational mode decomposition and a weighted regularized extreme learning machine. Energies2016; 9(12): 989.
49.
CostaMGoldbergerALPengCK. Multiscale entropy analysis of complex physiologic time series. Phys Rev Lett2002; 89(6): 068102.
50.
HeKZhangXRenS, et al. Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, 27 June–30 June 2016.
51.
ZeilerMDFergusR. Visualizing and understanding convolutional networks. In: 13th European conference on computer vision (ECCV), Zurich, Switzerland, 5 September–12 September 2014, pp. 818–833.
