This study presents a novel approach for autonomous bolt-loosening monitoring by integrating computer-aided design (CAD)-assisted PointNet deep learning and three-dimensional (3D) point cloud processing. The following approaches are implemented to achieve the objective. First, a procedure of CAD-assisted databank generation for PointNet deep learning models is proposed. The CAD-generated databank contains diverse and well-labeled 3D point clouds of a bolt connection of steel girder with variation in loosening conditions. Second, PointNet segmentation and classification models are trained based on CAD-generated databank. The PointNet segmentation model is used to identify bolts from 3D point cloud, and PointNet classification models are used to identify bolt head angles and loosening lengths. Third, the CAD-assisted PointNet models are validated on real-world 3D point clouds of a steel girder bolt connection under various bolt-loosening levels. To enhance the performance of PointNet deep learning, advanced 3D point cloud processing techniques such as representative orientation alignment, bolt isolation using K-means clustering, and best-fitting rectangle for bolt group identification are introduced. Experimental results demonstrated that the proposed method effectively identifies bolt-loosening angles with high accuracy.
ZadoksRYuX.An investigation of the self-loosening behavior of bolts under transverse vibration. J Sound Vib1997; 208(2): 189–209.
2.
DingerGFriedrichC.Avoiding self-loosening failure of bolted joints with numerical assessment of local contact state. Eng Fail Anal2011; 18(8): 2188–2200.
3.
WangTSongGLiuS, et al. Review of bolted connection monitoring. Int J Distrib Sens Netw2013; 9(12): 871213.
4.
ValdezRPalaciosETutivénC, et al. Bolt-loosening detection in offshore wind turbines’ jacket-type supports. Struct Health Monit2024; 24(4): 14759217241268522.
5.
ZhangYSunXLohKJ.Automated vision-based bolt loosening detection and localization for steel structures. Struct Health Monit2024: 24(2): 123–135.
6.
PavelkoIPavelkoVKuznetsovS, et al. Bolt-joint structural health monitoring by the method of electromechanical impedance. Aircr Eng Aerosp Technol2014; 86(3): 207–214.
7.
HuynhTCDangNLKimJT.Preload monitoring in bolted connection using piezoelectric-based smart interface. Sensors2018; 18(9): 2766.
8.
NaWS.Bolt loosening detection using impedance based non-destructive method and probabilistic neural network technique with minimal training data. Eng Struct2021; 226: 111228.
9.
NguyenTTTaQBHoDD, et al. A method for automated bolt loosening monitoring and assessment using [b1] impedance technique and deep learning. Dev Built Environ2023; 14: 100122.
10.
FengYLanJYuanY, et al. Bolt looseness fault diagnosis of GIS based on vibration signal amplitude. J Phys Conf Ser2018; 1074(1): 012132.
11.
HudaFKajiwaraIHosoyaN, et al. Bolt loosening analysis and diagnosis by non-contact laser excitation vibration tests. Mech Syst Signal Process2013; 40(2): 589–604.
12.
DengSWangTTanB, et al. Theoretical and experimental study on FBG bending sensor for quantitative monitoring of bolt looseness. Measurement2023; 216: 113002.
13.
XuCWuGDuF, et al. A modified time reversal method for guided wave based bolt loosening monitoring in a lap joint. J Nondestruct Eval2019; 38: 1–13.
14.
YuanBSunWWangY, et al. Study on bolt preload measurement: An error compensation model for ultrasonic detection based on solid coupling. Measurement2023; 221: 113484.
15.
NicholsJMTrickeySTSeaverM, et al. Using ambient vibrations to detect loosening of a composite-to-metal bolted joint in the presence of strong temperature fluctuations. J Vib Acoust2007; 129(6): 710–717.
16.
SanliADemirkaleBKanounO.Real-time detection of loosening torque in bolted joints using piezoresistive pressure-sensitive layer based on multi-walled carbon nanotubes reinforced epoxy nanocomposites. Sci Rep2025: 15(1): 4830.
17.
AgdasDRiceJAMartinezJR, et al. Comparison of visual inspection and structural-health monitoring as bridge condition assessment methods. J Perform Constr Facil2016; 30(3): 04015049.
18.
ChaYJYouKChoiW.Vision-based detection of loosened bolts using the Hough transform and support vector machines. Autom Constr2016; 71: 181–188.
19.
RamanaLChoiWChaYJ.Fully automated vision-based loosened bolt detection using the Viola–Jones algorithm. Struct Health Monit2019; 18(2): 422–434.
20.
ZhangYSunXLohKJ, et al. Autonomous bolt loosening detection using deep learning. Struct Health Monit2020; 19(1): 105–122.
21.
HuynhTCParkJHJungHJ, et al. Quasi-autonomous bolt loosening detection method using vision-based deep learning and image processing. Autom Constr2019; 105: 102844.
22.
HuynhTC.Vision-based autonomous bolt-looseness detection method for splice connections: design, lab-scale evaluation, and field application. Autom Constr2021; 124: 103591.
23.
ParkJHHuynhTCChoiSH, et al. Vision-based technique for bolt loosening detection in wind turbine tower. Wind Struct2015; 21(6): 709–726.
LiSLeYGaoJ, et al. Bolt loosening angle measurement along full range of screw exposure length based on 3D point cloud. Autom Constr2024; 168: 105785.
26.
PanXYangT.3D vision-based bolt loosening assessment using photogrammetry, deep neural networks, and 3D point-cloud processing. J Build Eng2023; 70: 106326.
27.
PanXTavasoliSYangT.Autonomous 3D vision-based bolt loosening assessment using micro aerial vehicles. Comput Aided Civ Infrastruct Eng2023; 38(17): 2443–2454.
28.
QiCRSuHMoK, et al. Pointnet: deep learning on point sets for 3d classification and segmentation. Proc IEEE Conf Comput Vis Pattern Recognit2017: 652–660.
29.
KazhdanMFunkhouserTRusinkiewiczS.Rotation invariant spherical harmonic representation of 3d shape descriptors. Symp Geom Process2003; 6: 156–164.
30.
WuZSongSKhoslaA, et al. 3D shapenets: a deep representation for volumetric shapes. Proc IEEE Conf Comput Vis Pattern Recognit2015: 1912–1920.
31.
MaturanaDSchererS. Voxnet: a 3D convolutional neural network for real-time object recognition. In: 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS), Harburg, 28 September 2015, pp. 922–928.
32.
QiCRSuHNießnerM, et al. Volumetric and multi-view CNNs for object classification on 3D data. Proc IEEE Conf Comput Vis Pattern Recognit2016: 5648–5656.
33.
SuHMajiSKalogerakisE, et al. Multi-view convolutional neural networks for 3D shape recognition. Proc IEEE Int Conf Comput Vis2015: 945–953.
34.
ArthurDVassilvitskiiS.K-means++: the advantages of careful seeding. In: Proceedings of the 8th annual ACM-SIAM symposium on discrete algorithms, New Orleans, 7–9 January 2007, pp. 1027–1035. Standford.
35.
QiCRYiLSuH, et al. Pointnet++: deep hierarchical feature learning on point sets in a metric space. Adv Neural Inf Process Syst2017; 30: 5105–5144.
36.
QianGLiYPengH, et al. Pointnext: revisiting pointnet++ with improved training and scaling strategies. Adv Neural Inf Process Syst2022; 35: 23192–23204.
37.
ZhaoHJiangLFuCW, et al. Pointweb: enhancing local neighborhood features for point cloud processing. Proc IEEE/CVF Conf Comput Vis Pattern Recognit2019: 5565–5573.
38.
WuWQiZFuxinL.Pointconv: deep convolutional networks on 3D point clouds. Proc IEEE/CVF Conf Comput Vis Pattern Recognit2019: 9621–9630.
