Structural vibrations in the supporting foundations of rotating machinery can significantly affect system performance and longevity, yet damage to these structures is often overlooked as a key factor in reducing the operational life of rotating systems. In this study, structural damage is experimentally introduced through small modifications affecting stiffness and proportional damping. Vibrational data measured at the bearings is then analyzed in both the time and frequency domains to detect and classify these faults. Using convolutional neural networks (CNNs), high classification accuracies are achieved, particularly with acceleration signals in both domains. Simpler CNN models, such as a three-layer network, show performance comparable to more complex architectures while offering faster training times and greater practicality. These results demonstrate that CNN-based methods can effectively automate structural health monitoring, providing a robust alternative to traditional techniques like operational modal analysis, and enhancing real-time maintenance strategies for rotating machinery.
CavalcaKL.L’interazione tra rotori e struttura portante: metodologie per la sua modellazione. PhD Thesis, Politecnico di Milano, Italy, 1993.
2.
OkabeEP.Interação rotor-estrutura: modelo teórico-experimental. PhD Thesis, Universidade Estadual de Campinas (UNICAMP), Brazil, 2007.
3.
Saint MartinLB. Interação entre rotor e fundação flexível sujeita a variações estruturais. PhD Thesis, Universidade Estadual de Campinas (UNICAMP), Brazil, 2020.
4.
CavalcaKLOkabeEPCavalcantePF. An experimental analysis of rotors on flexible structures. In: Sixth IFToMM. Sydney, Australia: UNSW Printing Services, 2002, pp. 531–538.
5.
SinhaJKFriswellMILeesAW.The identification of the unbalance and the foundation model of a flexible rotating machine from a single run-down. Mech Syst Signal Process2002; 16: 255–271.
6.
LeesAWEdwardsSFriswellMI. The estimation of foundation parameters and unbalance. In: 7th international conference on vibrations in rotating machinery (IMechE), Nottingham, UK, 12–14 September 2000, pp. 31–41.
7.
CavalcaKLOkabeEP. On the analysis of rotor-bearing-foundation systems. In: IUTAM symposium on emerging trends in rotor dynamics 2009, Dordrecht, Netherlands, 23–29 March 2009, pp. 89–101.
8.
LiuWNovakM.Dynamic behavior of turbine-generator-foundation systems. Int J Rock Mech Mining Sci Geom1995; 24(3): 339–360.
9.
GentaG.Dynamics of rotating systems. New York, NY: Springer, 2005.
10.
FriswellMIPennyJETGarveySD, et al. Dynamics of rotating machines. 1st ed. Cambridge, UK: Cambridge University Press, 2010.
11.
MartiniVMOkabeEPCavalcaKL. Experimental modal analysis in a rotating machine foundation and its implications in a simple case of dynamic substructuring. In: Proceedings of the ISMA-USD2022 conference, Leuven, Belgium, 12–14 September 2022.
12.
EwinsDJ.Modal testing: theory, practice, and application. 2nd ed. Baldock, Hertfordshire, UK: Research Studies Press, 2000.
13.
MartiniVMOkabeEPCavalcaKL. Dynamic decoupling of a bearing support structure: comparison of four different decoupling methods based on a dual approach. In: 9th international operational modal analysis conference, Vancouver, Canada, 3–6 July 2022.
14.
MartiniVMOkabeEPCavalcaKL.On the experimental dynamic substructuring of rotating machine foundations. Mech Syst Signal Proc2024; 206: 110921.
15.
FarrarCRDoeblingSW.Damage detection and evaluation II: field applications to large structures. In: NATO advanced study institute on modal analysis and testing, Sesimbra, Portugal, 3–15 May 1998, pp. 345–378.
16.
ModarresCAstorgaNDroguettEL, et al. Convolutional neural networks for automated damage recognition and damage type identification. Struct Control Health Monit2018; 25: e2230.
17.
VerstraeteDFerradaADroguettEL, et al. Deep learning enabled fault diagnosis using time-frequency image analysis of rolling element bearings. Shock Vibr2017; 2017: 1–17.
18.
LinYNieZMaH.Structural damage detection with automatic feature-extraction through deep learning. Comput Aided Civ Infrastruct Eng2017; 32: 1025–1046.
19.
DosovitskiyABeyerLKolesnikovA, et al. An image is worth 16×16 words: transformers for image recognition at scale. In: The 9th international conference on learning representations (ICLR), Austria, 3–7 May 2021.
20.
KrizhevskyASutskeverIHintonGE.ImageNet classification with deep convolutional neural networks. Commun ACM2017; 60: 84–90.
21.
GoodfellowIBengioYCourvilleA.Deep learning. Cambridge, MA: The MIT Press, 2016.
22.
KhodabandehlouHPekcanGFadaliMS.Vibration-based structural condition assessment using convolution neural networks. Struct Control Health Monit2019; 26: e2308.
23.
ChaY-JChoiWBüyüköztürkO.Deep learning-based crack damage detection using convolutional neural networks: deep learning-based crack damage detection using CNNs. Comput Aided Civ Infrastruct Eng2017; 32: 361–378.
24.
RaoASNguyenTPalaniswamiM, et al. Vision-based automated crack detection using convolutional neural networks for condition assessment of infrastructure. Struct Health Monit2021; 20: 2124.
25.
YuYHoshyarANSamaliB, et al. Corrosion and coating defect assessment of coal handling and preparation plants (CHPP) using an ensemble of deep convolutional neural networks and decision-level data fusion. Neural Comput Appl2023; 35: 18697–18718.
26.
ZhangJJinZTengS, et al. Structural damage detection using convolutional neural networks based on modal strain energy and population of structures. Int J Comput Methods2023; 20: 2230001.
27.
TengSChenXChenG, et al. Structural damage detection based on convolutional neural networks and population of bridges. Measurement2022; 202: 111747.
28.
WangLYiSYuY, et al. Automated ultrasonic-based diagnosis of concrete compressive damage amidst temperature variations utilizing deep learning. Mech Syst Signal Proc2024; 221: 111719.
29.
TengSChenGGongP, et al. Structural damage detection using convolutional neural networks combining strain energy and dynamic response. Meccanica2020; 55: 945–959.
30.
TranV-LVoT-CNguyenT-Q.One-dimensional convolutional neural network for damage detection of structures using time series data. Asian J Civ Eng2024; 25: 827–860.
31.
AlazzawiOWangD.A novel structural damage identification method based on the acceleration responses under ambient vibration and an optimized deep residual algorithm. Struct Health Monit2022; 21: 2587–2617.
32.
AzimiMEslamlouAPekcanG.Data-driven structural health monitoring and damage detection through deep learning: state-of-the-art review. Sensors2020; 20: 2778.
33.
LiYDuXWanF, et al. Rotating machinery fault diagnosis based on convolutional neural network and infrared thermal imaging. Chin J Aeron2020; 33: 427–438.
34.
ZhangYZhouTHuangX, et al. Fault diagnosis of rotating machinery based on recurrent neural networks. Measurement2021; 171: 108774.
35.
JanssensOSlavkovikjVVervischB, et al. Convolutional neural network based fault detection for rotating machinery. J Sound Vibr2016; 377: 331–345.
36.
JiaFLeiYLinJ, et al. Deep neural networks: a promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data. Mech Syst Signal Proc2016; 72–73: 303–315.
37.
Saint MartinLBGusmãoLLMachadoTH, et al. Operational modal analysis application to support structure identification under rotating machinery unbalance. Eng Struct2021; 249: 113344.
38.
StortiGCMartiniVMOkabeEP, et al. Enhancing structural health monitoring through automatic modal parameter identification for rotating machinery on flexible foundation structures. In: Proceedings of the 10th international operational modal analysis conference, Naples, Italy, 22–24 May 2024.
39.
ZhangYMiyamoriYMikamiS, et al. Vibration-based structural state identification by a 1-dimensional convolutional neural network. Comput Aided Civ Infrastruct Eng2019; 34: 822–839.
40.
GröchenigK.Foundations of time-frequency analysis. Boston, MA: Birkhäuser Boston, 2001.
41.
MitraSK.Digital signal processing: a computer-based approach. 2nd ed. Boston: McGraw-Hill/Irwin, 2001.
42.
SmithJO.Spectral audio signal processing. Stanford, CA: Stanford University, CCRMA, 2011.
43.
GlorotXBengioY. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics (AISTATS), Sardinia, Italy, 13–15 May 2010.
44.
Cofre-MartelSKobrichPLopez DroguettE, et al. Deep convolutional neural network-based structural damage localization and quantification using transmissibility data. Shock Vibr2019; 2019: 1–27.
45.
HeHZhengJLiaoL, et al. Damage identification based on convolutional neural network and recurrence graph for beam bridge. Struct Health Monit2021; 20: 1392–1408.
