Recently, machine learning (ML) algorithms have shown strong potential in predicting structural damage. However, structural health monitoring data mostly represents normal operating conditions or minor deviations, rarely capturing severe or hazardous states. This makes it challenging to create realistic datasets for training ML models in structural damage detection. If such data were available, it would likely involve variables like the stress intensity factor range and stress ratio, which are challenging to measure directly in real-world structures. In this study, ML models, including Artificial Neural Network (ANN), Extreme Gradient Boosting (XGB), and Random Forest (RF), were developed to predict the locations, widths, and depths of saw-cuts in steel beams, using changes in natural frequencies as predictive indicators. The natural frequencies under various damage conditions were calculated using the Finite Element Method (FEM). To validate the results, the natural frequencies of both damaged and undamaged beams were calculated using the Rational Fraction Polynomial (RFP) method and compared with the outcomes from the Finite Element Method (FEM) to evaluate their consistency. The study seeks to establish conclusions regarding the most effective machine learning models and the integration of FEM, RFP, and machine learning for enhanced structural health monitoring.
YangXSwamidasASeshadriR.Crack identification in vibrating beams using the energy method. J Sound Vib2001; 244(1): 339–357.
2.
SwamidasASJYangXSeshadriR.Identification of cracking in beam structures using Timoshenko and Euler formulations. J Eng Mech2004; 130(11): 1297–1308.
3.
GillichG-RPraisachZ-IAbdel WahabM, et al. Free vibration of a perfectly clamped-free beam with stepwise eccentric distributed masses. Shock Vib2016; 2016: 1–10.
4.
ZhouY-LMaiaNMMSampaioRPC, et al. Structural damage detection using transmissibility together with hierarchical clustering analysis and similarity measure. Struct Health Monit2017; 16(6): 711–731.
5.
GillichG-RFurduiHAbdel WahabM, et al. A robust damage detection method based on multi-modal analysis in variable temperature conditions. Mech Syst Signal Process2019; 115: 361–379.
6.
ZhouY-LMaiaNMAbdel WahabM.Damage detection using transmissibility compressed by principal component analysis enhanced with distance measure. J Vib Control2018; 24(10): 2001–2019.
7.
KhiemNTTranTHNinhVTA, et al. A closed-form solution to the problem of crack detection in a multistep beam based on Rayleigh quotient. Int J Solids Struct2018; 150: 154–165.
8.
HaiTTHangPTKhiemNT.A novel criterion for crack identification in beam-like structures using distributed piezoelectric sensor and controlled moving load. J Sound Vib2024; 572(1): 118155.
9.
KhiemNTToanLK.A novel method for crack detection in beam-like structure by measurement of natural frequencies. J Sound Vib2014; 333(18): 4084–4103.
10.
KhiemNTLienTV.Multi-crack detection for beam by natural frequencies. J Sound Vib2004; 273(1–2): 175–184.
11.
KhiemNTHaiTTHuongLQ.Crack identification for functionally graded beam using distributed piezoelectric sensor. J Vib Control2023; 29(15-16): 3401–3417.
12.
KhiemNTHangPT.Analysis and identification of multiple-cracked beam subjected to moving harmonic load. J Vib Control2018; 24(13): 2782–2801.
13.
KhiemNTTranHT.A procedure for multiple crack identification in beam-like structures from natural vibration mode. J Vib Control2014; 20(9): 1417–1427.
14.
KhiemNT.Crack detection for structures based on the dynamic stiffness model and the inverse problem of vibration. Inverse Probl Sci Eng2006; 14(1): 85–96.
15.
KhiemNTHungDT.A closed-form solution for free vibration of multiple cracked Timoshenko beam and application. Vietnam J Mech2017; 39(4): 315–340.
16.
KhiemNTHaiTTToanLK, et al. A novel criterion for crack detection in beam structures by frequency response functions. Vietnam J Mech2023; 45(3): 273–286.
17.
NguyenHNCanhTNThanhTT, et al. Finite element modelling of a composite shell with shear connectors. Symmetry2019; 11(4): 527.
18.
TuanLTDungNTVan ThomD, et al. Propagation of non-stationary kinematic disturbances from a spherical cavity in the pseudo-elastic cosserat medium. Eur Phys J Plus2021; 136(12): 1–16.
19.
VuVTThomDVTranTD.Dentification of damage in steel beam by natural frequency using machine learning algorithms. Proc IMechE, Part C: J Mechanical Engineering Science2024; 238(19): 9644–9659.
20.
Dao MinhTDo VanTPhung VanM, et al. Bending and buckling responses of organic nanoplates considering the size effect. Transp Commun Sci J2024; 75(7): 2015–2029.
21.
SamirKIdirBSerraR, et al. Genetic algorithm based objective functions comparative study for damage detection and localization in beam structures. J Phys Conf Ser2015; 628: 012035.
22.
GhadimiSKourehliSS.Crack detection of structures using modified extreme learning machine (MELM). Inverse Probl Sci Eng2017; 25(7): 995–1013.
23.
LeeJ-WKimS-RHuhY-C.Pipe crack identification based on the energy method and committee of neural networks. Int J Steel Struct2014; 14(2): 345–354.
24.
MortazaviSNSInceA. An artificial neural network modeling approach for short and long fatigue crack propagation. Comput Mater Sci2020; 185: 109962.
25.
GillichNTufisiCSacareaC, et al. Beam damage assessment using natural frequency shift and machine learning. Sensors2022; 22(3): 1118.
26.
SeguiniMDjamelNDjilaliB, et al. Crack prediction in beam-like structure using ANN based on frequency analysis. Frat Integrità Strut2022; 16(59): 18–34.
27.
SaeedRAGalybinANPopovV.Crack identification in curvilinear beams by using ANN and ANFIS based on natural frequencies and frequency response functions. Neural Comput Appl2012; 21(7): 1629–1645.
28.
NazariFBaghalianS.A new method for damage detection in symmetric beams using artificial neural network and finite element method. Int J Appl Sci Eng2011; 3: 30–36.
29.
RaoPSMahendraN. Vibration based damage identification method for cantilever beam using artificial neural network. In: International conference on experimental vibration analysis for civil engineering structures, 2017, pp.85–93. Springer.
30.
GowdBPJayasreeKHegdeMN.Comparison of artificial neural networks and fuzzy logic approaches for crack detection in a beam like structure. Int J Artif Intell Appl2018; 9(1): 35–51.
31.
AshigbiDMSackeyMNFiagbeYAK, et al. Vibration response based crack diagnosis in beam-like structures using fuzzy inference system. Sci Afr2021; 14: e01051.
32.
KhatirSAbdel WahabM.A computational approach for crack identification in plate structures using XFEM, XIGA, PSO and Jaya algorithm. Theor Appl Fract Mech2019; 103: 102240.
33.
KhatirSKhatirTBoutchichaD, et al. An efficient hybrid TLBO-PSO-ANN for fast damage identification in steel beam structures using IGA. Smart Struct Syst2020; 25: 605–617.
34.
SeguiniMKhatirSBoutchichaD, et al. Crack prediction in pipeline using ANN-PSO based on numerical and experimental modal analysis. Smart Struct Syst2021; 27: 507–523.
35.
Cuong-LeTNghia-NguyenTKhatirS, et al. An efficient approach for damage identification based on improved machine learning using PSO-SVM. Eng Comput2021; 38(4): 3069–3116.
36.
RathodVTMukherjeeSDengY.Machine learning enabled damage classification in composite laminated beams using mode conversion quantification. In: Nondestructive characterization and monitoring of advanced materials, aerospace, civil infrastructure, and transportation XIV, 2020, pp.36–52. SPIE.
37.
de SousaAASRdaSilvaCoelhoJMachadoMR, et al. Multiclass supervised machine learning algorithms applied to damage and assessment using beam dynamic response. J Vib Eng Technol2023; 11(6): 2709–2723.
38.
OmarIKhanMStarrA.Suitability analysis of machine learning algorithms for crack growth prediction based on dynamic response data. Sensors2023; 23(3): 1074.
39.
RumelhartDEHintonGEWilliamsRJ.Learning internal representations by error propagation. San Diego, LA: Institute for Cognitive Science, University of California, 1985.
40.
ShahinMA.Intelligent computing for modeling axial capacity of pile foundations. Can Geotech J2010; 47(2): 230–243.
41.
MaierHRDandyGC. Application of Artificial Neural Networks to Forecasting of Surface Water Quality Variables: Issues, Applications and Challenges. In: GovindarajuRSRaoAR (eds) Artificial Neural Networks in Hydrology. Dordrecht: Springer Netherlands, 2000, pp.287–309.
42.
HornikKStinchcombeMWhiteH.Multilayer feedforward networks are universal approximators. Neural Netw1989; 2(5): 359–366.
43.
CaudillM.Neural networks primer, Part III. AI Expert1988; 3: 53–59.
ChenTGuestrinC.Xgboost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, 2016, pp.785–794.
