The presence of faults is common in engineering composite structures. Precise detection of faults prior to failure has been the focal point for researchers working in this domain. Detection of damage from the modal characteristics is an age-old promising technique besides the artificial intelligence techniques such as neural network (NN), Artificial neural network (ANN), recurrent neural network (RNN), and particle swarm optimization (PSO) methods. However, multiple detection techniques combined can give better results. In this regard, recurrent neural networks (RNN) and modified particle swarm optimization (mPSO) are combined to detect damages in a glass fiber reinforced polymer (GFRP) composite cantilever beam. The proposed hybrid model consists of two stages; indices of relative natural frequencies applied to locate crack parameters (position and severity) by recurrent neural network technique and optimization of the results (position and severity) by mPSO. The results illustrate this method can be implemented to predict multiple transverse cracks and their parameters in a composite beam, manifested in the change of natural frequencies where the error is limited to 0.97% only.
WeiKLiangDMeiM, et al. Preforming behaviors of carbon fiber fabrics with different contents of binder and under various process parameters. Compos B Eng2019; 166: 221–232.
2.
ParidaSPJenaPC. Free and forced vibration analysis of flyash/graphene filled laminated composite plates using higher order shear deformation theory. Proc IMechE, Part C: J Mechanical Engineering Sciences2022; 236(9): 4648–4659.
3.
ParidaSPJenaPC. Multi-fillers GFRP laminated composite plates: fabrication & properties. Indian J Eng Mater Sci2022; 29(06): 817–825
4.
ParidaSPJenaPCDashRR. Dynamics of rectangular laminated composite plates with selective layer-wise fillering rested on elastic foundation using higher-order layer-wise theory. J Vib Control2023; 29(23-24): 5598–5615.
5.
MeiMHeYYangX, et al. Shear deformation characteristics and defect evolution of the biaxial ±45° and 0/90° glass non-crimp fabrics. Compos Sci Technol2020; 193.
6.
HeYMeiMWeiK, et al. Interlaminar shear behaviour and meso damage suppression mechanism of stitched composite under short beam shear using X-ray CT. Compos Sci Technol2022; 218.
7.
SekharAS. Multiple cracks effects and identification. Mech Syst Signal Process2008; 22(4): 845–878.
8.
DziedziechKPieczonkaLKijankaP, et al. Enhanced nonlinear crack-wave interactions for structural damage detection based on guided ultrasonic waves. Struct Control Health Monit2016; 23(8): 1108–1120.
9.
FengDFengMQ. Output-only damage detection using vehicle-induced displacement response and mode shape curvature index. Struct Control Health Monit2016; 23(8): 1088–1107.
10.
DimarogonasAD. Vibration of cracked structures: a state of the art review. Eng Fract Mech1996; 55(5): 831–857.
11.
JenaPPohitGParhiD. Fault measurement in composite structure by fuzzy-neuro hybrid technique from the natural frequency and fibre orientation. J Vib Eng Technol2017; 5(2): 123–136.
12.
ShaGRadzieńskiMCaoM, et al. A novel method for single and multiple damage detection in beams using relative natural frequency changes. Mech Syst Signal Process2019; 132: 335–352.
13.
PandeyAKBiswasM. Damage detection in structures using changes in flexibility. J Sound Vib1994; 169(1): 3–17.
14.
LiGQHaoKCLuY, et al. A flexibility approach for damage identification of cantilever-type structures with bending and shear deformation. Comput Struct1999; 73(6): 565–572.
ReyndersEDe RoeckG. A local flexibility method for vibration-based damage localization and quantification. J Sound Vib2010; 329(12): 2367–2383.
17.
HeJZhouY. A novel mode shape reconstruction method for damage diagnosis of cracked beam. Mech Syst Signal Process2019; 122: 433–447.
18.
JenaPCParhiDRPohitG. Dynamic Investigation of FRP cracked beam using neural network technique. J Vib Eng Technol2019; 7(6): 647–661.
19.
MinJParkSYunCB, et al. Impedance-based structural health monitoring incorporating neural network technique for identification of damage type and severity. Eng Struct2012; 39: 210–220.
20.
ChithraSKumarSRRSChinnarajuK, et al. A comparative study on the compressive strength prediction models for high performance concrete containing nano silica and copper slag using regression analysis and artificial neural networks. Constr Build Mater2016; 114: 528–535.
21.
KhademiFJamalSMDeshpandeN, et al. Predicting strength of recycled aggregate concrete using artificial neural network, adaptive neuro-fuzzy inference system and multiple linear regression. Int J Sustain Built Environ2016; 5(2): 355–369.
22.
MehrjooMKhajiNMoharramiH, et al. Damage detection of truss bridge joints using artificial neural networks. Expert Syst Appl2008; 35(3): 1122–1131.
23.
GanguliR. A fuzzy logic system for ground based structural health monitoring of a helicopter rotor using modal data. J Intell Mater Syst Struct2001; 12(6): 397–407.
24.
Vakil-BaghmishehMTPeimaniMSadeghiMH, et al. Crack detection in beam-like structures using genetic algorithms. Appl Soft Comput2008; 8(2): 1150–1160.
25.
CiveraMBoscatoGZanotti FragonaraL. Treed gaussian process for manufacturing imperfection identification of pultruded GFRP thin-walled profile. Compos Struct2020; 254.
26.
BoscatoGCiveraMZanotti FragonaraL. Recursive partitioning and Gaussian process regression for the detection and localization of damages in pultruded glass fiber reinforced polymer material. Struct Control Health Monit2021; 28(10).
27.
RanjbaranARanjbaranM. New finite-element formulation for buckling analysis of cracked structures. J Eng Mech2014; 140(5): 04014014.
28.
QuilaMCh. MondalPSSarkarPS. Free vibration analysis of an un-cracked & cracked fixed beam. IOSR J Mech Civil Eng2014; 11(3): 76–83.
29.
KennedyJEberhartR. Particle swarm optimization. In: Proceedings of ICNN’95-international conference on neural networks, 1995; 4, pp.1942–1948. New York: IEEE. DOI: 10.1109/ICNN.1995.488968
30.
ChenJTangYGeR, et al. Reliability design optimization of composite structures based on PSO together with FEA. Chin J Aeronaut2013; 26(2): 343–349.
31.
KangFLiJJXuQ. Damage detection based on improved particle swarm optimization using vibration data. Appl Soft Comput2012; 12(8): 2329–2335.
32.
ChenXLFuJPYaoJL, et al. Prediction of shear strength for squat RC walls using a hybrid ANN–PSO model. Eng Comput2018; 34(2): 367–383.
33.
ShariatiMMafipourMSMehrabiP, et al. Application of a hybrid artificial neural network-particle swarm optimization (ANN-PSO) model in behavior prediction of channel shear connectors embedded in normal and high-strength concrete. Appl Sci2019; 9(24): 5534.
34.
JenaPKThatoiDNParhiDR. Dynamically self-adaptive fuzzy PSO technique for smart diagnosis of transverse crack. Appl Artif Intell2015; 29(3): 211–232.
35.
JenaPCParhiDRPohitG. Faults detection of a single cracked beam by theoretical and experimental analysis using vibration signatures. IOSR J Mech Civil Eng2012; 4(3): 01–18.
36.
CobanR. A context layered locally recurrent neural network for dynamic system identification. Eng Appl Artif Intell2013; 26(1): 241–250.
JenaSParhiD. Fault detection in cracked structures under moving load through a recurrent-neural-networks-based approach. Sci Iran2020; 27(4): 1886–1896.
39.
BaiYXieJLiuC, et al. Regression modeling for enterprise electricity consumption: A comparison of recurrent neural network and its variants. Int J Electr Power Energy Syst2021; 126.
40.
MohandesMA. Modeling global solar radiation using particle swarm optimization (PSO). Sol Energy2012; 86(11): 3137–3145.
41.
BegambreOLaierJE. A hybrid particle swarm optimization – Simplex algorithm (PSOS) for structural damage identification. Adv Eng Softw2009; 40(9): 883–891.
42.
KhareARangnekarS. A review of particle swarm optimization and its applications in solar photovoltaic system. Appl Soft Comput2013; 13(5): 2997–3006.
43.
SahuSKumarPParhiD. Analysis of hybrid CSA-DEA method for fault detection of cracked structures. J Theor Appl Mech2019; 57(2): 369–382.
