In multidisciplinary design optimization of aerospace structures (e.g., a flexible wing), it may be convenient and practical to break such a complex problem into multi-fidelity, multi-stage design problems. Structural model updating is needed in multi-fidelity, multi-stage optimizations to ensure the consistency of models with different fidelity. However, due to the inequality in structural parameters, there exists a fundamental difficulty in the model updating from a lower fidelity model to a higher fidelity model. In this paper, a feed-forward neural network is applied to determine the structural dynamic characteristics of a higher fidelity model based upon a lower fidelity model. The feasibility of this approach is demonstrated by updating beam-like wings to a thin shell-based model and a one-cell wing box model, respectively. The quality and accuracy of model updating using the proposed method are also discussed regarding the neural network structure and sample size.
CiarletPDestuynderP. A justification of a nonlinear model in plate theory. Computer Methods Appl Mech Eng1979; 17-18(1): 227–258, doi:10.1016/0045-7825(79)90089-6.
2.
BerdichevskiiV. Variational-asymptotic method of constructing a theory of shells. J Appl Math Mech1979; 43(4): 711–736. DOI: 10.1016/0021-8928(79)90157-6.
3.
HodgesDAtilganACesnikC, et al.On a simplified strain energy function for geometrically nonlinear behaviour of anisotropic beams. Composites Eng1992; 2(5–7): 513–526. DOI: 10.1016/0961-9526(92)90040-D.
4.
CesnikCHodgesD. VABS: A new concept for composite rotor blade cross-sectional modeling. J Am Helicopter Soc1997; 42(1): 27–38, doi:10.4050/JAHS.42.27.
5.
YuWHodgesDVolovoiV, et al.On timoshenko-like modeling of initially curved and twisted composite beams. Int J Sol Structures2002; 39(19): 5101–5121. DOI: 10.1016/S0020-7683(02)00399-2.
6.
YuWHodgesDHoJ. Variational asymptotic beam sectional analysis – An updated version. Int J Eng Sci2012; 59: 40–64, doi:10.1016/j.ijengsci.2012.03.006.
7.
LevinRLievenN. Dynamic finite element model updating using neural networks. J Sound Vibration1998; 210(5): 593–607. DOI: 10.1006/jsvi.1997.1364.
8.
JaishiBRenW. Finite element model updating based on eigenvalue and strain energy residuals using multiobjective optimisation technique. Mech Syst Signal Process2007; 21(5): 2295–2317, doi:10.1016/j.ymssp.2006.09.008.
9.
LuYTuZ. A two-level neural network approach for dynamic fe model updating including damping. J Sound Vibration2004; 275(3–5): 931–952. DOI: 10.1016/S0022-460X(03)00796-X.
10.
YinTZhuHFuS. Damage identification of periodically-supported structures following the bayesian probabilistic approach. Int J Struct Stab Dyn2019; 19(01): 1940011, doi:10.1142/S021945541940011X.
11.
MottersheadJLinkMFriswellM. The sensitivity method in finite element model updating: A tutorial. Mech Syst Signal Process2011; 25(7): 2275–2296, doi:10.1016/j.ymssp.2010.10.012.
12.
AbdeljaberOAvciOKiranyazS, et al. Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks. J Sound Vibration2017; 388: 154–170, doi:10.1016/j.jsv.2016.10.043.
13.
YinTZhuH. An efficient algorithm for architecture design of bayesian neural network in structural model updating. Computer-Aided Civil Infrastructure Eng2020; 35(4): 354–372. DOI: 10.1111/mice.12492.
14.
IsmailHSinghMDarwishS, et al. Developing ANN-Kriging hybrid model based on process parameters for prediction of mean residence time distribution in twin-screw wet granulation. Powder Tech2019; 343: 568–577, doi:10.1016/j.powtec.2018.11.060.
15.
CybenkoG. Approximation by superpositions of a sigmoidal function. Math Control Signals Syst1989; 2: 303–314, doi:10.1007/BF02551274.
16.
LiuZFangHXuJ. Identification of piecewise linear dynamical systems using physically-interpretable neural-fuzzy networks: methods and applications to origami structures. Neural Networks2019; 116: 74–87. DOI: 10.1016/j.neunet.2019.04.007.
17.
YuWHodgesD. Elasticity solutions versus asymptotic sectional analysis of homogeneous, isotropic, prismatic beams. J Appl Mech2004; 71(1): 15–23, doi:10.1115/1.1640367.
18.
HaganMDemuthHBealeM, et al. Neural network design. 2nd ed.. Martin Hagan, 2014.
19.
SolaJSevillaJ. Importance of input data normalization for the application of neural networks to complex industrial problems. IEEE Trans Nucl Sci1997; 44(3): 1464–1468, doi:10.1109/23.589532.
20.
BishopC. Neural networks for pattern recognition. Oxford University Press, USA, 1996.
21.
MagarKReichGRickeyM, et al. Aerodynamic characteristics prediction via artificial hair sensor and feedforward neural network. ASME Conference on Smart Mater Adaptive Structures Intell Syst. Colorado Springs, CO: American Society of Mechanical Engineers, p. V002T06A004, doi:10.1115/SMASIS2015-8890.
22.
WangQMedeirosRCesnikC, et al. Techniques for improving neural network-based aerodynamics reduced-order models. AIAA SciTech 2019 Forum. San Diego, CA: American Institute of Aeronautics and Astronautics, doi:10.2514/6.2019-1849.
