The finite element modeling of electronic boards is a challenging task due to the complexity of the multi-component board structure. Hence, it is acceptable to attain equivalent orthotropic in-plane mechanical properties and use them throughout the finite element analysis (FEA) simulations. This paper aims to present an artificial intelligence-based methodology, using the artificial neural networks (ANNs), to estimate the in-plane mechanical properties of the printed circuit boards (PCB). In this methodology, the ANN technique used FEA data to find the relationship between the first 10 natural frequencies and the mechanical properties, that is, modulus of elasticity, Poisson’s ratio and the shear modulus, of the test board. Subsequently, the experimentally derived natural frequency data is then imported to the ANN model to identify the equivalent orthotropic properties. The ANN-predicted properties are plugged back into FEA and provided natural frequencies and mode shapes that are in great match with experimental results.
GharaibehMA. A simulation-based study on the effect of package parameters on the random vibration behavior of electronic packages. Eur Phys J Plus2021; 136(11): 1132.
2.
GharaibehMAPitarresiJM. A methodology to calculate the equivalent static loading for simulating electronic assemblies under impact. Microelectron Reliab2022; 139: 114842.
3.
GharaibehMA. An accuracy and efficiency study on the use of symmetrical numerical models of electronic packages under various loading conditions. Jordan J Mech Ind Eng2022; 16(4): 471–483.
4.
KavithaMMahmoudZHKishoreKH, et al. Application of Steinberg model for vibration lifetime evaluation of SN-AG-CU-based solder joints in power semiconductors. IEEE Trans Compon Packaging Manuf Technol2021; 11(3): 444–450.
5.
GharaibehMASuQTPitarresiJM, et al. Board-level drop test: comparison of two ANSYS modeling approaches and correlation with testing. In: Universal instruments advanced research in electronic assemblies consortium, Conklin, NY, 12−13 June 2013. Universal Instruments.
6.
SpinnerSTefftWE. A method for determining mechanical resonance frequencies and for calculation elastic moduli from these frequencies. Proc Am Soc Test Mater1961; 61: 1229–1238.
7.
LauwagieTSolHRoebbenG, et al. Validation of the Resonalyser method: an inverse method for material identification. In: Proceedings of ISMA2002, 2002, vol. 2, pp.687–695.
8.
SolH. Identification of anisotropic plate rigidities using free vibration data. PhD Thesis. Free University of Brussels, Belgium, 1986.
9.
DeobaldLRGibsonRF. Determination of elastic constants of orthotropic plates by a modal analysis/Rayleigh-Ritz technique. J Sound Vib1988; 124(2): 269–283.
10.
MoussuFNivoitM. Determination of elastic constants of orthotropic plates by a modal analysis/method of superposition. J Sound Vib1993; 165(1): 149–163.
11.
MottersheadJEFriswellMI. Model updating in structural dynamics: a survey. J Sound Vib1993; 167(2): 347–375.
12.
LauwagieTSolHHeylenW, et al. Determination of the in-plane elastic properties of the different layers of laminated plates by means of vibration testing and model updating. J Sound Vib2004; 274(3-5): 529–546.
13.
IsmailZKhovHLiWL. Determination of material properties of orthotropic plates with general boundary conditions using inverse method and Fourier series. Measurement2013; 46(3): 1169–1177.
14.
GaoPDuYWangY, et al. Study on repeated-root modes in substructure modal composition analysis. SAE Int J Passeng Cars - Mech Syst2016; 9(1): 160–166.
15.
SuQTGharaibehMAStewartAJ, et al. Accelerated vibration reliability testing of electronic assemblies using sine dwell with resonance tracking. J Electron Packag2018; 140(4): 041004.
16.
SuQTGharaibehMAStewartAJ, et al. Accelerated vibration reliability testing of electronic assemblies using sine dwell with resonance tracking. In: 2014 IEEE 64th electronic components and technology conference (ECTC), 2014, pp.119−125
17.
GharaibehMASuQTPitarresiJM, et al. Modeling and characterization for vibration. In: Universal instruments advanced research in electronic assemblies consortium, Conklin, NY, 12−13 June 2013. Universal Instruments.
ZhangBLiuPKDingH, et al. Modeling of board-level package by finite element analysis and laser interferometer measurements. Microelectron Reliab2010; 50(7): 1021–1027.
20.
PitarresiJM. Modeling of printed circuit cards subject to vibration. In: IEEE international symposium on circuits and systems, May1990, pp.2104−2107. IEEE.
21.
PitarresiJMPrimaveraAA. Comparison of modeling techniques for the vibration analysis of printed circuit cards. J Electron Packag1992; 114(4): 378–383.
22.
PitarresiJMAkandaA. Random vibration response of a surface mount lead/solder joint. Adv Electron Packag1993; 4: (1) 207–215.
23.
PitarresiJGengPBeltmanW, et al. Dynamic modeling and measurement of personal computer motherboards. In: 52nd electronic components and technology conference 2002, May 2002, Cat. No. 02CH37345, pp.597−603. IEEE.
24.
PitarresiJRoggemanBChaparalaS, et al. Mechanical shock testing and modeling of PC motherboards. In: 2004 proceedings 54th electronic components and technology conference, June 2004, vol. 1, IEEE Cat. No. 04CH37546, pp.1047−1054. IEEE.
25.
LeeYCWangBTLaiYS, et al. Finite element model verification for packaged printed circuit board by experimental modal analysis. Microelectron Reliab2008; 48(11-12): 1837–1846.
26.
GharaibehM. Finite element model updating of board-level electronic packages by factorial analysis and modal measurements. Microelectron Int2018; 35(2): 74–84.
27.
GharaibehM. Identification of printed circuit boards mechanical properties using response surface methods. Microelectron Int2022; 39(1): 38–47.
28.
RenGLiBLiD, et al. Modal analysis of the printed circuit board based on finite element method. In: 2014 international conference on computer science and electronic technology (ICCSET 2014), January 2015, pp.150−154. Atlantis Press.
29.
AithalSKBabuNRChethanKS, et al. Vibrational analysis of printed circuit board for space applications. In: AIP conference proceedings, November 2022, vol. 2615, no. 1, p.040007. AIP Publishing LLC.
30.
ChaithanyaTArjulaS. Free vibration analysis of composite plate with different cut outs, orientations and boundary conditions. Eng Sci2019; 10(12): 456–461.
31.
AltaraziSAmmouriMHijaziA. Artificial neural network modeling to evaluate polyvinylchloride composites’ properties. Comput Mater Sci2018; 153: 1–9.
32.
HijaziAAl-DahidiSAltaraziS. A novel assisted artificial neural network modeling approach for improved accuracy using small datasets: application in residual strength evaluation of panels with multiple site damage cracks. Appl Sci2020; 10(22): 8255.
33.
NoorRAMAhmadZDonMM, et al. Modelling and control of different types of polymerization processes using neural networks technique: a review. Can J Chem Eng2010; 88(6): 1065–1084.
34.
XuYZhangQZhangW, et al. Optimization of injection molding process parameters to improve the mechanical performance of polymer product against impact. Int J Adv Manuf Technol2015; 76: 2199–2208.
35.
ÖktemHShindeD. Determination of optimal process parameters for plastic injection molding of polymer materials using multi-objective optimization. J Mater Eng Perform2021; 30(11): 8616–8632.
36.
YadollahiMMBenliADemirboğaR. Prediction of compressive strength of geopolymer composites using an artificial neural network. Mater Res Innov2015; 19(6): 453–458.
37.
JayabalSRajamuneeswaranSRamprasathR, et al. Artificial neural network modeling of mechanical properties of calcium carbonate impregnated coir-polyester composites. Trans Indian Ins Metals2013; 66(3): 247–255.
Singh SivamSSRajendranRHarshavardhanaN. An investigation of hybrid models FEA coupled with AHP-ELECTRE, RSM-GA, and ANN-GA into the process parameter optimization of high-quality deep-drawn cylindrical copper cups. Mech Based Des Struct Mach2022; 52: 498–522.
40.
MoayediHRezaeiA. An artificial neural network approach for under-reamed piles subjected to uplift forces in dry sand. Neural Comput Appl2019; 31(2): 327–336.
41.
RezaeiMMonjeziMGhorbani MoghaddamS, et al. Burden prediction in blasting operation using rock geomechanical properties. Arab J Geosci2012; 5: 1031–1037.
42.
NegnevitskyM. Artificial intelligence: a guide to intelligent systems. London: Pearson Education, 2005.
43.
HayajnehMTHassanAMMayyasAT. Artificial neural network modeling of the drilling process of self-lubricated aluminum/alumina/graphite hybrid composites synthesized by powder metallurgy technique. J Alloys Comp2009; 478(1-2): 559–565.
44.
RoigerRJ (ed.). Data mining: a tutorial-based primer. 2nd ed.Boca Raton, FL: CRC Press, 2017.
45.
ZhangZFriedrichKVeltenK. Prediction on tribological properties of short fibre composites using artificial neural networks. Wear2002; 252(7-8): 668–675.
46.
ZhouJLiCArslanCA, et al. Performance evaluation of hybrid FFA-ANFIS and GA-ANFIS models to predict particle size distribution of a muck-pile after blasting. Eng Comput2021; 37: 265–274.
47.
GhasemiE. Particle swarm optimization approach for forecasting backbreak induced by bench blasting. Neural Comput Appl2017; 28: 1855–1862.
48.
GhasemiEKalhoriHBagherpourR. A new hybrid ANFIS–PSO model for prediction of peak particle velocity due to bench blasting. Eng Comput2016; 32: 607–614.
49.
LawalAIIdrisMA. An artificial neural network-based mathematical model for the prediction of blast-induced ground vibrations. Int J Environ Stud2020; 77(2): 318–334.
50.
LawalAI. An artificial neural network-based mathematical model for the prediction of blast-induced ground vibration in granite quarries in Ibadan, Oyo State, Nigeria. Sci Afr2020; 8: e00413.
