Prediction model for determining the optimum operational parameters in laser forming of fiber-reinforced composites

Abstract

Composite materials are widely employed in various industries, such as aerospace, automobile, and sports equipment, owing to their lightweight and strong structure in comparison with conventional materials. Laser material processing is a rapid technique for performing the various processes on composite materials. In particular, laser forming is a flexible and reliable approach for shaping fiber-metal laminates (FMLs), which are widely used in the aerospace industry due to several advantages, such as high strength and light weight. In this study, a prediction model was developed for determining the optimal laser parameters (power and speed) when forming FML composites. Artificial neural networks (ANNs) were applied to estimate the process outputs (temperature and bending angle) as a result of the modeling process. For this purpose, several ANN models were developed using various strategies. Finally, the achieved results demonstrated the advantage of the models for predicting the optimal operational parameters.

Keywords

Laser forming (LF) / Fiber-reinforced composite / Fiber-metal laminates (FMLs) / Glass laminate aluminum reinforced epoxy (GLARE) / Artificial neural networks (ANNs)

References

[1.] Gisario A, Mehrpouya M, Venettacci S, et al. Laser Origami (LO) of three-dimensional (3D) components: experimental analysis and numerical modelling. J Manuf Process, 2016, 23: 242-248.

[2.] Edwardson S, Abed E, Carey C et al (2007) Key factors influencing the bend per pass in laser forming. In: International congress on applications of lasers & electro-optics, 2007, p 506

[3.] Gisario A, Mehrpouya M, Venettacci S, et al. Laser-assisted bending of titanium grade-2 sheets: experimental analysis and numerical simulation. Opt Lasers Eng, 2017, 92: 110-119.

[4.] Mehrpouya M, Huang H, Venettacci S, et al. LaserOrigami (LO) of three-dimensional (3D) components: experimental analysis and numerical modeling-part II. J Manuf Process, 2019, 39: 192-199.

[5.] Gisario A, Barletta M. Laser forming of glass laminate aluminium reinforced epoxy (GLARE): on the role of mechanical, physical and chemical interactions in the multi-layers material. Opt Lasers Eng, 2018, 110: 364-376.

[6.] Asundi A, Choi AY. Fiber metal laminates: an advanced material for future aircraft. J Mater Process Technol, 1997, 63: 384-394.

[7.] Vlot A, Vogelesang L, De Vries T. Towards application of fibre metal laminates in large aircraft. Aircr Eng Aerosp Technol, 1999, 71: 558-570.

[8.] Le Bourlegat L, Damato C, Da Silva D, et al. Processing and mechanical characterization of titanium-graphite hybrid laminates. J Reinf Plast Compos, 2010, 29: 3392-3400.

[9.] Zhang Q, Huang JQ, Qian WZ, et al. The road for nanomaterials industry: a review of carbon nanotube production, post-treatment, and bulk applications for composites and energy storage. Small, 2013, 9: 1237-1265.

[10.] Hassani M, Hassani Y, Ajudanioskooei N, et al. Comparative study of bending angle in laser forming process using artificial neural network and fuzzy logic system. World Acad Sci Eng Technol Int J Math Comput Phys Electr Comput Eng, 2017, 9: 595-598.

[11.] Selvakumar N, Ganesan P, Radha P, et al. Modelling the effect of particle size and iron content on forming of Al-Fe composite preforms using neural network. Mater Des, 2007, 28: 119-130.

[12.] Mishra R, Malik J, Singh I, et al. Neural network approach for estimating the residual tensile strength after drilling in uni-directional glass fiber reinforced plastic laminates. Mater Des, 2010, 31: 2790-2795.

[13.] Jiang HJ, Liang LH, Xiao YL, et al. Three-dimensional transient thermodynamic analysis of laser surface treatment for a fiber laminated plate with a coating layer. Int J Heat Mass Transf, 2018, 118: 671-685.

[14.] Jiang HJ, Liang LH, Ma L, et al. An analytical solution of three-dimensional steady thermodynamic analysis for a piezoelectric laminated plate using refined plate theory. Compos Struct, 2017, 162: 194-209.

[15.] Mehrpouya M (2017) Laser welding of NiTi shape memory sheets: experimental analysis and numerical modeling. Dissertation, Sapienza University of Rome

[16.] Mehrpouya M, Shahedin AM, Daood SDS, et al. An investigation on the optimum machinability of NiTi based shape memory alloy. Mater Manuf Process, 2017, 32(13): 1497-1504.

[17.] Mehrpouya M (2013) Modeling of machining perocess of nickel based shape memory alloy. Dissertation, Universiti Putra Malaysia

[18.] Mehrpouya M, Gisario A, Rahimzadeh A, et al. An artificial neural network model for laser transmission welding of biodegradable polyethylene terephthalate/polyethylene vinyl acetate (PET/PEVA) blends. Int J Adv Manuf Technol, 2019, 102(5/8): 1497-1507.

[19.] Mehrpouya M, Gisario A, Rahimzadeh A, et al. A prediction model for finding the optimal laser parameters in additive manufacturing of NiTi shape memory alloy. Int J Adv Manuf Technol, 2019, 105: 4691-4699.

[20.] Hajian A, Styles P. Prior applications of neural networks in geophysics. Application of soft computing and intelligent methods in geophysics, 2018, Cham: Springer 71-198.

[21.] Lourakis M, Argyros A (2004) The design and implementation of a generic sparse bundle adjustment software package based on the levenberg-marquardt algorithm. Technical report 340, Institute of Computer Science-FORTH, Heraklion, Crete

[22.] Levenberg K. A method for the solution of certain non-linear problems in least squares. Q Appl Math, 1944, 2: 164-168.

[23.] Marquardt DW. An algorithm for least-squares estimation of nonlinear parameters. J Soc Ind Appl Math, 1963, 11: 431-441.

[24.] Moré JJ. The Levenberg-Marquardt algorithm: implementation and theory. Numerical analysis, 1978, Berlin, Heidelberg: Springer 105-116.

[25.] Mehrpouya M, Gisario A, Huang H, et al. Numerical study for prediction of optimum operational parameters in laser welding of NiTi alloy. Opt Laser Technol, 2019, 118: 159-169.

[26.] Akbari M, Saedodin S, Panjehpour A, et al. Numerical simulation and designing artificial neural network for estimating melt pool geometry and temperature distribution in laser welding of Ti6Al4V alloy. Optik, 2016, 127: 11161-11172.