Abstract
A computationally effective and physically accurate metamodeling approach is demonstrated to analyze, under uncertainties, the spring-in angle deformation for composite manufacturing processes. Various uncertainties are inevitably present in this manufacturing process due to the heterogeneous thermo-mechanical properties of the composite materials. Analysis of uncertainty propagation using the direct Monte Carlo approach is computationally prohibitive, which calls for the employment of machine learning techniques and surrogate models or metamodels such as Gaussian processes (GP). While these approaches are promising, tuning model parameters and optimizing the hyperparameters are essential to predictive modeling performance. So far, most existing approaches rely on empirical experience through trial and error. Randomly selecting these hyperparameters results in excessive computational cost and poor convergence results. A nature-inspired methodology has been developed to guide the GP in selecting and optimizing the hyperparameters for the uncertainty propagation analysis of composite manufacturing processes. An improved firefly algorithm (iFA) takes account of the environmental factor. It disregards the contribution of a constant attractiveness factor, which in turn accelerates the convergence rate at the early stages of the generation and boosts the immunity of the proposed algorithm. The proposed methodology enabled selection of the proper combination of the factors for the GP and showed its merits over other state-of-the-art deterministic/metaheuristic algorithms, which is further confirmed by various nonparametric, multiple comparison tests.
Similar content being viewed by others
Data availability
Not applicable.
Materials availability
Not applicable.
Code availability
Not applicable.
References
Ding A, Li S, Wang J, Zu L (2015) A three-dimensional thermo-viscoelastic analysis of process-induced residual stress in composite laminates. Compos Struct 129:60–69. https://doi.org/10.1016/j.compstruct.2015.03.034
Zhang JT, Zhang M, Li SX et al (2016) Residual stresses created during curing of a polymer matrix composite using a viscoelastic model. Compos Sci Technol 130:20–27. https://doi.org/10.1016/j.compscitech.2016.05.002
Sorrentino L, Bellini C, Capriglione D, Ferrigno L (2015) Local monitoring of polymerization trend by an interdigital dielectric sensor. Int J Adv Manuf Technol 79:1007–1016. https://doi.org/10.1007/s00170-015-6892-x
Sorrentino L, Polini W, Bellini C (2014) To design the cure process of thick composite parts: experimental and numerical results. Adv Compos Mater 23:225–238. https://doi.org/10.1080/09243046.2013.847780
Radford DW, Rennick TS (2000) Separating sources of manufacturing distortion in laminated composites. J Reinf Plast Compos 19:621–641. https://doi.org/10.1177/073168440001900802
Albert C (2002) Spring-in and warpage of angled composite laminates. Compos Sci Technol 62:1895–1912. https://doi.org/10.1016/S0266-3538(02)00105-7
Çınar K, Ersoy N (2015) Effect of fibre wrinkling to the spring-in behaviour of L-shaped composite materials. Compos Part A Appl Sci Manuf 69:105–114. https://doi.org/10.1016/j.compositesa.2014.10.025
Fernlund G, Rahman N, Courdji R et al (2002) Experimental and numerical study of the effect of cure cycle, tool surface, geometry, and lay-up on the dimensional fidelity of autoclave-processed composite parts. Compos Part A Appl Sci Manuf 33:341–351. https://doi.org/10.1016/S1359-835X(01)00123-3
Lu Y, Li Y, Li N, Wu X (2017) Reduction of composite deformation based on tool-part thermal expansion matching and stress-free temperature theory. Int J Adv Manuf Technol 88:1703–1710. https://doi.org/10.1007/s00170-016-8862-3
Kiauka M, Kasatkin M, Tcygantceva I et al (2021) Method for residual strain modeling taking into account mold and distribution of heat transfer coefficients for thermoset composite material parts. Int J Adv Manuf Technol 117:2429–2443. https://doi.org/10.1007/s00170-021-07149-5
Cao Z, Li S, Li C et al (2022) Formation mechanism and detection and evaluation methods as well as repair technology of crack damage in fiber-reinforced composite wind turbine blade: a review. Int J Adv Manuf Technol 120:5649–5672. https://doi.org/10.1007/s00170-022-09230-z
Kim D, Centea T, Nutt SR (2014) In-situ cure monitoring of an out-of-autoclave prepreg: effects of out-time on viscosity, gelation and vitrification. Compos Sci Technol 102:132–138. https://doi.org/10.1016/j.compscitech.2014.07.027
White SR, Hahn HT (1992) Process modeling of composite materials: residual stress development during cure. Part II. Exp Validation J Compos Mater 26:2423–2453. https://doi.org/10.1177/002199839202601605
Patham B (2013) Multiphysics simulations of cure residual stresses and springback in a thermoset resin using a viscoelastic model with cure-temperature-time superposition. J Appl Polym Sci 129:983–998. https://doi.org/10.1002/app.38744
Nawab Y, Shahid S, Boyard N, Jacquemin F (2013) Chemical shrinkage characterization techniques for thermoset resins and associated composites. J Mater Sci 48:5387–5409. https://doi.org/10.1007/s10853-013-7333-6
Baran I, Akkerman R, Hattel JH (2014) Material characterization of a polyester resin system for the pultrusion process. Compos Part B Eng 64:194–201. https://doi.org/10.1016/j.compositesb.2014.04.030
Adolf D, Martin JE (1996) Calculation of stresses in crosslinking polymers. J Compos Mater 30:13–34. https://doi.org/10.1177/002199839603000102
Pérez JM, Rodríguez F, Alonso MV, Oliet M (2011) Time-temperature-transformation cure diagrams of phenol-formaldehyde and lignin-phenol-formaldehyde novolac resins. J Appl Polym Sci 119:2275–2282. https://doi.org/10.1002/app.32866
Hu C, Qin Q-H (2020) Advances in fused deposition modeling of discontinuous fiber/polymer composites. Curr Opin Solid State Mater Sci 24:100867. https://doi.org/10.1016/j.cossms.2020.100867
Wisnom MR, Potter KD, Ersoy N (2007) Shear-lag analysis of the effect of thickness on spring-in of curved composites. J Compos Mater 41:1311–1324. https://doi.org/10.1177/0021998306068072
Mesogitis TS, Skordos AA, Long AC (2014) Uncertainty in the manufacturing of fibrous thermosetting composites: a review. Compos Part A Appl Sci Manuf 57:67–75. https://doi.org/10.1016/j.compositesa.2013.11.004
Struzziero G, Teuwen JJE (2020) A fully coupled thermo-mechanical analysis for the minimisation of spring-in and process time in ultra-thick components for wind turbine blades. Compos Part A Appl Sci Manuf 139:106105. https://doi.org/10.1016/j.compositesa.2020.106105
Chen W, Zhang D (2018) A multi-physics processing model for predicting spring-in angle of a resin transfer molded composite flange. In: 2018 AIAA/ASCE/AHS/ASC Structures, Structural Dynamics, and Materials Conference. American Institute of Aeronautics and Astronautics, Reston, Virginia, pp 1–18
Zamani SMM, Behdinan K, Mohammadpour A et al (2021) Friction stir welding of Al-SiC composite sheets: a numerical simulation of residual stresses. Int J Adv Manuf Technol 116:3717–3729. https://doi.org/10.1007/s00170-021-07751-7
Zhou K, Enos R, Zhang D, Tang J (2022) Uncertainty analysis of curing-induced dimensional variability of composite structures utilizing physics-guided Gaussian process meta-modeling. Compos Struct 280:114816. https://doi.org/10.1016/j.compstruct.2021.114816
Wahba G Spline models for observational data. SIAM
Hoerl AE, Kennard RW (1970) Ridge regression: biased estimation for nonorthogonal problems. Technometrics 12:55–67
Rasmussen CE, Williams CKI (2006) Gaussian processes for machine learning. The MIT Press
Bartels S, Hennig P (2020) Conjugate gradients for kernel machines. J Mach Learn Res 21:55
Butler A, Haynes RD, Humphries TD, Ranjan P (2014) Efficient optimization of the likelihood function in Gaussian process modelling. Comput Stat Data Anal 73:40–52. https://doi.org/10.1016/j.csda.2013.11.017
Czelusniak T, Amorim FL (2020) Selective laser sintering of carbon fiber–reinforced PA12: Gaussian process modeling and stochastic optimization of process variables. Int J Adv Manuf Technol 110:2049–2066. https://doi.org/10.1007/s00170-020-05993-5
Blum M, Riedmiller M (2013) Optimization of gaussian process hyperparameters using Rprop. ESANN 2013 proceedings, 21st European symposium on artificial neural networks, computational intelligence and machine learning. pp 339–344
Snoek J, Larochelle H, Adams Ryan P (2012) Practical bayesian optimization of machine learning algorithms. Adv Neur Inform Proc Syst NeurIPS Proc 25:2960–2968
Bardenet R, Brendel M, Kégl B, Sebag M (2013) Collaborative hyperparameter tuning. In: Proceedings of the 30th International Conference on Machine Learning, PMLR, pp199–207
Yogatama D, Mann G (2014) Efficient transfer learning method for automatic hyperparameter tuning. In: Proceedings of the 17th international con-ference on artificial intelligence and statistics (AISTATS), Reykjavik, Iceland. JMLR: W&CP, vol 33, 1077–1085
Du X, Xu H, Zhu F (2021) Understanding the effect of hyperparameter optimization on machine learning models for structure design problems. Comput Des 135:103013. https://doi.org/10.1016/j.cad.2021.103013
Klein A, Falkner S, Bartels S et al (2017) Fast Bayesian optimization of machine learning hyperparameters on large datasets. Artif Intell Stat PMLR 54:528–536
Deb K (2014) Optimization for engineering design: algorithms and examples, 2nd ed. Prentice Hall India Learning Private Limited, Delhi, India
Quinonero-Candela J, Rasmussen CE (2005) A unifying view of sparse approximate Gaussian process regression. J Mach Learn Res 6:1939–1959
Chalupka K, Williams CK, Murray I (2013) A framework for evaluating approximation methods for Gaussian process regression. J Mach Learn Res 14:333–350. https://doi.org/10.48550/arXiv.1205.6326
Schraudolph NN, Graepel T (2003) Combining conjugate direction methods with stochastic approximation of gradients. In: International workshop on artificial intelligence and statistics. Proceedings of machine learning research, pp 248–253
MacKay DJC (1997) Gaussian processes - a replacement for supervised neural networks? Lecture notes for a tutorial at conference on neural information processing systems
Lee S, Ha J, Zokhirova M et al (2018) Background information of deep learning for structural engineering. Arch Comput Methods Eng 25:121–129. https://doi.org/10.1007/s11831-017-9237-0
Li Y, Zhang Q, Yoon SW (2021) Gaussian process regression-based learning rate optimization in convolutional neural networks for medical images classification. Expert Syst Appl 184:115357. https://doi.org/10.1016/j.eswa.2021.115357
Carlone P, Aleksendrić D, Ćirović V, Palazzo GS (2014) Meta-modeling of the curing process of thermoset matrix composites by means of a FEM–ANN approach. Compos Part B Eng 67:441–448. https://doi.org/10.1016/j.compositesb.2014.08.022
Lee C-L, Wei K-H (2000) Curing kinetics and viscosity change of a two-part epoxy resin during mold filling in resin-transfer molding process. J Appl Polym Sci 77:2139–2148. https://doi.org/10.1002/1097-4628(20000906)77:10%3c2139::AID-APP6%3e3.0.CO;2-N
Lee C, Ho J, Wei K (2000) Resin transfer molding (RTM) process of a high performance epoxy resin. I: Kinetic studies of cure reaction. Polym Eng Sci 40:929–934. https://doi.org/10.1002/pen.11220
Yousefi A, Lafleur PG, Gauvin R (1997) Kinetic studies of thermoset cure reactions: a review. Polym Compos 18:157–168. https://doi.org/10.1002/pc.10270
Kamal MR, Sourour S (1973) Kinetics and thermal characterization of thermoset cure. Polym Eng Sci 13:59–64. https://doi.org/10.1002/pen.760130110
Shanku R, Vaughan JG, Roux JA (1997) Rheological characteristics and cure kinetics of EPON 862/W epoxy used in pultrusion. Adv Polym Technol 16:297–311. https://doi.org/10.1002/(SICI)1098-2329(199711)16:4%3c297::AID-ADV4%3e3.0.CO;2-Q
Hubert P, Johnston A, Poursartip A, Nelson K (2001) Cure kinetics and viscosity models for Hexcel 8552 epoxy resin. Int SAMPE Symp Exhib 46 II:2341–2354
O’Brien DJ, White SR (2003) Cure kinetics, gelation, and glass transition of a bisphenol F epoxide. Polym Eng Sci 43:863–874. https://doi.org/10.1002/pen.10071
Chen W (2019) An integrated flow-curing model for predicting residual stresses in textile composites. Doctoral dissertations, University of Connecticut
Tifkitsis KI, Skordos AA (2020) Real time uncertainty estimation in filling stage of resin transfer molding process. Polym Compos 41:5387–5402. https://doi.org/10.1002/pc.25803
Mesogitis TS, Skordos AA, Long AC (2015) Stochastic simulation of the influence of cure kinetics uncertainty on composites cure. Compos Sci Technol 110:145–151. https://doi.org/10.1016/j.compscitech.2015.02.009
Buche D, Schraudolph NN, Koumoutsakos P (2005) Accelerating evolutionary algorithms with Gaussian process fitness function models. IEEE Trans Syst Man Cybern Part C (Applications Rev 35:183–194. https://doi.org/10.1109/TSMCC.2004.841917
Shetty R, Pai RB, Rao SS, Nayak R (2009) Taguchi’s technique in machining of metal matrix composites. J Brazilian Soc Mech Sci Eng 31:12–20. https://doi.org/10.1590/S1678-58782009000100003
Powell MJD (1984) Nonconvex minimization calculations and the conjugate gradient method. 122–141
Bishnoi S, Ravinder R, Grover HS et al (2021) Scalable Gaussian processes for predicting the optical, physical, thermal, and mechanical properties of inorganic glasses with large datasets. Mater Adv 2:477–487. https://doi.org/10.1039/D0MA00764A
Abramowitz M, Stegun IA (1965) Handbook of mathematical functions, with formulas, graphs, and mathematical tables. Dover Publications, Inc. New York, USA
Ross PJ (1996) Taguchi techniques for quality engineering: loss function, orthogonal experiments, parameter and tolerance design, 2nd edn. McGraw Hill Professional, New York
Sanyılmaz M (2006) Design of experiment and an application for Taguchi method in quality improvement activity. Dumlupınar University, Turkey
Taguchi G, Chowdhury S, Wu Y (2004) Taguchi’s quality engineering handbook. John Wiley & Sons Inc, Hoboken, NJ, USA
Phadke MS (1989) Quality engineering using robust design. Prentice Hall, Englewood Cliffs, New Jersey
Roy RK (2010) A primer on the Taguchi method, 2nd edn. Society of Manufacturing Engineers, Dearborn, Michigan
Saha S, Ball AK, Mukherjee A et al (2021) Optimization of electrochemical etching process for manufacturing of micro electrodes for micro-EDM application. Proc Inst Mech Eng Part B J Eng Manuf 235:925–940. https://doi.org/10.1177/0954405420958961
Axelsson O (1987) A generalized conjugate gradient, least square method. Numer Math 51:209–227. https://doi.org/10.1007/BF01396750
Axelsson O (1980) Conjugate gradient type methods for unsymmetric and inconsistent systems of linear equations. Linear Algebra Appl 29:1–16. https://doi.org/10.1016/0024-3795(80)90226-8
Pratihar DK (2013) Soft computing: fundamentals and applications, 1st ed. Alpha Science International Ltd
Golub GH, Ye Q (1999) Inexact preconditioned conjugate gradient method with inner-outer iteration. SIAM J Sci Comput 21:1305–1320. https://doi.org/10.1137/S1064827597323415
Polak E, Ribiere G (1969) Note sur la convergence de méthodes de directions conjuguées. Rev française d’informatique Rech opérationnelle Série rouge 3:35–43. https://doi.org/10.1051/m2an/196903R100351
Kinsella J (1992) Comparison and evaluation of variants of the conjugate gradient method for efficient learning in feed-forward neural networks with backward error propagation. Netw Comput Neural Syst 3:27–35. https://doi.org/10.1088/0954-898X/3/1/005
Rao SS (2009) Engineering optimization. John Wiley & Sons Inc, Hoboken, NJ, USA
Kennedy J, Eberhart R Particle swarm optimization. In: Proceedings of ICNN’95 - International Conference on Neural Networks. IEEE, pp1942–1948
Goldberg DE (2006) Genetic algorithms in search, optimization and machine learning, 1st ed. Pearson Education India
Sivanandam SN, Deepa SN (2011) Principles of soft computing, 2nd ed. Wiley
Yang X-S (2009) Firefly algorithms for multimodal optimization. In: Stochastic algorithms: foundations and applications. Springer, Berlin, Heidelberg, pp 169–178
Yang X-S (2010) Nature-inspired metaheuristic algorithms, 2nd edn. Luniver Press, United Kingdom
Liu C, Gao F, Jin N (2014) Design and simulation of a modified firefly algorithm. In: 2014 seventh international joint conference on computational sciences and optimization. IEEE, pp 21–25
Ball AK, Roy SS, Kisku DR et al (2020) Optimization of drop ejection frequency in EHD inkjet printing system using an improved firefly algorithm. Appl Soft Comput 94:106438. https://doi.org/10.1016/j.asoc.2020.106438
Refaeilzadeh P, Tang L, Liu H et al (2020) Encyclopedia of database systems. Springer, New York, New York, NY
Friedman M (1937) The use of ranks to avoid the assumption of normality implicit in the analysis of variance. J Am Stat Assoc 32:675–701. https://doi.org/10.1080/01621459.1937.10503522
Sheskin DJ (2011) Handbook of parametric and nonparametric statistical procedures, 5th ed. Chapman and Hall/CRC
Iman RL, Davenport JM (1980) Approximations of the critical region of the fbietkan statistic. Commun Stat - Theory Methods 9:571–595. https://doi.org/10.1080/03610928008827904
Yang X, He X (2018) Why the firefly algorithm works? In: Nature-Inspired Algorithms and Applied Optimization, pp245–259
Singh M, Patel RN, Neema DD (2019) Robust tuning of excitation controller for stability enhancement using multi-objective metaheuristic firefly algorithm. Swarm Evol Comput 44:136–147. https://doi.org/10.1016/j.swevo.2018.01.010
Yang X-S (2010) Engineering optimization. John Wiley & Sons Inc, Hoboken, NJ, USA
Funding
This research is supported by the AFRL Materials and Manufacturing Directorate (AFRL/RXMS) under contract FA8650-18-C-5700.
Author information
Authors and Affiliations
Contributions
A. Ball, K. Zhou, D. Xu, D. Zhang, and J. Tang worked together to generate the conception of the work. A. Ball carried out algorithm development, data analysis and interpretation, and drafted the paper. K. Zhou and D. Xu supported the algorithm development and data analysis. D. Zhang provided guidance on process modeling and results interpretation. J. Tang provided advisement to A. Ball and also provided critical revision of the paper.
Corresponding author
Ethics declarations
Ethical approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Conflict of interest
The authors declare no competing interest.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Ball, A.K., Zhou, K., Xu, D. et al. Directed Gaussian process metamodeling with improved firefly algorithm (iFA) for composite manufacturing uncertainty propagation analysis. Int J Adv Manuf Technol 126, 49–66 (2023). https://doi.org/10.1007/s00170-023-10994-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-023-10994-1