Abstract
Cork-rubber composites are materials that can be used in different applications ranging from industry to construction sectors. One of its applications is building vibration isolation. One of the principal requirements in the design of these materials is the capacity of supporting static compressive loads. In this study, based on the shape factor and hardness Shore A of a cork-rubber block, the application of artificial neural networks methodology, for the prediction of apparent compression modulus, was evaluated. A large database with compression test results was used for the training and testing of neural networks. Using the early stopping method, several studies were performed regarding artificial neural networks architecture and training: the number of neurons on the hidden layer, change of training parameters and dataset division method. Neural networks with three neurons on the hidden layer proved to be more efficient without overfitting and presented a good correspondence between predicted and measured results. The use of different methods to divide the dataset through different development stages also influences the model performance. A comparison of performance with other models available in the literature revealed that the chosen ANN model proved, in most cases, to have a better performance regarding these materials.
Similar content being viewed by others
References
Mestre A, Vogtlander J (2013) Eco-efficient value creation of cork products: an LCA-based method for design intervention. J Clean Prod 57:101–114. https://doi.org/10.1016/j.jclepro.2013.04.023
Gil L (2009) Cork composites: a review. Materials 2:776–789. https://doi.org/10.3390/ma2030776
Silva SP, Sabino MA, Fernandes EM et al (2005) Cork: properties, capabilities and applications. Int Mater Rev 50:345–365. https://doi.org/10.1179/174328005X41168
Gent AN (1958) On the relation between indentation hardness and Young’s modulus. Rubber Chem Technol 31:896–906
BS 903 Methods of testing vulcanised rubber Part 19 (1950) and Part A7 (1957)
Qi HJ, Joyce K, Boyce MC (2003) Durometer hardness and the stress-strain behavior of elastomeric materials. Rubber Chem Technol 76:419–435. https://doi.org/10.5254/1.3547752
Kunz J, Studer M (2006) Determining the modulus of elasticity in compression via the shore a hardness. Kunststoffe Int 96:92–94
Gent AN (2012) Engineering with rubber: How to design rubber components. Carl Hanser Verlag GmbH & Co, KG
Fediuc DO, Budescu M, Fediuc V, Venghiac V-M (2013) Compression modulus of elastomers. Bul Inst Politeh Lasi Sect Constructii Arhitectura 59:157–166
Gent AN, Lindley PB (1959) The compression of bonded rubber blocks. Proc Inst Mech Eng 173:111–122. https://doi.org/10.1243/PIME
Lindley PB (1979) Compression moduli for blocks of soft elastic material bonded to rigid end plates. Anal Eng Design 14:11–16
Horton JM, Tupholme GE, Gover MJC (2002) Axial loading of bonded rubber blocks. J Appl Mech 69:836–843. https://doi.org/10.1115/1.1507769
Williams JG, Gamonpilas C (2008) Using the simple compression test to determine Young’s modulus, Poisson’s ratio and the Coulomb friction coefficient. Int J Solids Struct 45:4448–4459. https://doi.org/10.1016/j.ijsolstr.2008.03.023
Khanam PN, AlMaadeed MA, AlMaadeed S et al (2016) Optimization and prediction of mechanical and thermal properties of graphene/LLDPE nanocomposites by using artificial neural networks. Int J Polymer Sci 2016:15
Altarazi S, Ammouri M, Hijazi A (2018) Artificial neural network modeling to evaluate polyvinylchloride composites’ properties. Comput Mater Sci 153:1–9. https://doi.org/10.1016/j.commatsci.2018.06.003
Bustillo A, Urbikain G, Perez JM et al (2018) Smart optimization of a friction-drilling process based on boosting ensembles. J Manuf Syst 48:108–121. https://doi.org/10.1016/j.jmsy.2018.06.004
Van DD, Ly H-B, Trinh SH et al (2019) Artificial intelligence approaches for prediction of compressive strength of geopolymer concrete. Materials 12:983. https://doi.org/10.3390/ma12060983
Ling Y, Wang K, Wang X, Li W (2021) Prediction of engineering properties of fly ash-based geopolymer using artificial neural networks. Neural Comput Appl 33:85–105. https://doi.org/10.1007/s00521-019-04662-3
Wang Y, Wu X, Li X et al (2020) Prediction and analysis of tensile properties of austenitic stainless steel using artificial neural network. Metals 10:234. https://doi.org/10.3390/met10020234
Zhang Z, Friedrich K (2003) Artificial neural networks applied to polymer composites: a review. Compos Sci Technol 63:2029–2044. https://doi.org/10.1016/S0266-3538(03)00106-4
Sha W, Edwards KL (2007) The use of artificial neural networks in materials science based research. Mater Des 28:1747–1752. https://doi.org/10.1016/j.matdes.2007.02.009
Xiang KL, Xiang PY, Wu YP (2014) Prediction of the fatigue life of natural rubber composites by artificial neural network approaches. Mater Des 57:180–185. https://doi.org/10.1016/j.matdes.2013.12.044
Sankar HR, Srikant RR, Krishna PV et al (2013) Estimation of the dynamic properties of epoxy glass fabric composites with natural rubber particle inclusions. Int J Automotive Mech Eng 7:968–980
Karaaǧaç B, Inal M, Deniz V (2009) Artificial neural network approach for predicting optimum cure time of rubber compounds. Mater Des 30:1685–1690. https://doi.org/10.1016/j.matdes.2008.07.010
Iglesias C, Anjos O, Martínez J et al (2015) Prediction of tension properties of cork from its physical properties using neural networks. Eur J Wood Wood Prod 73:347–356. https://doi.org/10.1007/s00107-015-0885-1
García Á, Anjos O, Iglesias C et al (2015) Prediction of mechanical strength of cork under compression using machine learning techniques. Mater Des 82:304–311. https://doi.org/10.1016/j.matdes.2015.03.038
Jain AK, Mao J, Mohiuddin KM (1996) Artificial neural networks: A tutorial. Computer 29:31–44. https://doi.org/10.1109/2.485891
Beale M, Hagan M, Demuth H (2019) MATLAB Deep Learning ToolboxTM User’s Guide R2019b. The MathWorks, Inc.
Plaut D, Nowlan S, Hinton G (1986) Experiments on learning by back propagation. Technical Report CMU-CS-86–126
Prechelt L (1998) Early stopping– but when? In: Orr GB, Müller K-R (eds) Neural networks: tricks of the trade. Springer, Berlin, pp 55–69
Levenberg K (1944) A method for the solution of certain non-linear problems in least squares. Q Appl Math 2:164–168. https://doi.org/10.1090/qam/10666
Marquardt DW (1963) An Algorithm for Least-Squares Estimation of Nonlinear Parameters. J Soc Ind Appl Math 11:431–441. https://doi.org/10.1137/0111030
Yu H, Wilamowski BM (2011) Levenberg-Marquardt Training. In: Wilamowski BM, Irwin JD (eds) Intelligent Systems: The Industrial Electronics Handbook, 2nd edn. CRC Press, Boca Raton
Lopes H, Silva S, Machado J (2020) Analysis of the effect of shape factor on cork-rubber composites under small strain compression. Appl Sci 10:7177. https://doi.org/10.3390/App10207177
Acknowledgements
The authors are grateful to FCT—Fundação para a Ciência e Tecnologia who financially supported this work through scholarship SFRH/BD/136700/2018 and to Amorim Cork Composites. This work has been supported by FCT—Fundação para a Ciência e Tecnologia within the R&D Units Project Scope: UIDP/04077/2020 and UIDB/04077/2020.
Funding
This study was funded by Fundação para a Ciência e Tecnologia (grant number SFRH/BD/136700/2018), by company Amorim Cok Composites and, also, funded within the R&D Units Project Scope: UIDP/04077/2020 and UIDB/04077/2020, by Fundação para a Ciência e Tecnologia.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lopes, H., Silva, S.P. & Machado, J. Application of artificial neural networks to predict mechanical behaviour of cork-rubber composites. Neural Comput & Applic 33, 14069–14078 (2021). https://doi.org/10.1007/s00521-021-06048-w
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06048-w