Skip to main content

Advertisement

SpringerLink
Log in

Prediction of Adhesion Strength Using Extreme Learning Machine and Support Vector Regression Optimized with Genetic Algorithm

  • Research Article-Systems Engineering
  • Published:
Arabian Journal for Science and Engineering Aims and scope Submit manuscript

Abstract

Adhesion strength is one of the most significant quality characteristics for coating performance. Heat treatment and sanding process parameters affect the adhesion strength. The aim of this study was to predict the adhesion strength using machine learning and optimization algorithms. Process factors were selected such as temperature, time, cutting speed, feed rate and grit size while coating performance index was selected as adhesion strength. Adhesion strength values of the specimens were determined by employing pull-off adhesion-type equipment. Firstly, central composite design with analysis of variance was used to create the experimental design and to determine the effective factors. Moreover, the main effect plot was used to determine the values of effective factors. Then, support vector machine (SVR) and extreme learning machine (ELM) were used to predict the adhesion strength. Finally, genetic algorithm was applied to optimize the parameters of SVM and ELM in order to improve the prediction accuracy. The proposed hybrid SVR-GA and ELM-GA approaches were compared with linear regression (LR), SVR and ELM. Experimental results showed that the proposed SVR-GA and ELM-GA approaches outperformed the LR, SVR and ELM in terms of prediction accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8

Similar content being viewed by others

References

  1. Bekhta, P.; Krystofiak, T.; Proszyk, S.; Lis, B.: Surface gloss of lacquered medium density fiberboard panels veneered with thermally compressed birch wood. Prog. Org. Coat. 117, 10–19 (2018). https://doi.org/10.1016/j.porgcoat.2017.12.020

    Article  Google Scholar 

  2. Toker, H.; Hiziroglu, S.; Ozcifci, A.: Influence of weathering an adhesion strength of chemically treated and coated scot pine. Prog. Org. Coat. 73, 211–214 (2012). https://doi.org/10.1016/j.porgcoat.2011.11.001

    Article  Google Scholar 

  3. Bekhta, P.; Proszyk, S.; Krystofiak, T.; Sedliacik, J.; Novak, I.; Mamonova, M.: Effect of short-term thermomechanical densification on the structure and properties of wood veneers. Wood Mater. Sci. Eng. 12, 40–54 (2017). https://doi.org/10.1080/17480272.2015.1009488

    Article  Google Scholar 

  4. We, Y.; Wang, M.; Zhang, P.; Chen, Y.; Gao, J.; Fan, Y.: The role of phenolic extractives in color changes of Locust Wood (Robinia pseudoacacia) during heat treatment. BioResources 12, 7041–7055 (2017)

    Google Scholar 

  5. Boonstra, M.J.; Tjeerdsma, B.: Chemical analysis of heat treated softwood. Holz als Roh-unWerkstoff 64, 204–211 (2006). https://doi.org/10.1007/s00107-005-0078-4

    Article  Google Scholar 

  6. Dubey, M.K.; Pang, S.; Walker, J.: Oil uptake by wood during heat-treatment and post-treatment cooling, and effects on wood dimensional stability. Eur. J. Wood Wood Prod. 70, 183–190 (2012). https://doi.org/10.1007/s00107-011-0535-1

    Article  Google Scholar 

  7. Huang, X.; Kocaefe, D.; Kocaefe, Y.; Pichette, A.: Combined effect of acetylation and heat treatment on the physical, mechanical and biological behavior of jack pine (Pinus banksiana) wood. Eur. J. Wood Wood Prod. 76, 525–540 (2018). https://doi.org/10.1007/s00107-017-1232-5

    Article  Google Scholar 

  8. Unsal, O.; Korkut, S.; Atik, C.: The effect of heat treatment on some technological properties and color in eucalyptus (Eucalyptus camaldulensis Dehn) wood. Maderas Ciencia Y Technological 5, 145–152 (2003). https://doi.org/10.4067/S0718-221X2003000200006

    Article  Google Scholar 

  9. Bekhta, P.; Krystofiak, T.; Proszyk, S.; Lis, B.: Adhesion strength of thermally compressed and varnished (TCW) substrate. Prog. Org. Coat. 125, 331–338 (2018). https://doi.org/10.1016/j.porgcoat.2018.09.013

    Article  Google Scholar 

  10. Richter, K.; Feist, W.C.; Knaebe, M.T.: The effect of surface roughness on the performance of finishes. Part 1. Roughness characterization and stain performance. For. Prod. J. 45, 91–97 (1995)

    Google Scholar 

  11. Özdemir, T.; Hiziroglu, S.; Kocapınar, M.: Adhesion strength of cellulosic varnish coated wood species as function of their surface roughness. Adv. Mater. Sci. Eng. Int. J. (2015). https://doi.org/10.1155/2015/525496

    Article  Google Scholar 

  12. Salca, E.A.; Krystofiak, T.; Lis, B.: Evaluation of selected properties of alder wood as functions of sanding and coating. Coatings 7, 176–182 (2017). https://doi.org/10.3390/coatings7100176

    Article  Google Scholar 

  13. Sogutlu, C.; Nzokou, P.; Koc, I.; Tutgun, R.; Döngel, N.: The effects of surface roughness on varnish adhesion strength of wood materials. J. Coat. Technol. Res. 13, 863–870 (2016). https://doi.org/10.1007/s11998-016-9805-5

    Article  Google Scholar 

  14. Alipanahpour Dil, E.; Ghaedi, M.; Ghaedi, A.M.; Asfaram, A.; Goudarzi, A.; Hajati, S.; Soylak, M.; Agarwal, S.; Gubta, V.K.: Modeling of quaternanaty dyes adsorption onto ZnO-NR-AC artificial neural network: analysis by derivative spectrophotometry. J. Ind. Eng. Chem. 34, 186–197 (2016). https://doi.org/10.1016/j.jiec.2015.11.010

    Article  Google Scholar 

  15. Laha, D.; Ren, Y.; Suganthan, P.N.: Modeling of steelmaking process with effective machining learning techniques. Expert Syst. Appl. 42, 4687–4696 (2015). https://doi.org/10.1016/j.eswa.2015.01.030

    Article  Google Scholar 

  16. Sarikaya, M.; Güllü, A.: Taguchi design and response surface methodology based analysis of machining parameters in CNC turning under MQL. J. Clean. Prod. 65, 604–616 (2016). https://doi.org/10.1016/j.jclepro.2013.08.040

    Article  Google Scholar 

  17. Panigrahi, S.; Behera, H.S.: A study on leading machine learning techniques for high order fuzzy time series forecasting. Eng. Appl. Artif. Intell. (2020). https://doi.org/10.1016/j.engappai.2019.103245

    Article  Google Scholar 

  18. Tiryaki, S.; Aydın, A.: An artificial neural network model for predicting compression strength of heat treated woods and comparison with a multiple linear regression model. Constr. Build. Mater. 62, 102–108 (2014). https://doi.org/10.1016/j.conbuildmat.2014.03.041

    Article  Google Scholar 

  19. Zhang, J.; Qu, L.; Wanh, Z.; Zhao, Z.; He, Z.; Yi, S.: Simulation and validation of heat transfer during wood heat treatment process. Results Phys. 7, 3806–3812 (2017). https://doi.org/10.1016/j.rinp.2017.09.046

    Article  Google Scholar 

  20. Nguyen, T.H.V.; Nguyen, T.T.; Ji, X.; Do, K.T.L.; Guo, M.: Using artificial neural network (ANN) for modeling predicting hardness change of wood during heat treatment. IOP Conf. Ser. Mater. Sci. Eng. 394, 1–7 (2018)

    Google Scholar 

  21. Nguyen, T.H.V.; Nguyen, T.T.; Ji, X.; Guo, M.: Predicting color change in wood heat treatment using an artificial neural network model. BioResources 11, 6250–6264 (2018). https://doi.org/10.15376/biores.13.3.6250-6264

    Article  Google Scholar 

  22. Ozsahin, S.; Murat, M.: Prediction of equilibrium moisture content and specific gravity of heat treated wood by artificial neural networks. Eur. J. Wood Prod. 76, 563–572 (2018). https://doi.org/10.1007/s00107-017-1219-2

    Article  Google Scholar 

  23. Cool, J.; Hernandez, R.E.: Effects of peripheral planning on surface characteristics and adhesion of a waterborne acrylic coating to black spruce wood. For. Prod. J. 62, 124–133 (2012). https://doi.org/10.13073/0015-7473-62.2.124

    Article  Google Scholar 

  24. Ugulino, B.; Hernandez, R.E.: Assessment of surface properties and solvent-borne coating performance of red oak wood produced by peripheral planning. Eur. J. Wood Prod. 75, 581–593 (2017). https://doi.org/10.1007/s00107-016-1090-6

    Article  Google Scholar 

  25. Salca, E.A.; Krystofiak, T.; Lis, B.; Mazela, B.; Proszyk, S.: Some coating properties of black alder wood as a function of varnish type and application method. BioResources 11, 7580–7594 (2016). https://doi.org/10.15376/biores.11.3.7580-7594

    Article  Google Scholar 

  26. Ghasemi, E.; Kalhori, H.; Bagherpour, R.: A new hybrid ANFIS-PSO model for prediction of peak particle velocity due to bench blastik. Eng. Comput. 32, 607–614 (2016). https://doi.org/10.1007/s00366-016-0438-1

    Article  Google Scholar 

  27. Kazem, A.; Sharifi, E.; Hussain, F.K.; Saberi, M.; Hussain, O.K.: Support vector regression with chaos-based firefly algorithm for stock market price forecasting. Appl. Soft Comput. 13, 947–958 (2013). https://doi.org/10.1016/j.asoc.2012.09.02

    Article  Google Scholar 

  28. Esfa, M.H.; Ahangar, M.R.H.; Rejvani, M.; Toghraire, D.; Hajmohammad, M.H.: Designing an artificial neural network to predict dynamic viscosity of aqueous nanofluid of TiO2 using experimental data. Int. Commun. Heat Mass Transf. 75, 192–196 (2016). https://doi.org/10.1016/j.icheatmasstransfer.2016.04.002

    Article  Google Scholar 

  29. Patel, J.; Shah, S.; Thakkar, P.; Kotecha, K.: Predicting stock market index using fusion of machine learning techniques. Expert Syst. Appl. 42, 2162–2172 (2015). https://doi.org/10.1016/j.eswa.2014.10.031

    Article  Google Scholar 

  30. Vapnik, V.: The Nature of Statistical Learning Theory. Springer, Berlin (1999)

    MATH  Google Scholar 

  31. Huang, G.B.; Zhu, Q.Y.; Siev, C.K.: Extreme learning machine: theory and applications. Neurocomputing 70, 489–501 (2006). https://doi.org/10.1016/j.neucom.2005.12.126

    Article  Google Scholar 

  32. Cao, J.; Zhang, K.; Luo, M.; Yin, C.; Lai, X.: Extreme learning machine and adaptive sparse representation for image classification. Neural Netw. 81, 91–102 (2016). https://doi.org/10.1016/j.neunet.2016.06.001

    Article  Google Scholar 

  33. Qin, L.; Yi, Z.; Zhang, Y.: Enhanced surface roughness discrimination with optimized features bio-inspired tactile sensor. Sens. Actuators A 264, 133–140 (2017). https://doi.org/10.1016/j.sna.2017.07.054

    Article  Google Scholar 

  34. Rafiei, M.; Niknam, T.; Khooban, M.H.: Probabilistic forecasting of hourly electricity price by generalization of ELM for usage improved wavelet neural network. IEEE Trans. Ind. Inf. 13, 71–79 (2017). https://doi.org/10.1109/tii.2016.2585378

    Article  Google Scholar 

  35. Holland, J.M.: Adaptation in Natural and Artificial Systems. University of Michigan Press, Ann Arbor (1975)

    Google Scholar 

  36. Hazir, E.; Ozcan, T.: Response surface methodology integrated with desirability function and genetic algorithm approach for the optimization of CNC machining parameters. Arab. J. Sci. Eng. 44, 2795–2809 (2019). https://doi.org/10.1007/s13369-018-3559-6

    Article  Google Scholar 

  37. Falkenauer, E.: Applying genetic algorithms to real-world problems. Evolut. Algorithms 111, 65–88 (1999). https://doi.org/10.1007/978-1-4612-1542-4_4

    Article  MathSciNet  Google Scholar 

  38. Kadri, R.L.; Boctor, F.F.: An efficient genetic algorithm to solve the resource-constrained Project scheduling problem with transfer times: the single mode case. Eur. J. Oper. Res. 265, 454–462 (2018). https://doi.org/10.1016/j.ejor.2017.07.027

    Article  MathSciNet  MATH  Google Scholar 

  39. Armaghani, D.J.; Hasanipanah, M.; Mahdiyari, A.; Majid, M.A.; Amnieh, H.B.; Tahir, M.M.D.: Airblast prediction through a hybrid genetic algorithm-ANN model. Neural Comput. Appl. 29, 619–629 (2018). https://doi.org/10.1007/s00521-016-2598-8

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Forest Industrial Engineering, Faculty of Forestry, Istanbul University - Cerrahpasa, 34473, Istanbul, Turkey

    Ender Hazir & Küçük Hüseyin Koç

  2. Department of Management Engineering, Faculty of Management, Istanbul Technical University, 34367, Istanbul, Turkey

    Tuncay Ozcan

Authors
  1. Ender Hazir
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Tuncay Ozcan
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Küçük Hüseyin Koç
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ender Hazir.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Appendix

Appendix

See Tables 10, 11 and 12.

Table 10 Experimental parameters and the recorded adhesion strength values
Full size table
Table 11 Predicted values of the proposed approaches for training data
Full size table
Table 12 Predicted values of the proposed approaches for testing data
Full size table

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hazir, E., Ozcan, T. & Koç, K.H. Prediction of Adhesion Strength Using Extreme Learning Machine and Support Vector Regression Optimized with Genetic Algorithm. Arab J Sci Eng 45, 6985–7004 (2020). https://doi.org/10.1007/s13369-020-04625-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s13369-020-04625-0

Keywords

Search

Navigation