Abstract
The properties of medium density fiberboard (MDF) panels manufactured by reconstituting wood fibers and binders under high temperature and pressure depend on various manufacturing variables, including wood-related parameters, adhesive-related ones, and process-related ones. This study focused on the analysis of big data (about 400 million data) of the manufacturing variables (1389 variables) of MDF panels to understand the influence of these variables on the properties of MDF, using Ridge, Lasso, and Elastic-net regression. Both Lasso and Elastic-net regression were better than Ridge one in predicting the properties of MDF. The analysis results also showed that flash tube dryer, mat forming, and hot-pressing variables were closely related to panel density while fiber bin, refiner, forming, press, and hot-press heating variables affected the modulus of rupture (MOR) of the MDF panel. The analysis of interactions between manufacturing variables and MDF properties showed that the panel density affected internal bond (IB) strength, core density, and moisture content while IB strength and moisture content were associated with the MOR of the MDF panel. However, it is not clear which variables are dominantly affecting the formaldehyde emission of MDF.
Similar content being viewed by others
References
Ayrilmis N, Benthien JT, Ohlmeyer M (2017) Effect of wood species, digester conditions, and defibrator disc distance on wettability of fiberboard. J Wood Sci 63:248–252. https://doi.org/10.1007/s10086-017-1620-9
Bickel PJ, Li B, Tsybakov AB, van de Geer SA, Yu B, Valdés T, Rivero C, Fan, van der Vaart A (2006) Regularization in Statistics. Sociedad de Estad´ıstica e Investigaci´on Operativa Test, 15(2): 271–344
Cai Z, Muehl JH, Winandy JE (2006) Effects of panel density and mat moisture content on processing medium density fiberboard. For Prod J 56(10):20–25
Chai T, Draxler RR (2014) Root mean square error (RMSE) or mean absolute error (MAE)? Geosci Model Dev Discuss 7:1525–1534. https://doi.org/10.5194/gmdd-7-1525-2014
Chicco D, Warrens MJ, Jurman G (2021) The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation. PeerJ Comput Sci 7:1–24. https://doi.org/10.7717/PEERJ-CS.623
Davenport TH, Barth P, Bean R (2012) How Big Data is different. MIT Sloan Management Review 54(1):22–25
Ding Wong E, Zhang M, Wang Guangping Han Q et al (2000) Formation of the density profile and its effects on the properties of fiberboard. J Wood Sci 46:202–209
Donoho DL (2000) High-dimensional data analysis: the curses and blessings of dimensionality. LECTURE 16: dimensions: concentration of Measure/Extreme stats. Hardvard University
Fan J, Han F, Liu H (2014) Challenges of Big Data analysis. Natl Sci Rev 1:293–314
Fosso Wamba S, Akter S, Edwards A et al (2015) How big data can make big impact: findings from a systematic review and a longitudinal case study. Int J Prod Econ 165:234–246. https://doi.org/10.1016/j.ijpe.2014.12.031
Friedman J, Hastie T, Tibshirani R (2010) Regularization paths for generalized linear models via coordinate descent. J Stat Softw 33:1–22. https://doi.org/10.18637/jss.v033.i01
Fürnkranz J, Chan PK, Craw S et al (2011a) Mean Absolute Error. Encyclopedia of machine learning. Springer US, Boston, MA, pp 652–652
Fürnkranz J, Chan PK, Craw S et al (2011b) Mean squared Error. Encyclopedia of machine learning. Springer US, Boston, MA, pp 653–653
Gao Y, Hua J, Chen G et al (2018) Prediction of Fiber quality using refining parameters in medium-density fiberboard production via the support Vector Machine Algorithm. BioResources 13:7229–7246. https://doi.org/10.15376/biores.13.4.8184-8197
Gao Y, Hua J, Chen G et al (2019) Bi-directional prediction of wood fiber production using the combination of improved particle swarm optimization and support vector machine. BioResources 14:7229–7246. https://doi.org/10.15376/biores.14.3.7229-7246
García-Nieto PJ, García-Gonzalo E, Paredes-Sánchez JP (2021) Prediction of the critical temperature of a superconductor by using the WOA/MARS, Ridge, Lasso and Elastic-net machine learning techniques. Neural Comput Appl 33:17131–17145. https://doi.org/10.1007/s00521-021-06304-z
Gul W, Khan A, Shakoor A (2017) Impact of hot pressing temperature on medium density fiberboard (MDF) performance. Adv Mater Sci Eng 2017:1–6. https://doi.org/10.1155/2017/4056360
He Z, Zhang Y, Wei W (2012) Formaldehyde and VOC emissions at different manufacturing stages of wood-based panels. Build Environ 47:197–204. https://doi.org/10.1016/j.buildenv.2011.07.023
Hoerl AE, Kennard RW (2000) Ridge Regression: Biased Estimation for Nonorthogonal Problems. 42(1): 80–86
Hong MK, Lubis MAR, Park BD (2017) Effect of panel density and resin content on properties of medium density fiberboard. J Korean Wood Sci Technol 45:444–455. https://doi.org/10.5658/WOOD.2017.45.4.444
Kuhn M (2008) Building Predictive models in R using the Caret Package. J Stat Softw 28
Lubis MAR, Hong MK, Park BD, Lee SM (2018) Effects of recycled fiber content on the properties of medium density fiberboard. Eur J Wood Prod 76:1515–1526. https://doi.org/10.1007/s00107-018-1326-8
Melkumova LE, Shatskikh SY (2017) Comparing Ridge and LASSO estimators for data analysis. Procedia Engineering. Elsevier Ltd, pp 746–755
Pugazhenthi N, Anand P (2021) Mechanical and thermal behavior of hybrid composite medium density fiberboard reinforced with phenol formaldehyde. Heliyon 7(12):1–7. https://doi.org/10.1016/j.heliyon.2021.e08597
Salem MZM, Böhm M (2013) Understanding of formaldehyde emissions from solid wood: an overview. BioResources 8(3):4775–4790
Skiera B, Reiner J, Albers S (2022) Regression analysis. Handbook of Market Research. Springer International Publishing, Cham, pp 299–327
Suchsland O, Woodson GE, McMillin CW (1986) Pressing of three-layer, dry-formed MDF with binderless hardboard faces. For Prod J 36:33–36
Thoemen Heiko (2010) Wood-based panels - an introduction for specialists. Brunel University Press
Tibshirani R (1996) Regression shrinkage and Selection Via the Lasso. J Roy Stat Soc: Ser B (Methodol) 58:267–288. https://doi.org/10.1111/j.2517-6161.1996.tb02080.x
Tiryaki S, Bardak S, Bardak T (2015) Experimental investigation and prediction of bonding strength of oriental beech (Fagus Orientalis Lipsky) bonded with polyvinyl acetate adhesive. J Adhes Sci Technol 29:2521–2536. https://doi.org/10.1080/01694243.2015.1072989
van Buuren S, Groothuis-Oudshoorn K (2011) Mice: multivariate imputation by chained equations in R. J Stat Software 45(3):1–67
Wamba SF, Gunasekaran A, Akter S et al (2017) Big data analytics and firm performance: effects of dynamic capabilities. J Bus Res 70:356–365. https://doi.org/10.1016/j.jbusres.2016.08.009
Wibowo ES, Lubis MAR, Park BD (2021) Simultaneous improvement of formaldehyde emission and adhesion of medium-density fiberboard bonded with low-molar ratio urea-formaldehyde resins modified with nanoclay. J Korean Wood Sci Technol 49:453–461. https://doi.org/10.5658/WOOD.2021.49.5.453
Williams EJ (1994) Downtime data - its collection, analysis, and importance. In: Winter Simulation Conference Proceedings. IEEE, pp 1040–1043
Willmott C, Matsuura K (2005) Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Clim Res 30:79–82. https://doi.org/10.3354/cr030079
Wright S (1921) CORRELATION AND CAUSATION. J Agric Res 20:557–585
Young TM, Shaffer LB, Guess FM et al (2008) A comparison of multiple linear regression and quantile regression for modeling the internal bond of medium density fiberboard. For Prod Journa 58:39–48
Zou H, Hastie T (2005) Regularization and variable selection via the elastic net. J Royal Stat Soc Ser B (Statistical Methodology) 67(2):301–320
Acknowledgements
This study was carried out with the support of R&D Program for Forest Science Technology (Project No. FTIS-2019149C10-2023-0301) provided by Korea Forest Service (Korea Forestry Promotion Institute).
Author information
Authors and Affiliations
Contributions
Byung-Dae Park and Seongsu Park contributed to the designing and writing of this manuscript, and Yongku Kim contributed to review and revise statistical analysis.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Electronic supplementary material
Below is the link to the electronic supplementary material.
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
Park, S., Park, BD. & Kim, Y. Big data analysis on manufacturing variables affecting properties of medium density fiberboard. Eur. J. Wood Prod. 82, 483–492 (2024). https://doi.org/10.1007/s00107-023-02030-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00107-023-02030-6