The relationship between color and mechanical properties of heat-treated wood predicted based on support vector machines model
-
Shuang Chen
und
Li Yan
Abstract
Thermal modification or heat treatment can cause the loss of mechanical property of wood. In this study, Poplar (Populus tomentosa Carr.) and spruce (Picea obies Mast.) were heat treated at 180, 200, and 220 °C for 2–10 h. Changes of color (L*, a* and b*) and mechanical strength including modulus of elasticity (MOE), modulus of rupture (MOR) and shear strength after heat treatment were analyzed. Time-temperature superposition methods were used to quantify color and mechanical strength. The prediction models of MOR, MOE and shear strength were assessed with support vector regression model (SVR) based on color parameters. The trends of color change and mechanical strength after heat treatment were highly consistent. The values of apparent activation energy (E a ) calculated from color parameters (110.6–187.2 kJ/mol) were identical to those from mechanical strengths (103.2–219.2 kJ/mol). Color parameters were used as input variables, and the MOE, MOR, and shear strength were output parameters in the established SVR model. Gaussian radial basis function (RBF) was found to be a kernel function for SRV model. Optimal hyperparameters in SVR model were obtained using cross-validation and grid search. The determination coefficients for MOE, MOR, and shear strength were 0.903, 0.835, and 0.865, respectively for poplar. The high correlation suggested that wood mechanical strength can be predicted non-destructively through measuring color parameters after heat treatment.
Funding source: Fundamental Research Funds for the Central Universities
Award Identifier / Grant number: 2452019057
Funding source: National Natural Science Foundation of China
Award Identifier / Grant number: 31971590
-
Author contributions: Shuang Chen and Jiapeng Wang: methodology, investigation, writing – original draft, data curation. Yanxu Liu: formal analysis, software and visualization. Zhangjing Chen: writing – review & editing. Yafang Lei: supervision and validation. Li Yan: conceptualization, resources, supervision, funding acquisition, project administration. All the authors have approved the submission for publication.
-
Research funding: This study was supported by the National Natural Science Foundation of China (31971590) and Fundamental Research Funds for the Central Universities (2452019057).
-
Conflict of interest statement: The authors declare that they have no conflicts of interest regarding this article.
References
Bal, B.C. (2018). A comparative study of some of the mechanical properties of pine wood heat treated in vacuum, nitrogen and air atmospheres. Bioresources 13: 5504–5511, https://doi.org/10.15376/biores.13.3.5504-5511.Suche in Google Scholar
Bekhta, P. and Niemz, P. (2003). Effect of high temperature on the change in color, dimensional stability and mechanical properties of spruce wood. Holzforschung 57: 539–546, https://doi.org/10.1515/hf.2003.080.Suche in Google Scholar
Borůvka, V., Zeidler, A., Holeček, T., and Dudík, R. (2018). Elastic and strength properties of heat-treated beech and birch wood. Forests 9: 197, https://doi.org/10.3390/f9040197.Suche in Google Scholar
Brischke, C., Welzbacher, C.R., Brandt, K., and Rapp, A.O. (2007). Quality control of thermally modifified timber: interrelationship between heat treatment intensities and CIE L* a* b* color data on homogenized wood samples. Holzforschung 61: 19–22, https://doi.org/10.1515/hf.2007.004.Suche in Google Scholar
Burges, C.J. (1998). A tutorial on support vector machines for pattern recognition. Data Min. Knowl. Discov. 2: 121–167, https://doi.org/10.1023/a:1009715923555.10.1023/A:1009715923555Suche in Google Scholar
Ebner, M. and Petutschnigg, A.J. (2007). Potentials of thermally modified beech (Fagus sylvatica) wood for application in toy construction and design. Mater. Des. 28: 1753–1759, https://doi.org/10.1016/j.matdes.2006.05.015.Suche in Google Scholar
Francisco, G.F., Paloma, D.P., Luis, G.E., Alberto, G.I., Beatriz, G.R., and Ernestina, M. (2012). Prediction of MOR and MOE of structural plywood board using an artificial neural network and comparison with a multivariate regression model. Compos. B Eng. 43: 3528–3533, https://doi.org/10.1016/j.compositesb.2011.11.054.Suche in Google Scholar
González-Peña, M.M. and Hale, M.D. (2009). Colour in thermally modified wood of beech, Norway spruce and Scots pine, Part 2: property predictions from colour changes. Holzforschung 63: 394–401, https://doi.org/10.1515/HF.2009.077.Suche in Google Scholar
Hazir, E., Ozcan, T., and Koç, K.H. (2020). Prediction of adhesion strength using extreme learning machine and support vector regression optimized with genetic algorithm. Arabian J. Sci. Eng. 45: 6985–7004, https://doi.org/10.1007/s13369-020-04625-0.Suche in Google Scholar
He, Z., Wang, Z., Qu, L., Qian, J., and Yi, S. (2019). Modeling and simulation of heat-mass transfer and its application in wood thermal modification. Results Phys. 13: 102213, https://doi.org/10.1016/j.rinp.2019.102213.Suche in Google Scholar
Herrera-Díaz, R., Sepúlveda-Villarroel, V., Pérez-Peña, N., Salvo-Sepúlveda, L., Salinas-Lira, C., Llano-Ponte, R., and Ananías, R.A. (2018). Effect of wood drying and heat modification on some physical and mechanical properties of radiata pine. Dry. Technol. 36: 537–544, https://doi.org/10.1080/07373937.2017.1342094.Suche in Google Scholar
Johansson, D. and Morén, T. (2006). The potential of colour measurement for strength prediction of thermally treated wood. Holz als Roh- Werkst. 64: 104–110, https://doi.org/10.1007/s00107-005-0082-8.Suche in Google Scholar
Matsuo, M., Yokoyama, M., Umemura, K., Gril, J., Yano, K., and Kawai, S. (2010). Color changes in wood during heating: kinetic analysis by applying a time-temperature superposition method. Appl. Phys. A: Mater. Sci. Process. 99: 47–52, https://doi.org/10.1007/s00339-010-5542-2.Suche in Google Scholar
Matsuo, M., Yokoyama, M., Umemura, K., Sugiyama, J., Kawai, S., Gril, J., Kubodera, S., Mitsutani, T., Ozaki, H., Sakamoto, M., et al.. (2011). Aging of wood: analysis of color changes during natural aging and heat treatment. Holzforschung 65: 361–368, https://doi.org/10.1515/hf.2011.040.Suche in Google Scholar
Matsuo, M., Umemura, K., and Kawai, S. (2012). Kinetic analysis of color changes in cellulose during heat treatment. J. Wood Sci. 58: 113–119, https://doi.org/10.1007/s10086-011-1235-5.Suche in Google Scholar
Matsuo, M., Umemura, K., and Kawai, S. (2014). Kinetic analysis of color changes in Keyaki (Zelkova serrata) and sugi (Cryptomeria japonica) wood during heat treatment. J. Wood Sci. 60: 12–20, https://doi.org/10.1007/s10086-013-1369-8.Suche in Google Scholar
Matsuo, M.U., Mitsui, K., Kobayashi, I., Kohara, M., Yoshida, M., and Yamamoto, H. (2016). Effect of hygrothermal treatment on wood properties: color changes and kinetic analysis using four softwood and seven hardwood species. Wood Sci. Technol. 50: 1145–1160, https://doi.org/10.1007/s00226-016-0833-1.Suche in Google Scholar
Nasir, V., Nourian, S., Avramidis, S., and Cool, J. (2019). Classification of thermally treated wood using machine learning techniques. Wood Sci. Technol. 53: 275–288, https://doi.org/10.1007/s00226-018-1073-3.Suche in Google Scholar
Okon, K.E., Lin, F., Lin, X., Chen, C.X., Chen, Y.D., and Huang, B. (2018). Modification of Chinese Fir (Cunninghamia lanceolata L.) wood by silicone oil heat treatment with micro-wave pretreatment. Eur. J. Wood Wood Prod. 76: 221–228, https://doi.org/10.1007/s00107-017-1165-z.Suche in Google Scholar
Racasan, S., Bedelean, B., Georgescu, S., and Varodi, A.M. (2020). Comparison between artificial neural networks and response surface methodology to predict the bending moment capacity of heat-treated wood dowel joints. Bioresources 15: 5764–5775, https://doi.org/10.15376/biores.15.3.5764-5775.Suche in Google Scholar
Ruiz-Aquino, F., Gonzalez-Pena, M.M., Valdez-Hernandez, J.I., Romero-Manzanares, A., and Fuentes-Salinas, M. (2018). Mechanical properties of wood of two Mexican oaks: relationship to selected physical properties. Eur. J. Wood Wood Prod. 76: 69–77, https://doi.org/10.1007/s00107-017-1168-9.Suche in Google Scholar
Scholkopf, B. and Smola, A.J. (2002). Learning with kernels: support vector machines, regulari-zation, optimization, and beyond: adaptive computation and machine learning. MIT Press, Cambridge, MA.Suche in Google Scholar
Smola, A.J. and Schölkopf, B. (2004). A tutorial on support vector regression. Stat. Comput. 14: 199–222, https://doi.org/10.1023/b:stco.0000035301.49549.88.10.1023/B:STCO.0000035301.49549.88Suche in Google Scholar
Tiryaki, S. (2015). Investigating the relationship between some mechanical properties and weight loss in heat treated woods. J. Polytech. 18: 149–154.Suche in Google Scholar
Tiryaki, S. and Hamzaçebi, C. (2014). Predicting modulus of rupture (MOR) and modulus of elasticity (MOE) of heat treated woods by artificial neural networks. Measurement 49: 266–274, https://doi.org/10.1016/j.measurement.2013.12.004.Suche in Google Scholar
Trzciński, T. and Rokita, P. (2017). Predicting popularity of online videos using support vector regression. IEEE Trans. Multimed. 19: 2561–2570, https://doi.org/10.1109/tmm.2017.2695439.Suche in Google Scholar
Vapnik, V.N. (1995). The nature of statistical learning theory. Springer, New York.10.1007/978-1-4757-2440-0Suche in Google Scholar
Welzbacher, C.R., Brischke, C., Rapp, A.O., Koch, S., and Hofer, S. (2009). Performance of thermally modified timber (tmt) in outdoor application - durability, abrasion and optical appearance. Dev. Ind. 60: 75–82, https://doi.org/10.1007/s00226-008-0200-y.Suche in Google Scholar
Wennekers, T. (2001). Orientation tuning properties of simple cells in area V1 derived from an approximate analysis of nonlinear neural field models. Neural Comput. 13: 1721–1747, https://doi.org/10.1162/08997660152469323.Suche in Google Scholar PubMed
Yan, L. and Morrell, J.M. (2019). Kinetic color analysis for assessing the effects of borate and glycerol on thermal modification of wood. Wood Sci. Technol. 53: 263–274, https://doi.org/10.1007/s00226-018-1072-4.Suche in Google Scholar
Yang, H., Cheng, W., and Han, G. (2015). Wood modification at high temperature and pressurized steam: a relational model of mechanical properties based on a neural network. Bioresources 10: 5758–5776, https://doi.org/10.15376/biores.10.3.5758-5776.Suche in Google Scholar
Supplementary Material
The online version of this article offers supplementary material (https://doi.org/10.1515/hf-2022-0075).
© 2022 Walter de Gruyter GmbH, Berlin/Boston
Artikel in diesem Heft
- Frontmatter
- Original Articles
- Intra-species variation in maximum moisture content, cell-wall density and porosity of hardwoods
- Fractal dimension of wood pores from pore size distribution
- Fatigue testing of wood up to one billion load cycles
- The influence of vacuum heat treatment on the pore structure of earlywood and latewood of larch
- The relationship between color and mechanical properties of heat-treated wood predicted based on support vector machines model
- Effect of water/moisture migration in wood preheated by hot press on sandwich compression formation
- Quercetin-grafted modification to improve wood decay resistance
- Organosolv delignification of birch wood (Betula pendula): DMSO/water pulping optimization
- Alkali lignin as a pH response bifunctional material with both adsorption and flocculation for wastewater treatment
- Evaluation of the mechanical properties of different parts of bending bamboo culm by nanointendation
Artikel in diesem Heft
- Frontmatter
- Original Articles
- Intra-species variation in maximum moisture content, cell-wall density and porosity of hardwoods
- Fractal dimension of wood pores from pore size distribution
- Fatigue testing of wood up to one billion load cycles
- The influence of vacuum heat treatment on the pore structure of earlywood and latewood of larch
- The relationship between color and mechanical properties of heat-treated wood predicted based on support vector machines model
- Effect of water/moisture migration in wood preheated by hot press on sandwich compression formation
- Quercetin-grafted modification to improve wood decay resistance
- Organosolv delignification of birch wood (Betula pendula): DMSO/water pulping optimization
- Alkali lignin as a pH response bifunctional material with both adsorption and flocculation for wastewater treatment
- Evaluation of the mechanical properties of different parts of bending bamboo culm by nanointendation
