論文の公開元へ

書き出し

Refer/BibIX

RIS

BibTeX

TSV

Potential of machine learning approaches for predicting mechanical properties of spruce wood in the transverse direction

Chen, Shuoye Shiina, Rei Nakai, Kazushi Awano, Tatsuya Yoshinaga, Arata Sugiyama, Junji 京都大学 DOI:10.1186/s10086-023-02096-z

2023.06.25

概要

To predict the mechanical properties of wood in the transverse direction, this study used machine learning to extract the anatomical features of wood from cross-sectional stereograms. Specimens with different orientations of the ray parenchyma cell were prepared, and their modulus of elasticity (MOE) and modulus of rupture (MOR) were measured by a three-point bending test. The orientation of the ray parenchyma cell and wood density (ρ) were used as parameters for the MOE and MOR prediction. Conventional machine learning algorithms and artificial neural network were used, and satisfactory results were obtained in both cases. A regular convolutional neural network (CNN) and a density-informed CNN were used to automatically extract anatomical features from the specimens’ cross-sectional stereograms to predict the mechanical properties. The regular CNN achieved acceptable but relatively low accuracy in both the MOE and MOR prediction. The reason for this may be that ρ information could not be satisfactorily extracted from the images, because the images represented a limited region of the specimen. For the density-informed CNN, the average prediction coefficient for both the MOE and MOR drastically increased when ρ information was provided. A regression activation map was constructed to understand the representative anatomical features that are strongly related to the prediction of mechanical properties. For the regular CNN, the latewood region was highly activated in both the MOE and MOR prediction. It is believed that the ratio and orientation of latewood were successfully extracted for the prediction of the considered mechanical properties. For the density-informed CNN, the activated region is different. The earlywood region was activated in the MOE prediction, while the transition region between the earlywood and latewood was activated in the MOR prediction. These results may provide new insights into the relationship between the anatomical features and mechanical properties of wood.

論文の公開元へ

この論文で使われている画像

参考文献

1. Ross RJ (2010) Wood handbook-wood as an engineering material, U.S.

Dept. of Agriculture, Forest Service, Forest Products Laboratory, WI.

https://doi.org/10.2737/FPL-GTR-190

2. Guo K, Yang Z, Yu CH, Buehler MJ (2021) Artificial intelligence and

machine learning in design of mechanical materials. Mater Horiz

8:1153–1172. https://doi.org/10.1039/D0MH01451F

3. Mansfield SD, IIiadis L, Avramidis S (2007) Neural networks prediction of

bending strength and stiffness in western hemlock (Tsuga heterophylla

Raf.) Holzforschung 61:707–716. https://doi.org/10.1515/HF.2007.115

4. Esteban LG, Fernandez FG, DePalacios P (2011) Prediction of plywood

bonding quality using an artificial neural network. Holzoforschung

65:209–214. https://doi.org/10.1515/hf.2011.003

5. Tiryaki S, Hamzecebi 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.measu

rement.2013.12.004

6. Tiryaki S, Aydin A (2014) 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. https://

doi.org/10.1016/j.conbuildmat.2014.03.041

7. Nasir V, Nourian S, Avramidis S, Cool J (2019) Prediction of physical and

mechanical properties of thermally modified wood based on color

change evaluated by means of “group method of data handling” (GMDH)

neural network. Holzforschung 73:381–392. https://doi.org/10.1515/

hf-2018-0146

8. Fathi H, Nasir V, Kazemirad S (2020) Prediction of the mechanical properties of wood using guided wave propagation and machine learning.

Constr Build Mater 262: 120848. https://doi.org/10.1016/j.conbuildmat.

2020.120848

9. Haftkhani AR, Abdoli F, Sepehr A, Mohebby B (2021) Regression and ANN

models for predicting MOR and MOE of heat-treated fir wood. J Build Eng

42: 102788. https://doi.org/10.1016/j.jobe.2021.102788

10. Thygesen LG and Lundqvist SO (2000) NIR measurement of moisture

content in wood under unstable temperature conditions. Part 2. Handling temperature fluctuations. J Near Infrared Spectrosc 8: 191–199.

https://doi.org/10.1255/jnirs.278

11. Kothiyal V, Raturi A (2011) Estimating mechanical properties and specific

gravity for five-year-old Eucalyptus tereticornis having broad moisture

content range by NIR spectroscopy. Holzforschung 66:757–762. https://

doi.org/10.1515/hf.2011.055

12. Fujimoto T, Kobori H, Tsuchikawa S (2012) Prediction of wood density

independently of moisture conditions using near infrared spectroscopy. J

Near Infrared Spectrosc 20:353–359. https://doi.org/10.1255/jnirs.994

13. Ma T, Inagaki T, Tsuchikawa S (2017) Calibration of SilviScan data of

Crytomeria japonica wood concerning density and microfibril angles with

NIR hyperspectral imaging with high spatial resolution. Holzforschung

71:341–347. https://doi.org/10.1515/hf-2016-0153

14. Kobayashi K, Akada M, Torigoe T, Imazu S, Sugiyama J (2015) Automated

recognition of wood used in traditional Japanese sculptures by texture

analysis of their low-resolution computed tomography data. J Wood Sci

61:630–640. https://doi.org/10.1007/s10086-015-1507-6

15. Kobayashi K, Hwang SW, Lee WH, Sugiyama J (2017) Texture analysis of

stereograms of diffuse-porous hardwood: identification of wood species

used in Tripitaka Koreana. J Wood Sci 63:322–330. https://doi.org/10.

1007/s10086-017-1625-4

16. Hwang SW, Kobayashi K, Zhai S, Sugiyama J (2018) Automated identification of Lauraceae by scale-invariant feature transform. J Wood Sci

64:69–77. https://doi.org/10.1007/s10086-017-1680-x

17. Kobayashi K, Hwang SW, Okochi T, Lee WH, Sugiyama J (2019) Nondestructive method for wood identification using conventional X-ray

computed tomography data. J Cult Herit 38:88–93. https://doi.org/10.

1016/j.culher.2019.02.001

18. Kobayashi K, Kegasa T, Hwang SW, Sugiyama J (2019) Anatomical features

of Fagaceae wood statistically extracted by computer vision approaches:

some relationships with evolution. PLos ONE 14: e0220762. https://doi.

org/10.1371/journal.pone.0220762

19. Hwang SW, Kobayashi K, Sugiyama J (2020) Detection and visualization

of encoded local features as anatomical predictors in cross-sectional

images of Lauraceae. J Wood Sci 66:16. https://doi.org/10.1186/

s10086-020-01864-5

Page 13 of 13

20. Hwang SW, Sugiyama J (2021) Computer vision-based wood identification and its expansion and contribution potentials in wood science: a

review. Plant Methods 17:47. https://doi.org/10.1186/s13007-021-00746-1

21. Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification

with deep convolutional neural networks. Adv Neural Inf Process Syst

25:1097–1105

22. He T, Lu Y, Jiao L, Zhang Y, Jiang X, Yin Y (2020) Developing deep learning models to automate rosewood tree species identification for CITES

designation and implementation. Holzforschung 74:1123–1133. https://

doi.org/10.1515/hf-2020-0006

23. Wu J, Yin X, Xiao H (2018) Seeing permeability from images: fast prediction with convolutional neural networks. Sci Bull 63:1215–1222. https://

doi.org/10.1016/j.scib.2018.08.006

24. Sigaki HYD, Lenzi EK, Zola RS (2020) Learning physical properties of

liquid crystals with deep convolutional neural networks. Sci Rep 10:7664.

https://doi.org/10.1038/s41598-020-63662-9

25. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikn D, Batra D (2020)

Grad-CAM: visual explanations for deep networks via gradient-based

localization. Int J Comput Vis 128:336–359. https://doi.org/10.1007/

s11263-019-01228-7

26. Hwang SW, Isoda H, Nakagawa T, Sugiyama J (2021) Flexural anisotropy of

rift-sawn softwood boards induced by the end-grain orientation. J Wood

Sci 67:14. https://doi.org/10.1186/s10086-021-01946-y

27. Chen S, Awano T, Yoshinaga A, Sugiyama J (2022) Flexural behavior of

wood in the transverse direction investigated using novel computer

vision and machine learning approach. Holzforschung 76:875–885.

https://doi.org/10.1515/hf-2022-0096

28. Gibson LJ (2012) The hierarchical structure and mechanics of plant materials. J R Soc Interface 9:2749–2766. https://doi.org/10.1098/rsif.2012.0341

29. Domec JC, Barbara LG (2002) How do water transport and water storage

differ in coniferous earlywood and latewood? J Exp Bot 53:2369–2379.

https://doi.org/10.1093/jxb/erf100

30. Ohagama T, Yamada T (1981) Young’s moduli of earlywood and latewood

in transverse direction of softwoods. Zairyo 30:707–711. https://doi.org/

10.2472/jsms.30.707

31. Krauss A, Moliński W, Kúdela J, Cunderlík I (2011) Differences in the

mechanical properties of early and latewood within individual annual

rings in dominant pine tree (Pinus sylvstris L.) Wood Res 56: 1–12.

32. Büyüksarı Ü, As N, Dündar T (2017) Mechanical properties of earlywood

and latewood sections of scots pine wood. Bioresources 12:4004–4012.

https://doi.org/10.15376/biores.12.2.4004-4012.

33. Burley J, Evans J, Youngquist J (2004) Encyclopedia of forest sciences.

Elsevier Academic Press, Oxford

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

...

参考文献をもっと見る

分野

大学

学位論文種類・取得年

言語

Potential of machine learning approaches for predicting mechanical properties of spruce wood in the transverse direction

概要

この論文で使われている画像

関連論文

Machine learning-based evaluation of the damage using images on concrete infrastructure structures

Nondestructive spectroscopic research for fast growing hybrid wood

混合モデルの適用によるガーナ産チーク材の木材性質に関する研究

Material Evaluation of Cellulosic Materials by Terahertz Time-domain Spectroscopy

Irregular and suppressed elastic deformation by a structural twist in cellulose nanofibre models

参考文献

分野

大学

学位論文種類・取得年

言語

コピーが完了しました

URLをコピーしました

Potential of machine learning approaches for predicting mechanical properties of spruce wood in the transverse direction

概要

この論文で使われている画像

関連論文

Machine learning-based evaluation of the damage using images on concrete infrastructure structures

Nondestructive spectroscopic research for fast growing hybrid wood

混合モデルの適用によるガーナ産チーク材の木材性質に関する研究

Material Evaluation of Cellulosic Materials by Terahertz Time-domain Spectroscopy

Irregular and suppressed elastic deformation by a structural twist in cellulose nanofibre models

参考文献