Home Comparison of various multivariate models to estimate structural properties by means of non-destructive techniques (NDTs) in Pinus sylvestris L. timber
Article
Licensed
Unlicensed Requires Authentication

Comparison of various multivariate models to estimate structural properties by means of non-destructive techniques (NDTs) in Pinus sylvestris L. timber

  • Antonio Villasante ORCID logo , Guillermo Íñiguez-González ORCID logo EMAIL logo and Lluis Puigdomenech ORCID logo
Published/Copyright: October 17, 2018
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Holzforschung
From the journal Holzforschung Volume 73 Issue 4

Abstract

The predictability of modulus of elasticity (MOE), modulus of rupture (MOR) and density of 120 samples of Scots pine (Pinus sylvestris L.) were investigated using various non-destructive variables (such as time of flight of stress wave, natural frequency of longitudinal vibration, penetration depth, pullout resistance, visual grading and concentrated knot diameter ratio), and based on multivariate algorithms, applying WEKA as machine learning software. The algorithms used were: multivariate linear regression (MLR), Gaussian, Lazy, artificial neural network (ANN), Rules and decision Tree. The models were quantified based on the root-mean-square error (RMSE) and the coefficient of determination (R2). To avoid model overfitting, the modeling was built and the results validated via the so-called 10-fold cross-validation. MLR with the “greedy method” for variable selection based on the Akaike information metric (MLRak) significantly reduced the RMSE of MOR and MOE compared to univariate linear regressions (ULR). However, this reduction was not significant for density prediction. The predictability of MLRak was not improved by any other of the tested algorithms. Specifically, non-linear models, such as multilayer perceptron, did not contribute any significant improvements over linear models. Finally, MLRak models were simplified by discarding the variables that produce the lowest RMSE increment. The resulted models could be even further simplified without significant RMSE increment.

Keywords: 10-fold cross-validation; multivariate models; non-destructive methods; predictability; root-mean-square error; structural timber

  1. Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.

  2. Research funding: Ministerio de Economía y Competitividad [Spanish Ministry of Economy and Competitiveness]. Plan Nacional I+D+i 2008-2011. Grant Number: Proy.: BIA 2010-18858.

  3. Employment or leadership: None declared.

  4. Honorarium: None declared.

References

Adell, F.J., Hermoso, E., Arriaga, F., Richter, C. (2008) Comparison of the Spanish visual strength grading standard for structural sawn timber (UNE 56544) with the German one (DIN 4074) for Scots pine (Pinus sylvestris L.) from Germany. Holz Roh Werkst. 66:253–258.10.1007/s00107-008-0241-9Search in Google Scholar

Aha, D., Kibler, D., Albert, M.K. (1991) Instance-based learning algorithms. Mach. Learn. 6:37–66.10.1007/BF00153759Search in Google Scholar

Arriaga, F., Íñiguez-González, G., Esteban, M., Divos, F. (2012) Vibration method for grading of large cross-section coniferous timber species. Holzforschung 66:381–387.10.1515/hf.2011.167Search in Google Scholar

Arriaga, F., Montón, J., Segues, E., Iñiguez-González, G. (2014) Determination of the mechanical properties of radiata pine timber by means of longitudinal and transverse vibration methods. Holzforschung 68:299–305.10.1515/hf-2013-0087Search in Google Scholar

Avramidis, S., Iliadis, L. (2005a) Predicting wood thermal conductivity using artificial neural networks. Wood Fiber Sci. 37:682–690.Search in Google Scholar

Avramidis, S., Iliadis L. (2005b) Wood-water sorption isotherm prediction with artificial neural networks: a preliminary study. Holzforschung 59:336–341.10.1515/HF.2005.055Search in Google Scholar

Bell, E.R., Peck, E.C., Krueger, N.T. Young’s modulus of wood determined by a dynamic method. Report 1775. U.S. Department of Agriculture, Forest Service, Forest Products Laboratory, Madison, WI, 1950.Search in Google Scholar

Bobadilla, I., Esteban, M., Íñiguez, G., Arriaga, F., Ballarín, D., Palacios, J. (2007) Density estimation by screw withdrawal resistance and probing in structural sawn coniferous timber, and modulus of elasticity assessment. Inf. Constr. 59:107–116.10.3989/ic.2007.v59.i506.513Search in Google Scholar

Branco, J.M., Piazza, M., Cruz, P.J.S. (2010) Structural analysis of two King-post timber trusses: non-destructive evaluation and load-carrying tests. Constr. Build. Mater. 24:371–383.10.1016/j.conbuildmat.2009.08.025Search in Google Scholar

Cavalli, A., Togni, M. (2013) How to improve the on-site MOE assessment of old timber beams combining NDT and visual strength grading. Nondestruct. Test. Eval. 28:252–262.10.1080/10589759.2013.764424Search in Google Scholar

Cleary, J.G., Trigg, L.E. (1995) K*: an instance-based learner using an entropic distance measure. 12th International Conference on Machine Learning. Morgan Kaufmann Publishers, Massachusetts, USA. pp. 108–114.10.1016/B978-1-55860-377-6.50022-0Search in Google Scholar

Cook, D.F., Chiu, C.C. (1997) Predicting the internal bond strength of particleboard, utilizing a radial basis function neural network. Eng. Appl. Artif. Intell. 10:171–177.10.1016/S0952-1976(96)00068-1Search in Google Scholar

Cook, D.F., Whittaker, A.D. (1992) Neural network models for prediction of process parameters in wood products manufacturing. In: 1st Industrial Engineering Research Conference Proceedings. Eds. Klutke, G.A., Mitta, D.A., Nnaji, B.O., Seiford, L.M. (Institute of Industrial Engineers). Chicago, IL, USA. pp. 209–211.Search in Google Scholar

Divos, F., Sismandy, F. (2010) Strength grading of structural lumber by portable lumber grading – effect of knots. The Future of Quality Control for Wood & Wood Products’, 4–7th May 2010, Edinburgh. The Final Conference of COST Action E53. Forest Products Research Institute/Centre for Timber Engineering Edinburgh Napier University, Edinburgh, Scotland, UK.Search in Google Scholar

European Standard (2002) EN 13183-2. Moisture content of a piece of sawn timber. Part 2: estimation by electrical resistance method. European Committee of Standardization (CEN), Brussels, Belgium.Search in Google Scholar

European Standard (2012) EN 408. Timber structures. Structural timber and glued laminated timber. Determination of some physical and mechanical properties. European Committee of Standardization (CEN), Brussels, Belgium.Search in Google Scholar

European Standard (2016) EN 384. Structural timber. Determination of characteristic values of mechanical properties and density. European Committee of Standardization (CEN), Brussels, Belgium.Search in Google Scholar

Esteban, L.G., Fernández, F.G., de Palacios, P. (2009) MOE prediction in Abies pinsapo Boiss. timber: application of an artificial neural network using nondestructive testing. Comput. Struct. 87:1360–1365.10.1016/j.compstruc.2009.08.010Search in Google Scholar

Esteban, L.G., Fernández, F.G., de Palacios, P., González Rodrigo, B. (2010) Use of artificial neural networks as a predictive method to determine moisture resistance of particle and fiber boards under cyclic testing conditions (UNE-EN 321). Wood Fiber Sci. 42:1–11.Search in Google Scholar

Fernández, F.G., de Palacios, P., Esteban, L.G., García-Iruela, A., González Rodrigo, B., Menasalvas, E. (2012) Prediction of MOR and MOE of structural plywood board using an artificial neural network and comparison with a multivariate regression model. Composites: Part B 43:3528–3533.10.1016/j.compositesb.2011.11.054Search in Google Scholar

Frank, E. Fully supervised training of Gaussian radial basis function networks in WEKA (Computer Science Working Papers, 04/2014).Department of Computer Science, The University of Waikato, Hamilton, NZ, 2014.Search in Google Scholar

Frank, E., Hall, M.A., Witten, I.H. (2016) The WEKA Workbench. Online Appendix for “Data Mining: Practical Machine Learning Tools and Techniques”. Morgan Kaufmann Publishers, Massachusetts, USA., pp. 525.Search in Google Scholar

Galiginaitis, S.V., Bell, E.R., Fine, A.M. Nondestructive testing of wood laminates. Final Report. Office of Naval Research, Institute of Industrial Research, University of Louisville, Louisville, KY, 1954.Search in Google Scholar

García Fernández, F., Esteban, L.G., de Palacios, P., Navarro, N., Conde, M. (2008) Prediction of standard particleboard mechanical properties utilizing an artificial neural network and subsequent comparison with a multivariate regression model. Inv. Agrar.-Sist. Recursos Fores. 17:178–187.10.5424/srf/2008172-01033Search in Google Scholar

García-Iruela, A., García Fernández, F., Esteban, L.G., de Palacios, P., Simón, C., Arriaga, F. (2016) Comparison of modelling using regression techniques and an artificial neural network for obtaining the static modulus of elasticity of Pinus radiata D. Don. timber by ultrasound. Composites: Part B 96:112–118.10.1016/j.compositesb.2016.04.036Search in Google Scholar

García de Ceca, J.L., Hermoso, E., Mateo, R., Íñiguez-González, G. Neural network models for the establishment of a structural stress grading methodology using nondestructive techniques. 18th International Nondestructive Testing and Evaluation of Wood Symposium. General Technical Report FPL-GTR-226.U.S. Department of Agriculture, Forest Service, Forest Products Laboratory, Madison, WI, 2013. pp. 808.Search in Google Scholar

Hellier, C.J. Handbook of Nondestructive Evaluation, Second Edition. McGraw-Hill Professional, US, 2012.Search in Google Scholar

Hermoso, E. Caracterización mecánica de la madera estructural de Pinus sylvestris L. Tesis doctoral. Universidad Politécnica de Madrid, ETS de Ingenieros de Montes, 2001. pp. 277. Archivo PDF: http://oa.upm.es/644.Search in Google Scholar

Holmes G., Hall M., Prank E. Generating Rule Sets from Model Trees. Lecture Notes in Computer Science: Advanced Topics in Artificial Intelligence 1747:1–12. Springer, Berlin, Heidelberg, 1999.10.1007/3-540-46695-9_1Search in Google Scholar

Íñiguez, G. Grading by Non Destructive Techniques and Assessment of the Mechanical Properties of Large Cross Section Coniferous Sawn Timber for Structural Use. Doctoral thesis. Universidad Politécnica de Madrid, ETS de Ingenieros de Montes, 2007a. pp. 223.Search in Google Scholar

Íñiguez, G., Arriaga, F., Esteban, M., Argüelles, R. (2007b) Vibration methods as non-destructive tool for structural properties assessment of sawn timber. Inf. Constr. 59:97–105.10.3989/ic.2007.v59.i506.512Search in Google Scholar

Íñiguez, G., Arriaga, F., Esteban, M., Bobadilla, I., González, C., Martínez, R. (2010) In-situ non-destructive density estimation for the assessment of existing timber structures. In: 10th World Conference on Timber Engineering. Ed. Ceccotti, A. Trento, Italy.Search in Google Scholar

Íñiguez-González, G., Montón, J., Arriaga, F., Segués, E. (2015) In-situ assessment of structural timber density using non-destructive and semi-destructive testing. BioResources 10:2256–2265.10.15376/biores.10.2.2256-2265Search in Google Scholar

James, W.L. (1962) Dynamic strength and elastic properties of wood. Forest Prod. J. 12:253–260.Search in Google Scholar

Jayne, B.A. (1959) Vibrational properties of wood as indices of quality. Forest Prod. J. 9:413–416.Search in Google Scholar

Jordan, R., Feeney, F., Nesbitt, N., Evertsen, J.A. (1998) Classification of wood species by neural network analysis of ultrasonic signals. Ultrasonics 36:219–222.10.1016/S0041-624X(97)00148-0Search in Google Scholar

Kohavi, R. (1995) The power of decision tables. Machine learning: ECML-95. pp. 174–189.10.1007/3-540-59286-5_57Search in Google Scholar

Llana, D.F., Iñiguez-Gonzalez, G., Arriaga, F., Wang, X. (2016) Time-of-flight adjustment procedure for acoustic measurements in structural timber. BioResources 11:3303–3317.10.15376/biores.11.2.3303-3317Search in Google Scholar

Llana, D.F., Íñiguez-González, G., Martínez, R.D., Arriaga, F. (2018a) Influence of timber moisture content on wave time-of-flight and longitudinal natural frequency in coniferous species for different instruments. Holzforschung 72:405–411.10.1515/hf-2017-0113Search in Google Scholar

Llana, D.F., Hermoso, E., Bobadilla, I., Íñiguez-González, G. (2018b) Influence of moisture content on the results of penetration and withdrawal resistance measurements on softwoods. Holzforschung 72:549–555.10.1515/hf-2017-0133Search in Google Scholar

Madsen, B. Structural behaviour of timber. Timber Engineering Ltd., North Vancouver, BC, Canada, 1992. pp. 405.Search in Google Scholar

Madsen, B., Buchanan, A.H. (1986) Size effects in timber explained by a modified Weakest-link theory. Can. J. Civil. Eng. 13: 218–232.10.1139/l86-030Search in Google Scholar

MacKay, D.J.C. (2003) Information theory, inference and learning algorithms. Cambridge University Press, Cambridge, UK. pp. 628. Chapter 45.Search in Google Scholar

Mansfield, S.D., Iliadis, L., Avramidis, S. (2007) Neural network prediction of bending strength and stiffness in western hemlock (Tsuga heterophylla Raf.). Holzforschung 61:707–716.10.1515/HF.2007.115Search in Google Scholar

Mansfield, S.D., Kang, K.Y., Iliadis, L., Tachos, S., Avramidis, S. (2011) Predicting the strength of Populus spp. clones using artificial neural networks and e-regression support vector machines (e-rSVM). Holzforschung 65:855–863.10.1515/HF.2011.107Search in Google Scholar

McKean, H.B., Hoyle, R.J. Stress Grading Method for Dimension Lumber. Special Technical Publication. 353. American Society for Testing Materials, Philadelphia, PA, 1962.Search in Google Scholar

Mier Pérez R. Clasificación de madera aserrada estructural mediante inteligencia artificial: Redes Neuronales. Master Thesis. ETSI de Montes, Universidad Politécnica de Madrid, 2001.Search in Google Scholar

Mier Pérez R., García De Ceca J.L., Díez Barra M.R., Fernández-Golfín Seco J.I., Hermoso Prieto E. (2005) Aplicación de redes neuronales a la clasificación de madera estructural. Comparación con otros modelos de clasificación. Proceedings of IV Congreso Forestal Español, Zaragoza, Spain.Search in Google Scholar

Pellerin, R.F. (1965) A vibrational approach to nondestructive testing of structural lumber. Forest Prod. J. 15:93–101.Search in Google Scholar

Pellerin, R.F., Ross, R.J. Nondestructive Evaluation of Wood. Forest Products Society. Madison, WI, USA, 2002. pp. 210.Search in Google Scholar

Platt, J. (1998) Sequential minimal optimization: a fast algorithm for training support vector machines. Technical Report MSR-TR-98-14, Microsoft Research. pp. 12.Search in Google Scholar

Ponneth, D., Vasu, A.E., Easwaran, J.C., Mohandass, A., Chauhan, S.S. (2014) Destructive and non-destructive evaluation of seven hardwoods and analysis of data correlation. Holzforschung 68:951–956.10.1515/hf-2013-0193Search in Google Scholar

Quinlan, J.R. (1992) Learning with continuous classes. In: 5th Australian Joint Conference on Artificial Intelligence 92. Eds. Adams & Sterling. Singapore. pp. 343–348.Search in Google Scholar

Rousseeuw, P.J., Leroy, A.M. Wiley Series in Probability and Mathematical Statistics, in Robust Regression and Outlier Detection. John Wiley & Sons, Inc., Hoboken, NJ, USA, 1987.10.1002/0471725382Search in Google Scholar

Senft, J.F., Suddarth, S.K., Angleton, H.D. (1962) A new approach to stress grading of lumber. Forest Prod. J. 12:183–186.Search in Google Scholar

Shevade, S.K., Keerthi, S.S., Bhattacharyya, C., Murthy, K.R.K. (1999) Improvements to the SMO algorithm for SVM regression. IEEE Trans. Neural Netw. 11:1188–1193.10.1109/72.870050Search in Google Scholar PubMed

Spanish Standard (2011) UNE 56544. Clasificación visual de la madera aserrada para uso estructural. Asociación Española de Normalización (AENOR), Madrid, Spain.Search in Google Scholar

Tanaka, T., Tanaka, T., Nagao, H., Kato, H. (1996) A preliminary investigation on evaluation of strength of softwood timbers by neural network. Proceeding of the 10th International Symposium on Nondestructive Testing of Wood, Lausanne. pp. 323–329.Search in Google Scholar

Thelandersson, S., Larsen, H.J. Timber Engineering. John Wiley & Sons, Chichester, 2003. pp. 456.Search in Google Scholar

Tiryaki, S., Aydın, 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. 62:102–108.10.1016/j.conbuildmat.2014.03.041Search in Google Scholar

Tiryaki, S., Hamzaçebi, C. (2014) Predicting modulus of rupture (MOR) and modulus of elasticity (MOE) of heat treated woods by artificial neural networks. Measurement 49:266–274.10.1016/j.measurement.2013.12.004Search in Google Scholar

Vega, A., Dieste, A., Guaita, M., Majada, J., Baño, V. (2012) Modelling of the mechanical properties of Castanea sativa Mill. Structural timber by a combination of non-destructive variables and visual grading parameters. Eur. J. Wood Prod. 70:839–844.10.1007/s00107-012-0626-7Search in Google Scholar

Wang, Y. A new approach to fitting linear models in high dimensional spaces. PhD thesis, Department of Computer Science, University of Waikato, New Zealand, 2000.Search in Google Scholar

Received: 2018-05-01
Accepted: 2018-09-23
Published Online: 2018-10-17
Published in Print: 2019-04-24

©2019 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Frontmatter
  2. Original Articles
  3. Rapid identification of wood species by near-infrared spatially resolved spectroscopy (NIR-SRS) based on hyperspectral imaging (HSI)
  4. Comparison of various multivariate models to estimate structural properties by means of non-destructive techniques (NDTs) in Pinus sylvestris L. timber
  5. Influence of length on acoustic time-of-flight (ToF) measurement in built-in structures of Norway spruce timber
  6. Characterization of Pinus nigra var. laricio [Maire] bark extracts at the analytical and pilot scale
  7. Determination of the absolute molar mass of acetylated eucalyptus kraft lignin by two types of size-exclusion chromatography combined with multi-angle laser light-scattering detectors
  8. Moisture-induced deformation in the neck of a classical guitar
  9. 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
  10. A self-cleaning surface based on heat treatment of g-C3N4-coated wood prepared by a rapid and eco-friendly method
  11. Mechanical, thermo-mechanical and water uptake performance of wood flour filled polyurethane elastomer eco-composites: influence of surface treatment of wood flour
  12. Investigation of a new formaldehyde-free adhesive consisting of soybean flour and Kymene® 736 for interior plywood
  13. Negative oxygen ion (NOI) production by enhanced photocatalytic TiO2/GO composites anchored on wooden substrates
https://doi.org/10.1515/hf-2018-0103
Keywords for this article
10-fold cross-validation; multivariate models; non-destructive methods; predictability; root-mean-square error; structural timber

Articles in the same Issue

  1. Frontmatter
  2. Original Articles
  3. Rapid identification of wood species by near-infrared spatially resolved spectroscopy (NIR-SRS) based on hyperspectral imaging (HSI)
  4. Comparison of various multivariate models to estimate structural properties by means of non-destructive techniques (NDTs) in Pinus sylvestris L. timber
  5. Influence of length on acoustic time-of-flight (ToF) measurement in built-in structures of Norway spruce timber
  6. Characterization of Pinus nigra var. laricio [Maire] bark extracts at the analytical and pilot scale
  7. Determination of the absolute molar mass of acetylated eucalyptus kraft lignin by two types of size-exclusion chromatography combined with multi-angle laser light-scattering detectors
  8. Moisture-induced deformation in the neck of a classical guitar
  9. 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
  10. A self-cleaning surface based on heat treatment of g-C3N4-coated wood prepared by a rapid and eco-friendly method
  11. Mechanical, thermo-mechanical and water uptake performance of wood flour filled polyurethane elastomer eco-composites: influence of surface treatment of wood flour
  12. Investigation of a new formaldehyde-free adhesive consisting of soybean flour and Kymene® 736 for interior plywood
  13. Negative oxygen ion (NOI) production by enhanced photocatalytic TiO2/GO composites anchored on wooden substrates
Sign up now to receive a 20% welcome discount
Institutional Access
How does access work?
Have an idea on how to improve our website?
Please write us.
© 2025 De Gruyter Brill
Downloaded on 29.10.2025 from https://www.degruyterbrill.com/document/doi/10.1515/hf-2018-0103/html
Scroll to top button