Predicting Wood Thermal Conductivity Using Artificial Neural Networks

Authors

  • Stavros Avramidis
  • Lazaros Iliadis

Keywords:

Artificial neural networks, density, moisture content, temperature, thermal conductivity coefficient, wood

Abstract

An artificial neural network model that estimates wood thermal conductivity under a wide range of conditions of moisture content, temperature and apparent density was developed and tested with literature-obtained experimental data. The optimal network was determined to consist of an input layer, three hidden layers, and one output layer following the feed forward network structure and more specifically the back-propagation algorithm. Each of the three hidden layers of the ANN consisted of eleven neurons. The Neuralworks software package was used for the determination of the network structure and architecture, and for the training and testing phase. The evaluation produced an R2 value equal to 0.9994 and a RMS Error equal to 0.0123, thus proving that the developed ANN model is a reliable approach with powerful predictive capacity towards the estimation of thermal conductivity and it can be used by researchers under a wide range of conditions.

References

Avramidis, S., and L. Iliadis. 2005. Wood-water sorption isotherm prediction with artificial neural networks: a preliminary study. Holzforschung59(3):336-341.nBishop, M. C. 1994. Neural networks and their applications. Rev. Sci. Instr.64(6):1803-1831.nCai, L., and J. Chang. 1995. Using FEM to analyse heat transfer processes in wood. Holz Roh-Werkst.53(3): 183-186.nCallan R. 1999. The essence of neural networks. Prentice Hall, UK.nChia, L. H. L, P. H. Chua, and E. E. N. Lee. 1985. A preliminary study on the thermal conductivity and flammability of WPC based on some tropical woods. Radiat. Phys. Chem.26(4):423-432.nGaupe, D. 1997. Principles of artificial neural networks. World Scientific, Singapore.nHendricks, L. T. 1962. Thermal conductivity of wood as a function of temperature and moisture contant. M.S. Thesis, SUNY College of Forestry, Syracuse, NY.nHornik, K., M. Stinchombe, and H. White. 1989. Multilayer feed forward networks are universal approximators. Neural Network2:359-366.nJacobs, R. A. 1988. Increased rates of convergence through training rate adaption. Neural Networks1:295-307.nKeey, R. B., T. A. G. Langrish, and J. C. F. Walker. 2000. Kiln-drying of lumber. Springer, New York, NY.nKhattabi, A. and P. Steinhagen. 1993. Analysis of transient nonlinear heat conduction in wood using finite-difference solutions. Holz Roh-Werkst.51(4):272-278.nKoumoutsakos, A., S. Avramidis, and S. Hatzikiriakos. 2003. Radio frequency vacuum drying Part III. Two-dimensional model, optimization and validation. Drying Technol.21(8):1399-1410.nLeondes, C. 1998. Fyzzy logic and expert systems applications. Academic Press, California.nMacLean, J. D. 1941. Thermal conductivity of wood. Heating, Piping and Air Conditioning, 13:380-391.nMaku, T. 1954. Studies on the heat conduction in wood. Wood Res. Bull. 13, Wood Res. Inst., Kyoto Univ., Kyoto, Japan.nMinai, A. A., and R. D. Wiliams. 1990. Acceleration of Back-Propagation through Training Rate and Momentum Adaption. International Joint Conference on Neural Networks. Vol. I, pp. 676-679.nNeural Computing. 2001. A technology handbook for neuralworks professional II PLUS. Carnegie, PA.nNeuralware. 2001. Getting started. A tutorial for Neuralworks Professional II/PLUS. Carnegie, PA.nNeuralworks Professional II PLUS. 2001. Reference Guide. Carnegie, PA.nPicton P. 2000. Neural Networks. 2nd ed. Palgrave, New York, NY.nRummelhart, D. E., G. E. Hinton, and R. J. Wiliams. 1985. Training internal representations by error propagation. Institute for Cognitive Science Report 8506, University of California, San Diego, CA.nShida, S. 1982. Studies on thermal insulation property of wood based materials and wood frame wall. Ph.D. Dissertation, University of Tokyo, Tokyo, Japan.nSiau, J. F. 1970. A geometrical model for thermal conductivity. Wood Fiber, 1:302-307.nSiau, J. F. 1984. Transport processes in wood, Springer-Verlag, New York, NY.nSiau, J. F. 1995. Wood: Influence of moisture on physical properties. Department of Wood Science and Forest Products, VPI&SU, Blacksburg, VA.nSteinhagen, P. 1977. Thermal conductive properties of wood, green or dry, from -40° to +100°C: A literature review. USDA. Forest Prod. Lab. General Technical Report, FPL-9, Madison, WI.nSuleiman, B. M., B. Larfeldt, B. Leckner, and M. Gustavsson. 1999. Thermal conductivity and diffusivity of wood. Wood Sci. Technol.33(6):465-473.nWaangard, F. F. 1943. The effect of wood structure upon thermal conductivity. Trans. Am. Soc. Mech. Eng., 65: 127-135.n

Downloads

Published

2007-06-05

Issue

Number 4 / October 2005

Section

Research Contributions

License

The copyright of an article published in Wood and Fiber Science is transferred to the Society of Wood Science and Technology (for U. S. Government employees: to the extent transferable), effective if and when the article is accepted for publication. This transfer grants the Society of Wood Science and Technology permission to republish all or any part of the article in any form, e.g., reprints for sale, microfiche, proceedings, etc. However, the authors reserve the following as set forth in the Copyright Law:

1. All proprietary rights other than copyright, such as patent rights.

2. The right to grant or refuse permission to third parties to republish all or part of the article or translations thereof. In the case of whole articles, such third parties must obtain Society of Wood Science and Technology written permission as well. However, the Society may grant rights with respect to Journal issues as a whole.

3. The right to use all or part of this article in future works of their own, such as lectures, press releases, reviews, text books, or reprint books.