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)
Keywords:
ANN, internal bond strength, swelling, artificial neural network, particleboard, fiberboardAbstract
Determining internal bond strength and thickness swelling after cyclic aging tests in humid conditions is essential to assess moisture resistance of particle and fiber boards. However, because operating procedures for these types of tests take at least 3 wk, their use in daily finished product control is impractical. To solve this problem, an artificial neural network was used as a predictive method to determine these values from the board properties of thickness, density, and moisture content in conjunction with thickness swelling and internal bond strength values obtained before the aging cycle. Using 113 boards, an artificial neural network was designed consisting of two separate feedforward multilayer perceptrons applying the hyperbolic tangent as the transfer function. Training was conducted through supervised learning after the input data had been normalized. In the testing group, the network attained a determination coefficient of 0.94 for internal bond strength and 0.92 for thickness swelling.References
AENOR (1994a) Tableros de partículas y tableros de fibras. Determinación de la hinchazón en espesor después de inmersión en agua. UNE-EN 317. Asociación Española de Normalización, Madrid, Spain.nAENOR (1994b) Tableros de partículas y tableros de fibras. Determinación de la resistencia a la tracción perpendicular a las caras del tablero. UNE-EN 319. Asociación Española de Normalización, Madrid, Spain.nAENOR (1994c) Tableros derivados de la madera. Determinación del contenido de humedad. UNE-EN 322. Asociación Española de Normalización, Madrid, Spain.nAENOR (1994d) Tableros derivados de la madera. Determinación de la densidad. UNE-EN 323. Asociación Española de Normalización, Madrid, Spain.nAENOR (1994e) Tableros derivados de la madera. Determinación de las dimensiones de las probetas. UNE-EN 325. Asociación Española de Normalización, Madrid, Spain.nAENOR (1995) Tableros derivados de la madera. Muestreo, despiece e inspección. Parte 1: Muestreo y despiece de probetas y expresión de los resultados de ensayo. UNE-EN 326-1. Asociación Española de Normalización, Madrid, Spain.nAENOR (2001) Tableros derivados de la madera. Muestreo, despiece e inspección. Parte 2: Control de la calidad en fábrica. UNE-EN 326-2. Asociación Española de Normalización, Madrid, Spain.nAENOR (2002) Tableros derivados de la madera. Determinación de la resistencia a la humedad bajo condiciones de ensayo cíclicas. UNE-EN 321. Asociación Española de Normalización, Madrid, Spain.nAENOR (2004) Tablero de Partículas. Especificaciones. UNE-EN 312. Asociación Española de Normalización, Madrid, Spain.nAENOR (2005) Evaluación de la conformidad. Requisitos generales para la competencia de los laboratorios de ensayo y calibración. UNE-EN ISO/IEC 17025. Asociación Española de Normalización, Madrid, Spain.nAENOR (2007) Tableros de fibras. Especificaciones. Parte 5: Requisitos de los tableros de fibras fabricados por proceso seco (MDF). UNE-EN 622-5. Asociación Española de Normalización, Madrid, Spain.nAvramidis S, Iliadis L. (2005) Predicting wood thermal conductivity using artificial neural networks. Wood Fiber Sci 37(4):682-690.nAvramidis S, Iliadis L, Mansfield SD. (2006) Wood dielectric loss factor prediction with artificial neural networks. Wood Sci Technol 40(7):563-574.nBaykaso˘lu A, Dereli T, Taniş S. (2004) Prediction of cement strength using soft computing techniques. Cement Concr Res 34(11):2083-2090.nBilim C, Atiş CD, Tanyildizi H, Karahan O. (2009) Predicting the compressive strength of ground granulated blast furnace slag concrete using artificial neural networks. Adv Eng Softw 40(5):334-340.nCheng CS. (1995) A multilayer neural-network model for detecting changes in the process mean. Comput Ind Eng 28(1):51-61.nCook DF, Chiu CC. (1997) Predicting the internal bond strength of particleboard, utilizing a radial basis function neural network. Eng Appl Artif Intell 10(2):171-177.nCook DF, Ragsdale CT, Major RL. (2000) Combining a neural network with a genetic algorithm for process parameter optimization. Eng Appl Artif Intell 13(4):391-396.nCook DF, Whittaker AD. (1992) Neural network models for prediction of process parameters in wood products manufacturing. Pages 209-211 in G-A Klutke, DA Mitta, BO Nnaji, and LM Seiford (Institute of Industrial Engineers), eds. Proc First Industrial Engineering Research Conference, May 20-21, Chicago, IL.nDe Veaux RD, Ungar LH. (1997) A brief introduction to neural networks. Technical Report. Williams College, University of Pennsylvania, Williamstown, PA. 28 pp.nDemuth H, Beale M, Hagan M. (2002) Neural network toolbox user's guide. Version 4. The Mathworks Inc., Natick, MA. 808 pp.nEsteban LG, Guindeo A, Peraza C, de Palacios P. (2002) La madera y su tecnología. AITIM—Fundación Conde del Valle de Salazar—Mundi-Prensa, Madrid, Spain. 332 pp.nEsteban LG, Fernández FG, de Palacios P. (2009a) MOE prediction in Abies pinsapo Boiss. timber: Application of an artificial neural network using non-destructive testing. Comput Struc 87(21-22):1360-1365.nEsteban LG, Fernández FG, de Palacios P, Conde M. (2009b) Artificial neural networks in variable process control: application in particleboard manufacture. Invest Agrar-Sist R 18(1):92-100.nEsteban LG, Fernández FG, de Palacios P, Romero RM, Cano NN. (2009c) Artificial neural networks in wood identification: The case of two Juniperus species from the Canary Islands. IAWA J 30(1):87-94.nFernández FG, Esteban LG, 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. Invest Agra-Sist R 17(2):178-187.nHagan MT, Demuth HB, Beale M. (1996) Neural network design. PWS Pub. Co., Boston, MA. 732 pp.nHassan AM, Alrashdan A, Hayajneh MT, Mayyas AT. (2009) Prediction of density, porosity and hardness in aluminum-copper-based composite materials using artificial neural network. J Mater Process Technol 209(2):894-899.nHaykin S. (1999) Neural networks: A comprehensive foundation. 2nd ed. Prentice Hall, Upper Saddle River, NJ. 842 pp.nHornik K, Stinchcombe M, White H. (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2(5):359-366.nLin TY, Tseng CH. (2000) Optimum design for artificial networks: An example in a bicycle derailleur system. Eng Appl Artif Intell 13(1):3-14.nMalinov S, Sha W, McKeown JJ. (2001) Modelling the correlation between processing parameters and properties in titanium alloys using artificial neural network. Comput Mater Sci 21(3):375-394.nMorris AJ, Montague GA, Willis MJ. (1994) Artificial neural networks: Studies in process modeling and control. Chem Eng Res Des 72(A1):3-19.nMukherjee A, Schmauder S, Rühle M. (1995) Artificial neural networks for the prediction of mechanical behaviour of metal matrix composites. Acta Metall Mater 43(11):4083-4091.nÖzcan F, Atiş CD, Karahan O, Uncuo˘lu E, Tanyildizi H. (2009) Comparison of an artificial neural network and fuzzy logic models for prediction of long-term compressive strength of silica fume concrete. Adv Eng Softw 40(9):856-863.nOzerdem MS, Kolukisa S. (2009) Artificial neural network approach to predict the mechanical properties of Cu-Sn-Pb-Zn-Ni cast alloys. Mater Des 30(3):764-769.nPriore P, de la Fuente D, Puente J, Pino R. (2002) Utilización de las redes neuronales en la toma de decisiones: Aplicación en un problema de secuenciación. Anales de Mecánica y Electricidad 79(6):28-34.nRafiq MY, Bugmann G, Easterbrook DJ. (2001) Neural network design for engineering applications. Comput Struc 79(17):1541-1552.nReddy NS, Krishnaiah J, Hong SG, Lee JS. (2009) Modeling medium carbon steels by using artificial neural networks. Mat Sci Eng A-Struct 508(1-2):93-105.nSandemir M. (2009) Prediction of compressive strength of concretes containing metakaolin and silica fume with artificial neural networks. Adv Eng Softw 40(5): 350-355.nSarle WS. (1997) Neural Networks FAQ, part 1-7: Introduction, periodic posting to the Usenet newsgroup comp.ai. neural-nets. ftp://ftp.sas.com/pub/neural/FAQ.html'>ftp://ftp.sas.com/pub/neural/FAQ.htmlnSha W. (2007) Comment on the issues of statistical modelling with particular reference to the use of artificial neural networks. Appl Catal Gen 324:87-89.nSha W, Edwards KL. (2007) The use of artificial neural networks in materials science based research. Mater Des 28(6):1747-1752.nSukthomya W, Tannock A. (2005) The training of neural networks to model manufacturing processes. J Intell Manuf 16(1):39-51.nTompos A, Margitfalvi JL, Tfirst E, Héberger K. (2007) Predictive performance of ‘highly complex’ artificial neural networks. Appl Catal Gen 324:90-93.nVanstone B, Finnie G. (2009) An empirical methodology for developing stockmarket trading systems using artificial neural networks. Expert Syst Appl 36(3):6668-6680.n
Downloads
Published
Issue
Section
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.
