Prediction of the optimum veneer drying temperature for good bonding in plywood manufacturing by means of artificial neural network

Veneer drying is one of the most important stages in the manufacturing of veneer-based composites such as plywood and laminated veneer lumber. Due to the high drying costs, increased temperatures are being used commonly in plywood industry to reduce the overall drying time and increase capacity. However, high drying temperatures can alter some physical, mechanical and chemical characteristics of wood and cause some drying-related defects. In this study, it was attempted to predict the optimum drying temperature for beech and spruce veneers via artificial neural network modeling for optimum bonding. Therefore, bonding shear strength values of plywood panels manufactured from beech and spruce veneers dried at temperatures of 20, 110, 150 and 180 °C were obtained experimentally. Then, the intermediate bond strength values based on veneer drying temperatures were predicted by artificial neural network modeling, and the values not measured experimentally were evaluated. The optimum drying temperature values that yielded the highest bonding strength were obtained as 169 °C for urea formaldehyde and 125 °C for phenol formaldehyde adhesive in beech plywood panels, while 162 °C for urea formaldehyde and 151 °C for phenol formaldehyde in spruce plywood panels.

[1]  Sun Liping,et al.  Modeling of temperature-humidity for wood drying based on time-delay neural network , 2006 .

[2]  Michael Sylvester Packianather,et al.  Modelling neural network performance through response surface methodology for classifying wood veneer defects , 2004 .

[3]  J. F. Lutz.  Wood Veneer: Log Selection, Cutting, and Drying , 1978 .

[4]  Yong Haur Tay,et al.  Computer Vision-based Wood Recognition System , 2007 .

[5]  T. Theppaya,et al.  Optimization of Rubber Wood Drying by Response Surface Method and Multiple Contour Plots , 2004 .

[6]  R. Rice.  Mass transfer, creep and stress development during the drying of red oak , 1988 .

[7]  I. Aydin,et al.  Variations in Bending Strength and Modulus of Elasticity of Spruce and Alder Plywood after Steaming and High Temperature Drying , 2008 .

[8]  Şükrü Özşahin,et al.  THE USE OF AN ARTIFICIAL NEURAL NETWORK FOR MODELING THE MOISTURE ABSORPTION AND THICKNESS SWELLING OF ORIENTED STRAND BOARD , 2012 .

[9]  A. W. Christiansen.  HOW OVERDRYING WOOD REDUCES ITS BONDING TO REVIEW OF THE LITERATURE. PART I. PHYSICAL RESPONSES , 1990 .

[10]  A. Christiansen.  How overdrying wood reduces its bonding to phenol-formaldehyde adhesives : a critical review of the literature. Part II, Chemical reactions , 1990 .

[11]  Lazaros S. Iliadis,et al.  Wood-water sorption isotherm prediction with artificial neural networks: A preliminary study , 2005 .

[12]  Sandhya Samarasinghe,et al.  Neural Networks for predicting fracture toughness of individual wood samples , 2007 .

[13]  Lazaros S. Iliadis,et al.  Neural network prediction of bending strength and stiffness in western hemlock (Tsuga heterophylla Raf.) , 2007 .

[14]  Kuo-Cheng Shen.  THE EFFECTS OF DRYER TEMPERATURE, SAPWOOD AND HEARTWOOD, AND TIME ELAPSING BETWEEN DRYING AND GLUING ON THE GLUING PROPERTIES OF ENGELMANN SPRUCE VENEER , 1958 .

[15]  Jun Cao,et al.  ANN-based data fusion for lumber moisture content sensors , 2006 .

[16]  I. Aydin,et al.  Formaldehyde Emission, Surface Roughness, and Some Properties of Plywood as Function of Veneer Drying Temperature , 2005 .

[17]  Luis García Esteban,et al.  Prediction of plywood bonding quality using an artificial neural network , 2011 .

[18]  Liping Sun,et al.  Modeling of temperature-humidity for wood drying based on time-delay neural network , 2006, Journal of Forestry Research.

[19]  Luis García Esteban,et al.  Artificial Neural Networks in Wood Identification: The Case of two Juniperus Species from the Canary Islands , 2009 .

[20]  L. García Esteban,et al.  Prediction of standard particleboard mechanical properties utilizing an artificial neural network and subsequent comparison with a multivariate regression model , 2008 .

[21]  Robert W. Rice,et al.  Detection of Structural Damage in Medium Density Fiberboard Panels using Neural Network Method , 2008 .

[22]  M. Šernek.  Comparative analysis of inactivated wood surfaces : dissertation submitted to the Faculty of Virginia Polytechnic Institute and State University in partial fulfillment of the requirements for the degree of Doctor of Philosophy in Wood Science and Forest Products , 2002 .

[23]  Deborah F. Cook,et al.  Predicting the internal bond strength of particleboard, utilizing a radial basis function neural network , 1997 .

[24]  Marzuki Khalid,et al.  DESIGN OF AN INTELLIGENT WOOD SPECIES RECOGNITION SYSTEM , 2008 .

[25]  Michael Sylvester Packianather,et al.  A decision tree of neural networks for classifying images of wood veneer , 1998 .

[26]  Hongwei Wu,et al.  Prediction of Timber Kiln Drying Rates by Neural Networks , 2006 .

[27]  J. C. F. Walker,et al.  Primary Wood Processing , 1993, Springer Netherlands.

[28]  Marco Castellani,et al.  Evolutionary feature selection applied to artificial neural networks for wood-veneer classification , 2008 .

[29]  Cliff T. Ragsdale,et al.  Combining a neural network with a genetic algorithm for process parameter optimization , 2000 .

[30]  H. Nagao,et al.  A preliminary investigation on evaluation of strength of soft wood timbers by neural network , 1996 .

[31]  R. Fisher.  Unasylva—An International Journal of Forestry and Forest Industries 1947–2000 , 2003 .

[32]  I. Ceylan.  Determination of Drying Characteristics of Timber by Using Artificial Neural Networks and Mathematical Models , 2008 .