Home Prediction of plywood bonding quality using an artificial neural network
Article
Licensed
Unlicensed Requires Authentication

Prediction of plywood bonding quality using an artificial neural network

  • Luis García Esteban EMAIL logo , Francisco García Fernández and Paloma de Palacios
Published/Copyright: October 15, 2010
Become an author with De Gruyter Brill
Holzforschung
From the journal Volume 65 Issue 2

Abstract

The bonding quality test is one of the most important of all tests performed on plywood, because it determines the suitability of boards for use in the type of exposure they are intended for. Because this test involves aging pretreatment, results are not available in <24–97 h after manufacture, depending on the type of board, and therefore any error in the manufacturing process is not detected until 1–4 days later. To solve this time problem, an artificial neural network was developed as a predictive method to determine the suitability of board bonding through other properties that can be determined in less testing time: thickness, moisture content, density, bending strength, and modulus of elasticity. The network designed WAS a feedforward multilayer perceptron trained by supervised learning after normalization of the input data, and allowed the bonding test result to be predicted with 93% accuracy.


Corresponding author. Universidad Politécnica de Madrid, Escuela Técnica Superior de Ingenieros de Montes, Departamento de Ingeniería Forestal, Ciudad Universitaria s/n, 28040 Madrid, Spain Phone: +34-91-3367121 Fax: +34-91-3367126

Received: 2010-5-20
Accepted: 2010-7-30
Published Online: 2010-10-15
Published Online: 2010-10-15
Published in Print: 2011-03-01

©2011 by Walter de Gruyter Berlin New York

Articles in the same Issue

  1. Editorial
  2. Note from the Editor-in-Chief
  3. Original papers
  4. Delineating pMDI model reactions with loblolly pine via solution-state NMR spectroscopy. Part 1. Catalyzed reactions with wood models and wood polymers
  5. Delineating pMDI model reactions with loblolly pine via solution-state NMR spectroscopy. Part 2. Non-catalyzed reactions with the wood cell wall
  6. Effect of periodate on lignin for wood adhesive application
  7. Spherical PF resin beads prepared from phenol-liquefied Bambusa dolichoclada with suspension polymerization
  8. Novel paper sizing agents based on renewables. Part 4: Application properties in comparison to conventional ASA sizes
  9. Organosolv pretreatment of olive tree biomass for fermentable sugars
  10. NIR-based prediction of extractives in American white oak heartwood
  11. Synthesis and herbicidal activity of 5-dehydroabietyl-1,3,4-oxadiazole derivatives
  12. Quantification of polypropylene (PP) in wood plastic composites (WPCs) by analytical pyrolysis (Py) and differential scanning calorimetry (DSC)
  13. Prediction of plywood bonding quality using an artificial neural network
  14. Photostability and moisture uptake properties of wood veneers coated with a combination of thin sol-gel films and light stabilizers
  15. Thermal degradation of bending properties of structural wood and wood-based composites
  16. Modelling time-dependent mechanical behaviour of softwood using deformation kinetics
  17. Viscoelastic properties of woody hemp core
  18. Scale effect in the anisotropic deformation change of tracheid cells during water adsorption
  19. Phylogenetic analysis of major molds inhabiting woods and their discoloration characteristics. Part 1. Genus Trichoderma
  20. Phylogenetic analysis of major molds inhabiting woods and their discoloration characteristics. Part 2. Genus Penicillium
  21. Fungi associated with bamboo and their decay capabilities
  22. Antifungal activities of three supercritical fluid extracted cedar oils
  23. Short Note
  24. Influence of wood specimen thickness on its mechanical properties by tensile testing: solid wood versus veneer
  25. Meetings
  26. Meetings
Downloaded on 1.10.2025 from https://www.degruyterbrill.com/document/doi/10.1515/hf.2011.003/html?lang=en
Scroll to top button