Home A study on the GA-BP neural network model for surface roughness of basswood-veneered medium-density fiberboard
Article
Licensed
Unlicensed Requires Authentication

A study on the GA-BP neural network model for surface roughness of basswood-veneered medium-density fiberboard

  • Xizhi Wu , Han Niu , Xian-Jun Li EMAIL logo and Yiqiang Wu
Published/Copyright: February 24, 2020
Become an author with De Gruyter Brill
Submit Manuscript Author Information
Holzforschung
From the journal Holzforschung Volume 74 Issue 10

Abstract

Roughness is an important property of wood surface and has a significant influence on the interface bonding strength and surface coating quality. However, there are no theoretical models for basswood-veneered medium-density fiberboard (MDF) by fine sanding from existing research work. In this paper, the basswood-veneered MDF was fine sanded with an air drum. Orthogonal experiment was implemented to study the effects of abrasive granularity, feed rate, belt speed, air drum deformation and air drum pressure on the surface roughness of basswood-veneered MDF. The simulation models of the parallel-grain roughness and the vertical-grain roughness of the sanded surface were conducted based on the BP (error back propagation) neural network, which was optimized by a genetic algorithm (GA) (GA-BP neural network), and these models were verified by extensive experimental data. The results showed that the influence of sanding parameters on parallel-grain roughness was similar to that on vertical-grain roughness. The order of influence was that: abrasive granularity > belt speed > feed speed > air drum deformation and air drum pressure. Based on the work, the parallel-grain roughness and vertical-grain roughness of basswood-veneered MDF could be well predicted by the GA-BP neural network. The average relative errors on parallel-grain roughness and vertical-grain roughness were 3.4% and 1.9%, respectively.

Keywords: BP neural network; genetic algorithm; medium-density fiberboard; sanding; surface roughness

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

  2. Research funding: The project is supported by the National Natural Science Foundation of China (grant no. U1737112, Funder Id: http://dx.doi.org/10.13039/501100001809) and Chinese Postdoctoral Station of Yihua Life Science and Technology Co., Ltd. (no. 201141).

  3. Employment or leadership: None declared.

  4. Honorarium: None declared.

References

Alves, M.C.S., Santiago, L.F.F., Gonçalves, M.T.T., Valarelli, I.D., Varasquim, F.M.F.D.A. (2015) Effects of belt speed, pressure and grit size on the sanding of Pinus elliottii wood. CERNE 21:45–50.10.1590/01047760201521011216Search in Google Scholar

Bao, X., Ying, J.H., Cheng, F., Zhang, J., Luo, B., Li, L., Liu, H.G. (2018) Research on neural network model of surface roughness in belt sanding process for Pinus koraiensis. Measurement 115:11–18.10.1016/j.measurement.2017.10.013Search in Google Scholar

Chandrasekaran, M., Devarasiddappa, D. (2014) Artificial neural network modeling for surface roughness prediction in cylindrical grinding of Al-SiCp metal matrix composites and ANOVA analysis. Adv. Prod. Eng. Manag. 9:59–70.10.14743/apem2014.2.176Search in Google Scholar

Cui, X., Guo, J., Zheng, J. (2016) Optimization of geometry parameters for ceramic cutting tools in intermittent turning of hardened steel. Mater. Design 92:424–437.10.1016/j.matdes.2015.12.089Search in Google Scholar

Hazir, E., Koc, K.H. (2018) A modeling study to evaluate the quality of wood surface. Maderas Cienc. Tecnol. 20:691–702.10.4067/S0718-221X2018005041501Search in Google Scholar

Hiziroglu, S., Salca, E.A. (2012) Analysis of surface roughness of black alder as function of various processing parameters. Pro Ligno 8:68–79.Search in Google Scholar

Li, X.-X., Chen, Y.-G., Li, L. (2010) Abrasive belt sanding technology of wood-based panel. Wood Process. Machinery 3:44–48.Search in Google Scholar

Luo, B. Study on Sanding Force and Optimal Sanding Parameters in the Belt Sanding Process of Wood Materials. Beijing Forestry University, Beijing, China, 2015.Search in Google Scholar

Luo, B., Li, L., Liu, H., Xu, M., Xing, F. (2014a) Analysis of sanding parameters, sanding force, normal force, power consumption, and surface roughness in sanding wood-based panels. BioResources 9:7494–7503.10.15376/biores.9.4.7494-7503Search in Google Scholar

Luo, B., Li, L., Xu, M., Liu, H., Xing, F. (2014b) Analysis of static friction coefficient between work-piece and rubber belt in sanding wood-based panel. BioResources 9:7372–7381.10.15376/biores.9.4.7372-7381Search in Google Scholar

Miao, T., Li, L. (2014) Study on influencing factors of sanding efficiency of abrasive belts in wood materials sanding. Wood Res. 59:835–842.Search in Google Scholar

Richter, K., Feist, W.C., Knabe, M.T. (1995) The effect of surface roughness on the performance of finishes. Part 1. Roughness characterization and stain performance. For. Prod. J. 45:91–97.Search in Google Scholar

Saloni, D.E., Lemaster, R.L., Jackson, S.D. (2005) Abrasive machining process characterization on material removal rate, final surface texture, and power consumption for wood. For. Prod. J. 55:35–41.Search in Google Scholar

Shi, M.-M., Lei, Y.-F., Xiao, J.-P., Liu, B. (2015) Abrasive belt grinding quality of several solid wood and wood-based board. Wood Process. Machinery 3:41–45.Search in Google Scholar

Sofuoglu, SD. (2015) Using artificial neural networks to model the surface roughness of massive wooden edge-glued panels made of Scotch pine (Pinus sylvestris L.) in a machining process with computer numerical control. Bioresources 10:6797–6808.10.15376/biores.10.4.6797-6808Search in Google Scholar

Song, Z.L., Guo, G.X. (2003) Analysis of factors affecting surface roughness of medium density fiberboard. China Wood-Based Panels 2:12–14.Search in Google Scholar

Varasquim, F.M.F.D.A., Alves, M.C.D.S., Gonçalves, M.T.T., Santiago, L.F.F., Souza, A.J.D.D. (2012) Influence of belt speed, grit sizes and pressure on the sanding of eucalyptus grandis wood. Cerne 18:231–237.10.1590/S0104-77602012000200007Search in Google Scholar

Wang, B.J., Dai, C., Ellis, S. Effect of veneer surface roughness and compressibility on plywood/LVL performance. International Symposium on Veneer Processing, Shanghai, 2007.Search in Google Scholar

Supplementary Material

The online version of this article offers supplementary material (https://doi.org/10.1515/hf-2019-0248).

Received: 2019-10-09
Accepted: 2020-01-21
Published Online: 2020-02-24
Published in Print: 2020-10-25

©2020 Walter de Gruyter GmbH, Berlin/Boston

Articles in the same Issue

  1. Frontmatter
  2. Original articles
  3. Axial variation in the cambium anatomy of Schizolobium parahyba var. amazonicum
  4. Effect of growth stress and interlocked grain on splitting of seven different hybrid clones of Eucalyptus grandis×Eucalyptus urophylla wood
  5. Dynamic parallel-to-grain compressive properties of three softwoods under seismic strain rates: tests and constitutive modeling
  6. European beech log and lumber grading in wet and dry conditions using longitudinal vibration
  7. Influence of chemical pretreatments on plant fiber cell wall and their implications on the appearance of fiber dislocations
  8. Enhancing the thermal stability, water repellency, and flame retardancy of wood treated with succinic anhydride and melamine-urea-formaldehyde resins
  9. Improvement of interfacial interaction in impregnated wood via grafting methyl methacrylate onto wood cell walls
  10. A study on the GA-BP neural network model for surface roughness of basswood-veneered medium-density fiberboard
  11. Characterisation and valorisation of the bark of Myrcia eximia DC. trees from the Amazon rainforest as a source of phenolic compounds
https://doi.org/10.1515/hf-2019-0248
Keywords for this article
BP neural network; genetic algorithm; medium-density fiberboard; sanding; surface roughness

Articles in the same Issue

  1. Frontmatter
  2. Original articles
  3. Axial variation in the cambium anatomy of Schizolobium parahyba var. amazonicum
  4. Effect of growth stress and interlocked grain on splitting of seven different hybrid clones of Eucalyptus grandis×Eucalyptus urophylla wood
  5. Dynamic parallel-to-grain compressive properties of three softwoods under seismic strain rates: tests and constitutive modeling
  6. European beech log and lumber grading in wet and dry conditions using longitudinal vibration
  7. Influence of chemical pretreatments on plant fiber cell wall and their implications on the appearance of fiber dislocations
  8. Enhancing the thermal stability, water repellency, and flame retardancy of wood treated with succinic anhydride and melamine-urea-formaldehyde resins
  9. Improvement of interfacial interaction in impregnated wood via grafting methyl methacrylate onto wood cell walls
  10. A study on the GA-BP neural network model for surface roughness of basswood-veneered medium-density fiberboard
  11. Characterisation and valorisation of the bark of Myrcia eximia DC. trees from the Amazon rainforest as a source of phenolic compounds
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 29.9.2025 from https://www.degruyterbrill.com/document/doi/10.1515/hf-2019-0248/html
Scroll to top button