A mathematical model to predict particleboard properties using the  GMDH-type neural network and genetic algorithm

Jahanilomer, Zahra; Farrokhpayam, Saeed Reza; Shamsian, Mohammad

doi:10.22092/ijwpr.2014.6130

Document Type : Research Paper

Authors

¹ M.Sc., Department of Wood and Paper Science &Technology, Faculty of Natural Resources, University of Zabol, Iran,

² Assistant Professor, Department of Wood and Paper science &Technology, Faculty of Natural Resources, University of Zabol, Iran

https://doi.org/10.22092/ijwpr.2014.6130

Abstract

Abstract

In this study, GMDH neural network based on genetic algorithm was used to predict the physical and mechanical properties of laboratory made particleboard. To predict the mechanical and physical properties of particleboard we used input parameters such as neural network including press closing time (10,20 and 30 seconds), moisture content of the mat (8,10,12 and 14%) and press temperature (150,160,170 and 180°C) as the input data and the output data was the physical and mechanical properties. The efficiency of these techniques was evaluated with statistical criteria of mean square error (MSE), root mean square error, (RMSE), mean absolute deviation (MAD) and the correlation coefficient (R²). Results showed that the value of MSE, RMSE and MAD for MOR, IB, TS_24h, TS_2h, WA_2hand WA_24h is low. Errors obtained for the MOE model were very high. According to the results obtained, this model is not the appropriate for prediction of MOE. R² values from the test and training set properties for MOR, IB, MOE, TS_24h, TS_2h, WA_2hand WA_24hwas more than 0.91%, which reflects that the performance of these models is better.

Keywords

Main Subjects

Composite wood products

References

-Avramidis, S. and Iliadis, L. 2005. Predicting wood thermal conductivity using artificial neural networks.Classification of wood species by neural network analysis of ultrasonic signals. Ultrasonic. 36: 219-222.

-Amanifard, N., Nariman-Zadeh, N., Borji, M., Khalkhali, A. and Habibdoust, A. 2007 Modelling and Pareto Optimization of Heat Transfer and Flow Coefficientsin Microchannels Using GMDH Type Neural Networks and Genetic Algorithms,Energy Conversion and Management. 49: 311-325.

-Atashkari, K., Nariman-Zadeh, N., Golcu, M., Khalkhali, A. and Jamali, A. 2007. Modelling and Multi-Objective optimization of a Va riable Valve-Timing Spark- Ignition Engine Using Polynomial Neural Networks and Evolutionary Algorithms, Energy Conversion and Management. 48( 3) 1029-1041.

-Asociación Eespañol De Normaliación (AENOR), 2001. Tableros derivados de la madera. Determinación del contenido de humedad. Standard UNE-EN 322. Madrid, España.

-Cook, DF., Whittaker, AD. 1992. Neural network models for prediction of process parameters in wood products manufacturing. In: Proceedings of the 1stindustrial engineering research conference. Chicago (IL), May, p. 209– 11.

-Cook, D.F., Ragsdale, C.T., Major R.L. 2000. Combining a neural network with a genetic algorithm for process parameter optimization. Eng Appl Artif Intell 13,391-396.

-Cook, D.E. and Chiu, C. C. 1997. Predicting the Internal Bond Strength of Particleboard, Utilizing a Radial Basis Function Neural Network. Engng Applic.Artif.lnteU. 10(2): 171-177.

-Drake, P.R. and Packianather, M.S. 1998. A decision treeof neural networks for classifying images of wood veneer. Int Journal Adv Manuf Technol, 14: 280-285.

-Esteban, L.G., Fernandez, F.G., Palacios, P., and Rodrigo, B.G. 2010. Use of ANN as a predictive method to determine moisture resistance of particle and fiber boards under cyclic testing conditions. (UNE-EN 321) Wood and Fiber Science, 42(3): 1-11.

-EN 317. 1993. Particleboard and Fiberboards. Determination of Swelling in Thickness after Immersion in Water. European Committee for Standardization, Brussels, Belgium.

-EN 319. 1993. Determination of Tensile Strength Perpendicular to the Plane of the Board. European Committee for Standardization, Brussels, Belgium.

-EN 310. 1993. Wood Based Panels. "Determination of Modulus of Elasticity in Bending and Bending Strength". European Committee for Standardization, Brussels, Belgium.

-Fernandez, G.F., Esteban L.G. DE., Palacios, P., Navarro, N. and Conde, M. 2008. Prediction of standard particleboard mechanical properties utilizing an artificial neural network and subsequent comparison with a multivariate regression model. Invest. Agrar.Sist. Rec. For. 17(2): 178-187.

-Fernandez, G.F., Esteban L.G. DE., Palacios, P. and Casasus GA. 2007. Use of an artificial neural network to differentiate the wood of Juniperus cedrusWebb & Bertel and Juniperus. canariensis Guyot. Pan-American IAWA Meeting 2007,San Luis Potosi, México, July 15-20.

-Hiassat, M., Abbod, M. and Mort, N. 2003. Using Genetic Programming to Improve the GMDH in Time Series Prediction, Statistical Data Mining and Knowledge Discovery, Edited by Hamparsum Bozdogan, Chapman and Hall CRC, PP. 257-268.

-Halligan, A.F., and Schniewind, A.P. 1974. Prediction of particleboard mechanical properties at various moisture contents.Wood Science Technology. 8(1): 68-78.

-Ivakhnenko, A.G. 1971. Polynomial Theory of Complex Systems. IEEE Transactions on Systems, Man, and Cybernetics. 364-378.

-Jordan, R., Afeeney, F., Nesbitt, N., Evertsen, J.A.1998. Classification of wood species by neural network, pp: 985.

-Krauss G, Kindangen JI, Depecker P. 1997. Using artificial neural networks to predict interior velocity coefficients. Build Environ. 32(4):295–303.

-Mier R ., Garcia J.L., Diez M.R., Fernandez-Golfin J.I. and Hermosoe E. 2005. Aplicacion de redes neuronales a la clasificacion visual de madera estructural. Comparación con otros métodos de clasificación. IV Congreso Forestal Espanol, 26-30.

-Nariman-zadeh, N., A. Darvizeh, M. and Gharababaei, H. 2002. Modelling of Explosive Cutting Process of Plates Using GMDHType Neural Network and Singular Value Decomposition Journal of Materials Processing Technology. 128 (1-3): 80- 87.

-Nirdosha, G. and Setunge, S. 2006. Formulation and process modeling of particleboard production using hardwood saw mill wastes using experimental design. Composite Structures. 75: 520–523.

-Suchsland, O., X. Hong. 1989. Model analysis of flakeboard variables. Forest Prod. J. 41(11/12):55-60.

-Yapici, F., Ozcifci, A., Akbulut, T. and Bayir, R. 2009. Determination of modulus of rupture and modulus of elasticity on flake board with fuzzy logic classifier. Mater. Des. 30: 2269-2273.

Iranian Journal of Wood and Paper Science Research

A mathematical model to predict particleboard properties using the GMDH-type neural network and genetic algorithm

References

References

Volume 29, Fall 3 - Serial Number 48
November 2014
Pages 376-389

A mathematical model to predict particleboard properties using the GMDH-type neural network and genetic algorithm

References

References

Volume 29, Fall 3 - Serial Number 48November 2014Pages 376-389

Volume 29, Fall 3 - Serial Number 48
November 2014
Pages 376-389