An artificial neural network model for predicting modulus of elasticity and modulus of rupture of particleboard comparison with a multiple linear regression model

Document Type : Research Paper

Authors

1 Department of wood and paper science,-Faculty of natural resource - University of zabol

2 Faculty of Agriculture and Natural Resources, University of Mohaghegh Ardabili

3 Department of Wood and Paper Science and Technology, Faculty of Natural Resources, College of Agriculture & Natural Resources, University of Tehran, Karaj, I.R. Iran

Abstract

Today, several modeling methods have been used to cost-efficiently predict the physical and mechanical properties of wood-based panel products which in turn reduce the cost of quality control of these products. Two common methods include regression and artificial neural network (ANN). In this study, the possibility of predicting the modulus of rupture (MOR) and modulus of elasticity (MOE) of particleboard by simple and multiple linear regression and ANN based on structural parameters including density in three levels (0.65, 0.7, and 0.75 g/cm3), slenderness ratio of particles in three levels (47, 30, and 13) adhesive percent in three level of (8, 9.5, and 11%) were evaluated. experimental and predicted data were compared with different criteria including mean absolute percentage error (MAPE), mean squared error (MSE) and coefficient of determination (R2). The results revealed that although both multiple linear regression models and artificial neural network were able to predict MOR and MOE values with acceptable accuracy, but ANN model predicted them with higher R2 and lower MAPE than multiple linear regression model. The value of MAPE and R2, for prediction of MOR and MOE by ANN model were 7.72% and 0.77, and 7% and 0.86, respectively. the corresponding value for multiple regression model were 8.3% and 0.738, and 9.06% and 0.783, respectively. These levels of error are industrially and practically satisfactory for the prediction of properties in particleboard.

Keywords

References

[1]  Doosthosei, K., 2001. Wood Composite Materials Manufacturing, Applications. Tehran university press, 648 p.
[2]  Godwald, J., Barbu, M.C., Petutschnigg, A., Krišťák, Ľ., and Tudor, E.M., 2021. Oversized Planer Shavings for the Core Layer of Lightweight Particleboard. Polymers, 13(7), p.1125.
[3]  Laskowska, A., and Mamiński, M., 2020. The properties of particles produced from waste plywood by shredding in a single-shaft shredder. Maderas. Ciencia y tecnología, 22(2), 197-204.
[4] Ferrandez-Villena, M., Ferrandez-Garcia, C. E., Garcia-Ortuño, T., Ferrandez-Garcia, A., and Ferrandez-Garcia, M. T., 2020. The influence of processing and particle size on binderless particleboards made from Arundo donax L. rhizome. Polymers, 12(3), 696.
[5]  Arabi, M., Faezipour, M. and Gholizadeh, H., 2011 Reducing resin content and board density without adversely affecting the mechanical properties of particleboard through controlling particle size. Journal of Forestry Research, 22 (4), 659-664.
[6] Arabi, M., Faezipour, M., Layeghi, M. and Enayati, A.A., 2011 Interaction analysis between slenderness ratio and resin content on mechanical properties of particleboard. Journal of forestry research, 22 (3), 461-464.
[7] Ahmed, S.A., Adamopoulos, S., Li, J., and Kovacikova, J., 2020. Prediction of mechanical performance of acetylated MDF at different humid conditions. Applied Sciences, 10(23), p.8712.
[8] Ismail, F.S., Bakar, N.A., and Alam, S., 2013. Multi-output hybrid GA-NN with adaptive mechanism. In Proceedings of the 2013 International Conference on Applied Mathematics and Computational Methods.pp. 232-237.
[9] Jahanilomer, Z., Farrokhpayam, S.R., and Shamsian, M., 2014. A mathematical model to predict particleboard properties using the GMDH-type neural network and genetic algorithm. Iranian Journal of Wood and Paper Science Research, 29(3), 376-389.
[10] Valarmathi, T.N., Palanikumar, K., Sekar, S., and Latha, B., 2020. Investigation of the effect of process parameters on surface roughness in drilling of particleboard composite panels using adaptive neuro fuzzy inference system. Materials and Manufacturing Processes, 35(4).469-477.
[11]  Eslah, F., Enayati, A.A., Tajvidi, M., and Faezipour, M.M., 2012. Regression models for the prediction of poplar particleboard properties based on urea formaldehyde resin content and board density.14(6).1321-1329.
[12]  Fernández, F. G., de Palacios, P., Esteban, L. G., Garcia-Iruela, A., Rodrigo, B. G., and Menasalvas, E., 2012. Prediction of MOR and MOE of structural plywood board using an artificial neural network and comparison with a multivariate regression model. Composites Part B: Engineering, 43(8), 3528-3533.
[13] Tiryaki, S., and Aydın, A., 2014. An artificial neural network model for predicting compression strength of heat treated woods and comparison with a multiple linear regression model. Construction and Building Materials, 62, 102-108.
[14]  Hagan MT,. 1995.Neural network design , PWS , USA;
[15] Anderson, J.A., 1995. An introduction to neural networks. MIT press.
[16] Melo, R. R. D., and Miguel, E. P., 2016. Use of artificial neural networks in predicting particleboard quality parameters. Revista Árvore, 40(5), 949-958.
[17]  Tiryaki, S., Aras, U., Kalaycıoğlu, H., Erişir, E., and Aydın, A., 2017. Predictive models for modulus of rupture and modulus of elasticity of particleboard manufactured in different pressing conditions. High Temperature Materials and Processes, 36(6), 623-634.
[18] Bardak, S., Tiryaki, S., Nemli, G., and Aydın, A., 2016. Investigation and neural network prediction of wood bonding quality based on pressing conditions. International Journal of Adhesion and Adhesives, 68, 115-123. 
[19] Kaya, A. İ., llkucar, M., and Çifci, A., 2019. Use of Radial Basis Function Neural Network in Estimating Wood Composite Materials According to Mechanical and Physical Properties. Erzincan Üniversitesi Fen Bilimleri Enstitüsü Dergisi, 12(1), 116-123.
[20]  Palacios, P., Fernández, F. G., García-Iruela, A., González-Rodrigo, B., and Esteban, L. G., 2018. Study of the influence of the physical properties of particleboard type P2 on the internal bond of panels using artificial neural networks. Computers and electronics in agriculture, 155, 142-149.
[21] Nazerian, M., Kamyabb, M., Shamsianb, M., Dahmardehb, M., and Kooshaa, M.,2018. Comparison of response surface methodology (RSM) and artificial neural networks (ANN) towards efficient optimization of flexural properties of gypsum-bonded fiberboards. Cerne, 24(1), 35-47.
[22]  Nazerian, M., Razavi, S. A., Partovinia, A., Vatankhah, E., and Razmpour, Z.,2020. Prediction of the Bending Strength of a Laminated Veneer Lumber (LVL) Using an Artificial Neural Network. Mechanics of Composite Materials, 56(5), 649-664.
[23]  Lewis, C. D., 1982: Industrial and business forecasting methods. Butterworths Publishing, London.
[24]  Kurt, R., and Karayilmazlar, S., 2019. Estimating Modulus of Elasticity (MOE) of Particleboards Using Artificial Neural Networks to Reduce Quality Measurements and Costs. Drvna industrija: Znanstveni časopis za pitanja drvne tehnologije, 70(3), pp.257-263.
Iranian Journal of Wood and Paper Industries
Volume 12, Issue 2
September 2021
Pages 283-297

Files

Share

How to cite

Statistics