Prediction of Retention Level and Mechanical Strength of Plywood Treated With Fire Retardant Chemicals by Artificial Neural Networks

Yıl 2020, Cilt: 5 Sayı: 5, 785 - 792, 31.12.2020

Şükrü Özşahin , Aydın Demir , İsmail Aydın

https://doi.org/10.35229/jaes.825435

Öz

The treatment with fire retardant chemicals is the most effective process to protect wood and wood based products from fire is. Therefore, use of fire retardant chemicals has been increased. However, the fire retardant chemicals have an effect on other physical, mechanical and some technological properties of the materials treated with them. In this study, firstly, the retention level prediction model was developed with the artificial neural network (ANN) to examine the effects of wood species and concentration aqueous solution on the retention levels of veneers. Then, the effects of wood species, concentration aqueous solution and retention level on the mechanical properties of plywood were investigated with the mechanical strength prediction model developed with ANN. The prediction models with the best performance were determined by statistical and graphical comparisons. It has been observed that ANN models yielded very satisfactory results with acceptable deviations. As a result, the findings of this study could be employed effectively into the forest products industry to reduce time, energy and cost for empirical investigations.

Anahtar Kelimeler

Artiical Neural Network, Fire Retardant, Plywood, Concentration, Retention Level, Mechanical Properties

Yangın Geciktirici Kimyasallarla Emprenye Edilmiş Kontrplakların Retensiyon Miktarları ve Mekanik Dirençlerinin Yapay Sinir Ağları ile Tahmin Edilmesi

Öz

Yangın geciktirici kimyasallar ile emprenye işlemi, ahşap ve ahşap esaslı ürünlerin yangından korunmasında çok etkili bir işlemdir. Bu yüzden, yangın geciktirici kimyasalların kullanımı tüm dünyada artmaktadır. Ancak, yangın geciktirici kimyasallar, uygulanmış oldukları malzemelerin fiziksel, mekanik ve diğer bazı teknolojik özellikleri üzerinde bir etkiye neden olmaktadır. Bu çalışmada ilk olarak, ağaç türlerinin ve konsantrasyon miktarlarının kaplamaların retensiyon miktarları üzerindeki etkilerini incelemek için yapay sinir ağı (YSA) ile retensiyon miktarı tahmin modeli geliştirilmiştir. Daha sonra YSA ile geliştirilen mekanik direnç tahmin modeli ile ağaç türleri, konsantrasyon miktarları ve retesiyon miktarlarının kontrplağın mekanik özelliklerine etkileri araştırılmıştır. En iyi performansa sahip tahmin modelleri, istatistiksel ve grafiksel karşılaştırmalarla belirlenmiştir. YSA modellerinin kabul edilebilir sapmalarla oldukça tatmin edici sonuçlar verdiği görülmüştür. Sonuç olarak, bu çalışmanın bulguları, deneysel araştırmalar için zaman, enerji ve maliyeti azaltmak için orman ürünleri endüstrisinde etkin bir şekilde kullanılabilecektir.

Anahtar Kelimeler

Konsantrasyon, Kontrplak, Mekanik Özellikler, Yangın Geciktirici, Yapay Sinir Ağları, Retensiyon Miktarı

Kaynakça

• Aydin, I., (2004). Effects of Some Manufacturing Conditions on Wettability and Bonding of Veneers Obtained from Various Wood Species, PhD Thesis, KTU Natural Science Institute, Trabzon.
• Ceylan, I., (2008). Determination of Drying Characteristics of Timber by Using Artificial Neural Networks and Mathematical Models, Drying Technology, 26(12), 1469-1476.
• Cheng, R. X. & Wang, Q. W., (2011). The influence of FRW-1 fire retardant treatment on the bonding of plywood, Journal of Adhesion Science and Technology, 25, 1715–1724.
• Demir, A., Aydin, I. & Colak, S., (2016). Effect of various fire retardant chemicals in different concentrations on mechanical properties of plywood. In Proc. 2nd International Furniture Congress, Muğla, Turkey, 13-15 October, pp. 411.
• Demirkir, C., Özsahin, Ş., Aydin, I. & Colakoglu, G., (2013). Optimization of some panel manufacturing parameters for the best bonding strength of plywood, International Journal of Adhesion and Adhesives, 46, 14-20.
• EN 310, (1993). Wood based panels. Determination of modulus of elasticity in bending and of bending strength. European Standard.
• EN 314-1, (1998). Plywood–bonding quality–Part1: test methods, European Standard.
• Esteban, L.G., Fernandez, F.G. & Palacios, P., (2011). Prediction of plywood bonding quality using an artificial neural network, Holzforschung, 65(2), 209–214.
• Fateh, T., Rogaume, T., Luche, J., Richard, F. & Jabouille, F., (2013). Kinetic and mechanism of the thermal degradation of a plywood by using thermogravimetry and Fourier-transformed infrared spectroscopy analysis in nitrogen and air atmosphere, Fire Safety Journal, 58, 25 - 37.
• Fernández, F.G., Esteban, L.G., Palacios, P., Navarro, N. & Conde, M., (2008). Prediction of standard particleboard mechanical properties utilizing an artificial neural network and subsequent comparison with a multivariate regression model, Investigación agraria: Sistemas y recursos forestales, 17(2), 178–187.
• He, X., Li, X., Zhong, Z., Yan, Y., Mou, Q., Yao, C. & Wang, C., (2014). The fabrication and properties characterization of wood-based flame retardant composites, Journal of Nanomaterials, Article ID 878357, 6 pages.
• Ozkaya, K., Ilce, C. A., Burdurlu, E. & Aslan, S., (2007). The effect of potassium carbonate, borax and wolmanit on the burning characteristics of Oriented Strand Board(OSB), Construction and Building Materials, 1457 - 1462.
• Ozsahin, S. and Aydin, I., (2014). Prediction of the optimum veneer drying temperature for good bonding in plywood manufacturing by means of artificial neural network, Wood science and technology, 48(1), 59-70.
• Stevens, R., Es, D. S., Bezemer, R. & Kranenbarg, A. (2006). The structure-activity relationship of fire retardant phosphorus compounds in wood, Polymer Degradation and Stability, 91, 832 - 841.
• Yao, C. H., Wu, Y. Q. & Hu, Y. C., (2012). Flame-retardation characteristics and mechanisms of three inorganic magnesium compounds as fire-retardant for wood, Journal of Central South University of Forestry and Technology, 32(1), 18 - 23, 2012.