Lamine kaplama kereste (LVL) rutubetinin basınç direnci üzerine etkisinin yapay zekâ ile belirlenmesi

Abstract

Yapı sektöründe kullanılan ahşap malzemeler, kullanım yerine bağlı olarak farklı yükleme çeşitlerine ve farklı dirençlere maruz kalmaktadır. Yükleme türüne uygun materyal kullanımı güvenlik, performans ve maliyet gibi önemli faktörleri etkilemektedir. Yapı sektöründe kullanılan ahşap materyallerde diğer bir önemli husus, odun-su ilişkileridir. Rutubet, odunun fiziksel, mekanik ve teknolojik (sertlik, aşınma) özellikleri üzerinde önemli değişikliklere neden olmaktadır. Bu çalışmada, soyma işlemi ile elde edilen 2 mm kayın (Fagus orientalis L.) kaplamlardan 5 katmanlı LVL (Laminated Veneer Lumber) üretimi gerçekleştirilmiştir. Üretilen LVL’ler dört farklı nem (% 0, % 12, % 18 ve % 25) değerinde ve liflere dik ve parallel olmak üzere iki farklı yönde basınç direncine tabi tutulmuştur. Belirtilen rutubet değerlerinden elde edilen verilerden yararlanılarak yapay zeka ile diğer rutubet miktarlarındaki basınç direnci değerleri tahmin edilmiştir. Tahminlerde Yapay Sinir Ağları (YSA), Karar Ağaçları (KA) ve Rastgele Orman (RO) algoritmaları kullanılmıştır. Mekanik test sonuçlarına göre, en yüksek basınç direnci değeri rutubeti %0 (fırın kurusu) olan örneklerin liflere parallel yönde yapılan yüklemelerinde (51,96 N/mm²) elde edilmiştir. En düşük basınç direnci değeri (13,57 N/mm²) ise %25 rutubetli örneklerin liflere dik yönde yapılan yüklemelerinde saptanmıştır. En yüksek tahmin başarısı R2=0,984 değeri ile Rastgele Orman algoritmasından elde edilmiştir. Sonuç olarak, farklı rutubetlerde LVL'lerin basınç direncini tahmin etmek için yapay zeka tekniklerinin çözüm olarak başarılı bir şekilde kullanılabileceği belirlenmiştir.

Keywords

• LVL
• Basınç direnci
• Rutubet
• Yapay zekâ
• Karar ağaçları
• Rastgele orman

Determination of the effect of laminated veneer lumber (LVL) moisture content on pressure resistance by artificial ıntelligence

Abstract

Wooden materials used in the building sector are exposed to different loading types and different strength depending on the place of use. The use of materials suitable for the type of loading affects important factors such as safety, performance and cost. Another important issue in wooden materials used in the building sector is wood-water relations. Moisture causes significant changes on the physical, mechanical and technological (hardness, wear) properties of wood. In this study, 5-layer LVL (Laminated Veneer Lumber) was produced from 2 mm beech (Fagus orientalis L.) veneer obtained by peeling process. Produced LVLs were subjected to four different moisture (0%, 12%, 18% and 25%) compressio strength in two different directions, perpendicular and parallel to the fibers. Using the data obtained from the specified moisture values, the pressure resistance values in other moisture amounts were estimated by artificial intelligence. Artificial Neural Networks (ANN), Decision Trees (DT) and Random Forest (RF) algorithms are used in the predictions. According to the mechanical test results, the highest compression strength value (51.96 N/mm²) was obtained in the loading parallel to the fibers of the samples with 0% moisture (oven dry). The lowest compression strength value (13.57 N/mm²) was determined in the loading vertical direction to the fibers of 25% moisture samples. The highest prediction success was obtained from the Random Forest algorithm with a value of R2 = 0.984. As a result, it has been determined that artificial intelligence techniques can be used successfully as a solution to predict the pressure resistance of LVLs at different humidity.

Keywords

• LVL
• Compression strength
• Moisture
• Artificial intelligence
• Decision trees
• Random forest

References

1. Aydemir, D., Civi, B., Alsan, M., Can, A., Sivrikaya, H., Gunduz, G., Wang, A., 2016. Mechanical, morphological and thermal properties of nano-boron nitride treated wood materials. Maderas Ciencia y Tecnología, 18(1): 19-32.
2. Aydın, İ., Çolak, S., Çolakoğlu, G., Salih, E., 2004. A comparative study on some physical and mechanical properties of Laminated Veneer Lumber (LVL) produced from Beech (Fagus orientalis Lipsky) and Eucalyptus (Eucalyptus camaldulensis Dehn.) veneers. Holz als Roh-und Werkstoff, 62(3): 218-220.
3. Bardak, S., Tiryaki, S., Bardak, T., Aydin, A., 2016. Predictive performance of artificial neural network and multiple linear regression models in predicting adhesive bonding strength of wood. Strength of Materials, 48(6): 811-824.
4. Bardak, T., Sozen, E., Kayahan, K., Bardak, S. 2018. The impact of nanoparticles and moisture content on bonding strength of urea formaldehyde resin adhesive. Drvna Industrija, 69(3): 247-252.
5. Bou-Hamad, I., Jamali, I., 2020. Forecasting financial time-series using data mining models: A simulation study. Research in International Business and Finance, 51: 101072.
6. Çolak, S., Aydin, I., Demirkir, C., Çolakoğlu, G., 2004. Some technological properties of laminated veneer lumber manufactured from pine (Pinus sylvestris L.) veneers with melamine added-UF resins. Turkish Journal of Agriculture and Forestry, 28(2): 109-113.
7. De Groot, R.C., Gjovik, L.R., Crawford, D., Woodward, B., 1998. Field durability of CCA-and ACA-treated plywood composed of hardwood and softwood veneers. Forest Products Journal, 48: 76-82.
8. de Souza, F., Del Menezzi, C.H.S., Júnior, G.B., 2011. Material properties and nondestructive evaluation of laminated veneer lumber (LVL) made from Pinus oocarpa and P. kesiya. European Journal of Wood and Wood Products, 69(2): 183-192.

9. Ersen, N., 2021. Analysis of furniture products’ contribution to Turkey’s economy with a hybrid multi-criteria decision making method. BioResources, 16(1): 339-353.
10. Gholizadeh, M., Jamei, M., Ahmadianfar, I., Pourrajab, R., 2020. Prediction of nanofluids viscosity using random forest (RF) approach. Chemometrics and Intelligent Laboratory Systems, 201: 104010.
11. Gilbert, B.P., Bailleres, H., Zhang, H., McGavin, R.L., 2017. Strength modelling of laminated veneer lumber (LVL) beams. Construction and Building Materials, 149: 763-777.
12. Gomben, P.C., Gorman, T.M., 1994. Treatability of lodgepole pine laminated veneer lumber. Forest Products Journal, 44(2): 39.
13. Jiang, Z., Wang, H., Tian, G., Yu, Y., 2012. Sensitivity of several selected mechanical properties of moso bamboo to moisture content change under the fibre saturation point. BioResources, 7(4): 5048-5058.
14. Khoshaim, A.B., Elsheikh, A.H., Moustafa, E.B., Basha, M., Mosleh, A.O., 2021. Prediction of residual stresses in turning of pure iron using artificial intelligence-based methods. Journal of Materials Research and Technology, 11: 2181-2194
15. Kim, S., Pan, S., Mase, H., 2019. Artificial neural network-based storm surge forecast model: Practical application to Sakai Minato, Japan. Applied Ocean Research, 91: 101871.
16. Kurt, R., Meriç, H., Aslan, K., Çil, M., 2012. Laminated veneer lumber (LVL) manufacturing using three hybrid poplar clones. Turkish Journal of Agriculture and Forestry, 36(2): 237-245.
17. Kurt, R., Karayilmazlar, S., Imren, E., Çabuk, Y. 2017. Yapay sinir ağları ile öngörü modellemesi: Türkiye kağıt-karton sanayi örneği. Bartın Orman Fakültesi Dergisi, 19(2): 99-106.
18. Kurt, R., Karayilmazlar, S., 2019. Estimating modulus of elasticity (MOE) of particleboards using artificial neural networks to reduce quality measurements and costs. Drvna industrija, 70(3): 257-263.
19. Nzokou, P., Zyskowski, J., Boury, S., Kamdem, D.P., 2005. Natural decay resistance of LVL made of veneers from durable and non-durable wood species. Holz als Roh-und Werkstoff, 63(3): 173-178.
20. Örs, Y., Keskin, H., 2008. Ağaç Malzeme Teknolojisi. Gazi Kitabevi, Ankara.
21. Pambou Nziengui, C.F., Ikogou, S., Moutou Pitti, R., 2018. Impact of cyclic compressive loading and moisture content on the mechanical behavior of Aucoumea Klaineana Pierre. Wood Material Science & Engineering, 13(4): 190-196.
22. Pereira, P.J., Cortez, P., Mendes, R., 2021. Multi-objective grammatical evolution of decision trees for mobile marketing user conversion prediction. Expert Systems with Applications, 168: 114287.
23. Roos, K., Edwardson, C., Adams, R., 1993. Manufacture of laminated veneer lumber from preservative treated veneers. IUFRO—symposium: protection of wood based composite products, 17-19 May, Orlando, Florida, pp: 69–78.
24. Sivrikaya, H., Can, A., de Troya, T., Conde, M., 2015. Comparative biological resistance of differently thermal modified wood species against decay fungi, Reticulitermes grassei and Hylotrupes bajulus. Maderas. Ciencia y tecnología, 17(3): 559-570.
25. Sözen, E., Bardak, T., Aydemir, D., Bardak, S., 2018. Yapay sinir ağları ve derin öğrenme algoritmaları kullanarak nanokompozitlerde deformasyonun tahmin edilmesi. Bartın Orman Fakültesi Dergisi, 20(2): 223-231.
26. Stark, N.M., Cai, Z., Carll, C., 2010. Wood-based composite materials panel products, glued-laminated timber, structural composite lumber, and wood-nonwood composite materials. In: Wood Handbook, Wood as an Engineering Material (Ed: Ross, R.J.), Centennial Edition, Madison, Wisconsin, pp:1-28
27. Tiryaki, S., Bardak, S., Bardak, T., 2015. Experimental investigation and prediction of bonding strength of Oriental beech (Fagus orientalis Lipsky) bonded with polyvinyl acetate adhesive. Journal of Adhesion Science and Technology, 29(23): 2521-2536. TS 2471, 1976. Odunda fiziksel ve mekaniksel deneyler için rutubet miktarı tayini. TSE, Ankara.
28. TS 2472, 1976. Odunda Fiziksel ve mekaniksel deneyler için birim hacim ağırlığı tayini. TSE, Ankara.
29. TS 2473, 1976. Odunun liflere dik doğrultuda basınçda denenmesi. TSE, Ankara.
30. TS 2595, 1977. Odunun liflere paralel doğrultuda basınç dayanımı tayini. TSE, Ankara.
31. Wadie, B.S., Badawi, A.M., Abdelwahed, M., Elemabay, S.M., 2006. Application of artificial neural network in prediction of bladder outlet obstruction: A model based on objective, noninvasive parameters. Urology, 68(6): 1211-1214.
32. Wang, H., Li, W., Ren, D., Yu, Z., Yu, Y., 2014. A two-variable model for predicting the effects of moisture content and density on compressive strength parallel to the grain for moso bamboo. Journal of Wood Science, 60(5): 362-366.