Isıl işlem uygulanmış sarıçam odununun bazı fiziksel ve mekanik özelliklerinin yapay sinir ağı kullanılarak modellenmesi

Abstract

Bu çalışmada, mobilya endüstrisinde yoğun olarak kullanılmakta olan sarıçam odununun (Pinus sylvestris) ısıl işlem sonrası bazı fiziksel ve mekanik özellikleri test edilmiş, elde edilen bulgular yapay sinir ağı (YSA) ile modellenerek sıcaklık ve süre varyasyonlarına ilişkin ara değerler tahmin edilmeye çalışılmıştır. Ara değerlere ulaşmayı kolaylaştıran bu çalışma, mobilya tasarım/üretim aşamalarında ilgili araştırmacıları, akla gelen tüm ısıl parametrelerini deneme yükünden kurtarmayı hedeflemektedir. Çalışmada, sarıçam odunu örnekleri, 2, 4 ve 6 saat süreyle 150, 160, 170, 180, 190 ve 200 °C sıcaklıkta, normal atmosfer ortamında ısıl işleme tabi tutulmuştur. Ardından ısıl işlem uygulanmış örneklerdeki renk değişiklikleri, ağırlık kayıpları ve liflere paralel basınç direnci değerleri belirlenmiştir. Deneysel çalışmanın ardından, yapay sinir ağı ile iki farklı öğrenme algoritması -Levenberg-Marquardt (LM) ve Scaled Conjugate Gradient (SCG) algoritması ve 15 farklı gizli nöron kullanılarak modelleme işlemi gerçekleştirilmiştir. En iyi model LM öğrenme algoritması kullanan 2-7-6 yapısında elde edilmiştir. En iyi modelin ortalama mutlak yüzde hatası (MAPE); tahmin edilen renk parametreleri için %8,0’in altında bulunmuştur. Ağırlık kaybı ve liflere paralel basınç direnci MAPE değerleri sırasıyla %5,79 ve %1,50 olarak bulunmuştur. Sonuç olarak, YSA’nın, ısıl işlem görmüş odun numunelerinin çalışılan bütün parametrelerini tahmin etmede başarıyla kullanılabileceği sonucuna varılmıştır.

Keywords

• Isıl işlem
• Modelleme
• Sarıçam
• Yapay sinir ağları

Modelling some physical and mechanical properties of heat-treated Scotch pine using artificial neural network

Abstract

In this study, some physical and mechanical properties of yellow pine wood (Pinus sylvestris), which is used extensively in furniture industry, were tested after heat treatment. The findings obtained were modelled by artificial neural network (ANN) and interval values related to temperature and time variations were tried to be estimated. This study, which makes it easier to reach intermediate values, aims to save the relevant researchers from trial load all of the heating parameters during the furniture design/production stages. In the study scotch pine samples were heat-treated at 150, 160, 170, 180, 190 and 200 °C for 2, 4 and 6 hours, under normal atmosphere conditions. Color changes, weight losses and compression strength parallel to grain values of heat-treated samples were determined. After experimental study, modelling procedure was performed by ANN using two different learning algorithm- Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) algorithm- 15 different hidden neurons. The best model was obtained from 2-7-6 structure using LM learning algorithm. Mean absolute percentage error (MAPE) of the best model was found below 8.0% for estimated color parameters. The weight loss and compression strength parallel to grain were 5.79% and 1.50%, respectively. It was concluded that ANN can be used successfully to predict all studied parameters of heat-treated wood samples.

Keywords

• Heat-treatment
• Modelling
• Scotch pine
• Artificial Neural Network

References

1. Adeli, H., 2001. Neural networks in civil engineering: 1989–2000. Computer‐Aided Civil and Infrastructure Engineering, 16(2): 126-142.
2. Akkılıç, H., Kaymakcı, A., Ünsal, Ö., 2014. Isıl işlem uygulanmış ahşap malzemenin dış cephe kaplaması olarak değerlendirilme potansiyeli, 7. Ulusal Çatı & Cephe Sempozyumu, 3-4 Nisan, İstanbul s. 1-9.
3. ASTM-D-1666-87, 1994. Standard Test Methods for Conducting Machining Tests of Wood and Wood-Base Materials. Annual Book of ASTM Standards, Philadelphia, USA.
4. Aydemir, D., Gündüz, G., 2009. The effect of heat treatment on physical, chemical, mechanical and biological properties of wood. Journal of Bartın Faculty of Forestry, 11(15): 71-81.
5. Boonstra, M.J., Tjeerdsma, B., 2006. Chemical analysis of heat treated softwoods. Holz als Roh-und Werkstoff, 64(3): 204-211.
6. Brito, J.O., Dias Júnior, A.F., Lana, A.Q., Andrade, C.R., Bernardes, F.F., 2019. Biological resistance of heat-treated wood of Pinus caribaea and eucalyptus saligna. Maderas. Ciencia y tecnología, 21(2): 223-230.
7. Budakçı, M., Sönmez A., Pelit H., 2012. The color changing effect of the moisture content of wood materials on water borne varnishes. BioResources, 7(4): 5448-5459.
8. Fengel, D., Wegener, G., 1989. Wood: Chemistry, Ultrastructure, Reactions. Walter De, Germany.

9. Hassoun, M.H., 1995. Fundamentals of Artificial Neural Networks. MIT Press, London, England.
10. Hill C.A., 2007. Wood Modification: Chemical, Thermal and Other Processes. John Wiley & Sons, England.
11. Hunt, R.W.G., Pointer M.R., 2011. Measuring Colour. John Wiley & Sons, USA.
12. Johansson, D., 2005. Strength and colour response of solid wood to heat treatment. Licentiate Thesis, Department of Skellefteå Campus, Luleå Tekniska Universitet, Skellefteå-Sweden.
13. Kamdem, D., Pizzi, A., Jermannaud, A., 2002. Durability of Heat-Treated Wood. Holz als Roh-und Werkstoff, 60(1): 1-6.
14. Kol, H.Ş., Keskin, S.A., Vaydoğan, K.G., 2017. Effect of heat treatment on the mechanical properties and dimensional stability of beech wood. Journal of Advanced Technology Sciences, 6(3): 820-830.
15. Korkut, S., Kocaefe D., 2009. Effect of heat treatment on wood properties. Duzce University Journal of Forestry, 5(2): 11-34.
16. McGuire, R.G., 1992. Reporting of objective color measurements. HortScience, 27(12): 1254-1255.
17. Millett, M., 1972. Accelerated aging: Residual weight and flexural properties of wood heated in air at 115 ℃ to 175 ℃. Journal of Wood Science, 4: 193-201.
18. Moayedi, H., Mosallanezhad, M., Rashid, A.S.A., Jusoh, W.A.W., Muazu, M.A., 2020. A systematic review and meta-analysis of artificial neural network application in geotechnical engineering: Theory and applications. Neural Computing and Applications, 32(2): 495-518.
19. Nasser, I.M., Abu-Naser, S.S., 2019. Predicting tumor category using artificial neural networks. International Journal of Academic Health and Medical Research, 3(2): 1-7.
20. Nguyen, T.T., Van Nguyen, T.H., Ji, X., Yuan, B., Trinh, H.M., Do, K.T.L. Guo, M., 2019. Prediction of the color change of heat-treated wood during artificial weathering by artificial neural network. European Journal of Wood and Wood Products, 77(6): 1107-111
21. Nuopponen, M., 2005. Thermal modification of wood and FT-IR and UV Raman spectroscopic; Studies of its extractable compounds. Ph.D. Thesis, Helsinki University, Helsinki-Sweden.
22. Oliveira, R.M.D., Brisolari, A., Sales A., Gonçalves D., 2010. Wettability, Shrinkage and color changes of Araucaria angustifolia after heating treatment. Materials Research, 13(3): 351-354.
23. Oliver, J., Blakeney, A., Allen H., 1992. Measurement of flour color in color space parameters. Cereal Chemistry, 69(5): 546-551.
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. Shi, J.L., Kocaefe, D., Zhang, J., 2007. Mechanical behaviour of quebec wood species heat-treated using thermowood process. Holz als Roh-und Werkstoff, 65(4): 255-259.
26. Tiryaki, S., Özşahin, Ş., Yıldırım, İ., 2014. Comparison of artificial neural network and multiple linear regression models to predict optimum bonding strength of heat treated woods. International Journal of Adhesion and Adhesives, 55: 29-36.
27. TS-2595, 1977. Wood-Determination of Ultimate Stress in Compression Parallel to Grain. Turkish Standards Institution, Turkey.
28. Unsal, O., Ayrilmis N., 2005. Variations in compression strength and surface roughness of heat-treated turkish river red gum (Eucalyptus camaldulensis) wood. Journal of Wood Science, 51(4): 405-409.
29. Van Nguyen, T. H., Nguyen, T.T., Ji, X., Do, K.T.L., Guo, M., 2018. Using artificial neural networks (ANN) for modeling predicting hardness change of wood during Heat Treatment. IOP Conference Series: Materials Science and Engineering, 394(3): 1-7.
30. Viitanen, H., Jämsä, S., Paajanen, L., Nurmi A., Viitaniemi P., 1994. The effect of heat treatment on the properties of spruce. A preliminary Report. The International Research Group on Wood Preservation, 29 May-3 June, Nusa Dua, Bali, Indonesia, pp. 1-4.
31. Vinha, A.J., Carvalho, A.G., Teixeira de Souza, M., Marangon Jardim, C., de Cassia Oliveira Carneiro, A., Luiz Colodette, J., 2015. Effect of extractives on wood color of heat treated Pinus radiata and Eucalyptus pellita. Maderas. Ciencia y Tecnología, 17(4): 857-864.
32. Walczak, S. 2005. Artificial neural network medical decision support tool: Predicting transfusion requirements of ER patients. IEEE Transactions on Information Technology in Biomedicine, 9(3): 468-474.
33. Willis, M.J., Montague, G.A., Di Massimo, C., Tham, M.T., Morris A.J., 1992. Artificial neural networks in process estimation and control. Automatica, 28(6): 1181-1187.
34. Yan-Jun, X., Yi-Xing, L., Yao-Xing S., 2002. heat-treated wood and its development in Europe. Journal of Forestry Research, 13(3): 224-230.
35. Yildiz, S., Gezer, E.D., Yildiz U.C., 2006. Mechanical and chemical behavior of spruce wood modified by heat. Building and Environment, 41(12): 1762-1766.
36. Zanuncio, A.J.V., Carvalho, A.G., Da Silva, L.F., Da Silva, M.G., Carneiro, A.D.C.O., Colodette, J.L., 2017. Prediction of the physical, mechanical and colorimetric properties of Eucalyptus grandis heat-treated wood using artificial neural networks. Scientia Forestalis/Forest Sciences, 45(113): 109-118.