Odun Yüzey Pürüzlülüğü Tahmininde Bir Yapay Sinir Ağı Modelinin Kullanılması

Abstract

Ağaç malzemelerin yüzey pürüzlülüğü, nihai ürünlerin kalitesinin değerlendirilmesi açısından çok önemlidir. Bu nedenle bu çalışmada, odun türü, bıçak sayısı, besleme hızı ve kesme derinliğinin planyalama işleminde yüzey pürüzlülüğü üzerindeki etkisini modellemek için bir yapay sinir ağı (YSA) modeli geliştirilmiştir. Farklı YSA modelleri oluşturulmuş ve bunların performansı ortalama mutlak yüzde hata (MAPE), ortalama karesel hatanın karekökü (RMSE) ve determinasyon katsayısı (R²) kullanılarak değerlendirilmiştir. Önerilen modelin test safhasındaki MAPE, RMSE ve R² değerleri sırasıyla %7,27, 0,57 ve 0,903 olmuştur. Sonuç olarak YSA, planyalanan odunun yüzey pürüzlülüğünü tahmin etmede etkili bir araçtır ve maliyetli ve zaman alıcı araştırmalar yerine oldukça yararlıdır.

Keywords

• Yapay sinir ağı,Yüzey pürüzlülüğü,Bıçak sayısı,Besleme hızı,Kesme derinliği

Utilizing an Artificial Neural Network Model in Wood Surface Roughness Prediction

Abstract

The surface roughness of wood materials is very important in terms of assessing the quality of final products. Therefore, in this study, an artificial neural network (ANN) model was developed to model the effect of wood species, number of knives, feed rate, and cutting depth on surface roughness in the planing process. Different ANN models were created and the performance of them was evaluated using the mean absolute percentage error (MAPE), the root mean square error (RMSE), and the coefficient of determination (R²). The MAPE, RMSE, and R² values in the testing phase of the proposed model were 7.27%, 0.57, and 0.903, respectively. Consequently, ANN is an effective tool in predicting the surface roughness of planed wood and quite useful instead of costly and time-consuming investigations.

Keywords

• Artificial neural network,Surface roughness,Number of knives,Feed rate,Cutting depth

References

1. [1] C. Söğütlü, P. Nzokou, I. Koc, R. Tutgun and N. Döngel, “The effects of surface roughness on varnish adhesion strength of wood materials,” Journal of Coatings Technology and Research, vol. 13, no. 5, pp. 863–870, 2016.
2. [2] S. D. Sofuoğlu and A. Kurtoğlu, “Effects of machining conditions on surface roughness in planing and sanding of solid wood,” Drvna Industrija, vol. 66, no. 4, pp. 265–272, 2015.
3. [3] L. Gurau and M. Irle, “Surface roughness evaluation methods for wood products: a review,” Current Forestry Reports, vol. 3, no. 2, pp. 119–131, 2017.
4. [4] M. Budakci, L. Gurleyen, H. Cinar and S. Korkut, “Effect of wood finishing and planing on surface smoothness of finished wood,” Journal of Applied Sciences, vol. 7, no. 16, pp. 2300–2306, 2007.
5. [5] B. Hendarto, E. Shayan, B. Ozarska and R. Carr, “Analysis of roughness of a sanded wood surface,” International Journal of Advanced Manufacturing Technology, vol. 28, no. 7–8, pp. 775–780, 2006.
6. [6] İ. Aydın ve G. Çolakoğlu, “Odun yüzeylerinde pürüzlülük ve pürüzlülük ölçüm yöntemleri,” Artvin Orman Fakültesi Dergisi, c. 4, s. 1, ss. 92–102, 2003.
7. [7] E. Csanády, E. Magoss and L. Tolvaj, Quality of machined wood surfaces, Basel: Springer International Publishing, 2015.
8. [8] H. Efe, S. Demirci and Y. Kilic, “Effect of the cutting direction, number of cutters, feed rate and cutting depth to the surface roughness in planning beech (Fagus orientalis Lipsky) wood,” Kastamonu University Journal of Forestry Faculty, vol. 3, no. 1, pp. 77–87, 2003.

9. [9] I. Usta, S. Demirci and Y. Kilic, “Comparison of surface roughness of locust acacia (Robinia pseudoacacia L.) and european oak (Quercus petraea (Mattu.) Lieble.) in terms of the preparative process by planing,” Building and Environment, vol. 42, no. 8, pp. 2988–2992, 2007.
10. [10] S. Demirci, “Effect of the number of knives, feed rate and cutting depth on surface roughness of some wood species processed with planer,” Kastamonu University Journal of Forestry Faculty, vol. 13, no. 1, pp. 100–108, 2013.
11. [11] A. Rolleri, F. Burgos and A. Aguilera, “Surface roughness and wettability variation: the effect of cutting distance during milling of pinus radiata wood,” Drvna Industrija, vol. 67, no. 3, pp. 223–228, 2016.
12. [12] R. Haghbakhsh, H. Adib, P. Keshavarz, M. Koolivand and S. Keshtkari, “Development of an artificial neural network model for the prediction of hydrocarbon density at high-pressure, high-temperature conditions,” Thermochimica Acta, vol. 551, pp. 124–130, 2013.
13. [13] I. Yildirim, S. Ozsahin and K. C. Akyuz, “Prediction of the financial return of the paper sector with artificial neural networks,” BioResources, vol. 6, no. 4, pp. 4076–4091, 2011.
14. [14] Ş. Özşahin, “The use of an artificial neural network for modeling the moisture absorption and thickness swelling of oriented strand board,” BioResources, vol. 7, no. 1, pp. 1053–1067, 2012.
15. [15] C. Demirkir, Ş. Özsahin, I. Aydin and G. Colakoglu, “Optimization of some panel manufacturing parameters for the best bonding strength of plywood,” International Journal of Adhesion and Adhesives, 46, pp. 14–20, 2013.
16. [16] S. Ozsahin, “Optimization of process parameters in oriented strand board manufacturing with artificial neural network analysis,” European Journal of Wood and Wood Products, vol. 71, no. 6, pp. 769–777, 2013.
17. [17] S. Tiryaki, Ş. Özşahin and A. Aydın, “Employing artificial neural networks for minimizing surface roughness and power consumption in abrasive machining of wood,” European Journal of Wood and Wood Products, vol. 75, no. 3, pp. 347–358, 2017.
18. [18] A. K. Yadav and S. S. Chandel, “Solar radiation prediction using artificial neural network techniques: a review,” Renewable and Sustainable Energy Reviews, vol. 33, pp. 772–781, 2014.
19. [19] S. Haykin, Neural networks: a comprehensive foundation, New York: Macmillan College Publishing Company, 1994.
20. [20] A. M. Kalteh, “Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform,” Computers & Geosciences, vol. 54, pp. 1–8, 2013.
21. [21] G. Z. Quan, Z. Y. Zou, T. Wang, B. Liu, J. C. Li, “Modeling the hot deformation behaviors of as-extruded 7075 aluminum alloy by an artificial neural network with back-propagation algorithm,” High Temperature Materials and Processes, vol. 36, no. 1, pp. 1–13, 2017.
22. [22] D. Z. Antanasijević, V. V. Pocajt, D. S. Povrenović, M. D. Ristić and A. A. Perić-Grujić, “PM10 emission forecasting using artificial neural networks and genetic algorithm input variable optimization,” Science of the Total Environment, vol. 443, pp. 511–519, 2013.
23. [23] S. Tiryaki, S. Bardak and A. Aydın, “Modeling of wood bonding strength based on soaking temperature and soaking time by means of artificial neural networks,” International Journal of Intelligent Systems and Applications in Engineering, vol. 4, pp. 153–157, 2016.
24. [24] V. Yadav and S. Nath, “Forecasting of PM10 using autoregressive models and exponential smoothing technique,” Asian Journal of Water, Environment and Pollution, vol. 14, no. 4, pp. 109–113, 2017.
25. [25] F. Taşpınar and Z. Bozkurt, “Application of artificial neural networks and regression models in the prediction of daily maximum PM10 concentration in Düzce, Turkey,” Fresenius Environmental Bulletin, vol. 23, no. 10, pp. 2450–2459, 2014.
26. [26] S. Ozsahin and I. Aydin, “Prediction of the optimum veneer drying temperature for good bonding in plywood manufacturing by means of artificial neural network,” Wood Science and Technology, vol. 48, no. 1, pp. 59–70, 2014.
27. [27] D. A. Stumbo, “Surface texture measurements for quality and production control,” Forest Products Journal, vol. 10, no. 12, pp. 122–124, 1960.
28. [28] S. Tiryaki, A. Malkoçoğlu and Ş. Özşahin, “Using artificial neural networks for modeling surface roughness of wood in machining process,” Construction and Building Materials, vol. 66, pp. 329–335, 2014.