Development of an Artificial Neural Network Model to Minimize Power Consumption in the Milling of Heat-Treated and Untreated Wood

Yıl 2019, Cilt: 19 Sayı: 3, 317 - 328, 23.12.2019

Şükrü Özşahin Hilal Singer

https://doi.org/10.17475/kastorman.662699

Cited By: 4

Öz

Aim of study: The power consumption of machining operations is an important part of the total production cost. Therefore, in this study, an artificial neural network (ANN) model was developed to model the effects of treatment, rotation speed, cutting depth, and feed rate on power consumption in the wood milling process.
Material and methods: A multilayer feed-forward ANN was employed for the prediction of power consumption. The accuracy of the model was assessed by performance indicators such as MAPE, RMSE, and R².
Main results: It has been observed that the ANN model yielded very satisfactory results with acceptable deviations. The MAPE, RMSE, and R2 values were obtained as 7.533, 0.027, and 0.9737 %, respectively, in the testing phase. Furthermore, it was found that power consumption decreased with decreasing of feed rate and cutting depth.
Research highlights: The findings of this study can be used effectively in the forest industry to reduce the experimental time and costs.

Anahtar Kelimeler

Artificial Neural Network, Milling, Power Consumption, Wood

Isıl İşlem Uygulanmış ve Uygulanmamış Odunun Frezelenmesinde Güç Tüketimini Azaltmak için Bir Yapay Sinir Ağı Modelinin Geliştirilmesi

Öz

Çalışmanın amacı: İşleme operasyonlarının güç tüketimi toplam üretim maliyetinin önemli bir parçasıdır. Bu nedenle, bu çalışmada odun frezeleme işleminde muamele, dönme hızı, kesme derinliği ve besleme hızının güç tüketimi üzerine olan etkilerini modellemek için bir yapay sinir ağı (YSA) modeli geliştirilmiştir.
Materyal ve yöntem: İleri beslemeli çok katmanlı bir YSA güç tüketimini tahmin etmek için kullanılmıştır. Modelin doğruluğu, MAPE, RMSE ve R2 gibi performans göstergeleri aracılığıyla değerlendirilmiştir.
Sonuçlar: YSA modelinin kabul edilebilir sapmalarla oldukça tatmin edici neticeler elde ettiği görülmüştür. MAPE, RMSE ve R2 değerleri, test aşamasında sırasıyla % 7.533, 0.027 ve 0.9737 olarak elde edilmiştir. Ayrıca, besleme hızının ve kesme derinliğinin azalması ile güç tüketiminin azaldığı bulunmuştur.
Araştırma vurguları: Bu çalışmanın bulguları orman endüstrisinde deneysel zamanı ve maliyetleri azaltmak için etkili bir şekilde kullanılabilir.

Anahtar Kelimeler

Yapay Sinir Ağı, Frezeleme, Güç Tüketimi, Odun

Kaynakça

• Aguilera, A. & Martin, P. (2001). Machining qualification of solid wood of Fagus silvatica L. and Picea excelsa L.: cutting forces, power requirements and surface roughness. Holz als Roh- und Werkstoff, 59(6), 483-488.
• Atıcı, U. (2011). Prediction of the strength of mineral admixture concrete using multivariable regression analysis and an artificial neural network. Expert Systems with Applications, 38(8), 9609-9618.
• Avramidis, S. & Wu, H. (2007). Artificial neural network and mathematical modeling comparative analysis of nonisothermal diffusion of moisture in wood. Holz als Roh- und Werkstoff, 65, 89-93.
• Aydın, G., Karakurt, I. & Hamzacebi, C. (2014). Artificial neural network and regression models for performance prediction of abrasive waterjet in rock cutting. International Journal of Advanced Manufacturing Technology, 75(9-12), 1321-1330.
• Bakar, B. F. A., Hızıroğlu, S. & Md Tahir, P. (2013). Properties of some thermally modified wood species. Materials and Design, 43, 348-355.
• Barcík, Š., Kminiak, R., Řehák, T. & Kvietková, M. (2010). The influence of selected factors on energy requirements for plain milling of beech wood. Journal of Forest Science, 56(5), 243-250.
• Betiku, E. & Taiwo, A.E. (2015). Modeling and optimization of bioethanol production from breadfruit starch hydrolyzate vis-à-vis response surface methodology and artificial neural network. Renewable Energy, 74, 87-94.
• Canakçı, A., Özsahin, S. & Varol, T. (2012). Modeling the influence of a process control agent on the properties of metal matrix composite powders using artificial neural networks. Powder Technology, 228, 26-35.
• Castellani, M. & Rowlands, H. (2008). Evolutionary feature selection applied to artificial neural networks for wood-veneer classification. International Journal of Production Research, 46(11), 3085-3105.
• Ceylan, İ. (2008). Determination of drying characteristics of timber by using artificial neural networks and mathematical models. Drying Technology, 26(12), 1469-1476.
• Chandwani, V., Agrawal, V. & Nagar, R. (2015). Modeling slump of ready mix concrete using genetic algorithms assisted training of Artificial Neural Networks. Expert Systems with Applications, 42(2), 885-893.
• Choudhury, T.A., Hosseinzadeh, N. & Berndt, C. C. (2012). Improving the generalization ability of an artificial neural network in predicting in-flight particle characteristics of an atmospheric plasma spray process. Journal of Thermal Spray Technology, 21(5), 935-949.
• Csábrági, A., Molnár, S., Tanos, P. & Kovács, J. (2017). Application of artificial neural networks to the forecasting of dissolvedoxygen content in the Hungarian section of the river Danube. Ecological Engineering, 100, 63-72.
• Güresen, E., Kayakutlu, G. & Daim, T. U. (2011). Using artificial neural network models in stock market index prediction. Expert Systems with Applications, 38(8), 10389-10397.
• Hamzehie, M.E., Fattahi, M., Najibi, H., Van der Bruggen, B. & Mazinani, S. (2015). Application of artificial neural networks for estimation of solubility of acid gases (H2S and CO2) in 32 commonly ionic liquid and amine solutions. Journal of Natural Gas Science and Engineering, 24, 106-114.
• Ispas, M., Gurau, L., Campean, M., Hacibektasoglu, M. & Racasan, S. (2016). Milling of heat-treated beech wood (Fagus sylvatica L.) and analysis of surface quality. BioResources, 11(4), 9095-9111.
• Kalteh, A.M. (2013). Monthly river flow forecasting using artificial neural network and support vector regression models coupled with wavelet transform. Computers & Geosciences, 54, 1-8.
• Khalid, M., Lee, E.L.Y., Yusof, R. & Nadaraj, M. (2008). Design of an intelligent wood species recognition system. International Journal of Simulation: Systems, Science and Technology, 9(3), 9-19.
• Kiani Deh Kiani, M., Ghobadian, B., Tavakoli, T., Nikbakht, A.M. & Najafi, G. (2010). Application of artificial neural networks for the prediction of performance and exhaust emissions in SI engine using ethanol-gasoline blends. Energy, 35(1), 65-69.
• Kocaefe, D., Shi, J.L., Yang, D.Q. & Bouazara, M. (2008). Mechanical properties, dimensional stability, and mold resistance of heat-treated jack pine and aspen. Forest Products Journal, 58(6), 88-93.
• Koçer, S. (2010). Classifying myopathy and neuropathy neuromuscular diseases using artificial neural networks. International Journal of Pattern Recognition and Artificial Intelligence, 24(5), 791-807.
• Küçükönder, H., Boyacı, S. & Akyüz, A. (2016). A modeling study with an artificial neural network: developing estimation models for the tomato plant leaf area. Turkish Journal of Agriculture and Forestry, 40(2), 203-212.
• Lewis, C.D. (1982). International and business forecasting methods. London: Butter-worths.
• Ma, X., Zeng, W., Tian, F., Sun, Y. & Zhou, Y. J. (2012). Modeling constitutive relationship of BT25 titanium alloy during hot deformation by artificial neural network. Journal of Materials Engineering and Performance, 21(8), 1591-1597.
• Mazela, B., Zakrzewski, R., Grześkowiak, W., Cofta, G. & Bartkowiak, M. (2004). Resistance of thermally modified wood to basidiomycetes. Wood Technology, 7(1), 253-262.
• Özşahin, Ş. (2012). The use of an artificial neural network for modeling the moisture absorption and thickness swelling of oriented strand board. BioResources, 7(1), 1053-1067.
• Özşahin, Ş. (2013). Optimization of process parameters in oriented strand board manufacturing with artificial neural network analysis. European Journal of Wood and Wood Products, 71(6), 769-777.
• Özşahin, Ş. & Murat, M. (2018). Prediction of equilibrium moisture content and specific gravity of heat treated wood by artificial neural networks. European Journal of Wood and Wood Products, 76(2), 563-572.
• Quan, G.Z., Zou, Z.Y., Wang, T., Liu, B. & Li, J.C. (2017). 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, 36(1), 1-13.
• Rousek, M. & Kopecký, Z. (2005). Monitoring of power consumption in high-speed milling. Drvna Industrija, 56(3), 121-126.
• Rumbayan, M., Abudureyimu, A. & Nagasaka, K. (2012). Mapping of solar energy potential in Indonesia using artificial neural network and geographical information system. Renewable and Sustainable Energy Reviews, 16(3), 1437-1449.
• Salca, E. A. (2015). Optimization of wood milling schedule – A case study. Pro Ligno, 11(4), 525-530.
• Samarasinghe, S., Kulasiri, D. & Jamieson, T. (2007). Neural networks for predicting fracture toughness of individual wood samples. Silva Fennica, 41(1), 105-122.
• Sedleckỳ, M. & Gašparík, M. (2017). Power consumption during edge milling of medium-density fiberboard and edge-glued panel. BioResources, 12(4), 7413-7426.
• Stewart, H.A. (1974). Comparison of factors affecting power for abrasive and knife planing of hardwoods. Forest Products Journal, 24(3), 31-34.
• Tiryaki, S. & Hamzaçebi, C. (2014). Predicting modulus of rupture (MOR) and modulus of elasticity (MOE) of heat treated woods by artificial neural networks. Measurement, 49, 266-274.
• Tiryaki, S., Aras, U., Kalaycıoğlu, H., Erişir, E. & Aydın, A. (2017a). 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.
• Tiryaki, S., Malkoçoğlu, A. & Özşahin, Ş. (2016). Artificial neural network modeling to predict optimum power comsumption in wood machining. Drewno, 59(196), 109-125.
• Tiryaki, S., Özşahin, Ş. & Aydın, A. (2017b). Employing artificial neural networks for minimizing surface roughness and power consumption in abrasive machining of wood. European Journal of Wood and Wood Products, 75(3), 347-358.
• Varol, T., Canakçı, A. & Özşahin, S. (2013). Artificial neural network modeling to effect of reinforcement properties on the physical and mechanical properties of Al2024-B4C composites produced by powder metallurgy. Composites: Part B, 54, 224-233.
• Wu, N., Huang, J., Schmalz, B. & Fohrer, N. (2014). Modeling daily chlorophyll a dynamics in a German lowland river using artificial neural networks and multiple linear regression approaches. Limnology, 15(1), 47-56.
• Yadav, A. K. & Chandel, S. S. (2014). Solar radiation prediction using artificial neural network techniques: A review. Renewable and Sustainable Energy Reviews, 33, 772-781.
• Yıldırım, I., Özşahin, S. & Akyüz, K. C. (2011). Prediction of the financial return of the paper sector with artificial neural networks. BioResources, 6(4), 4076-4091.
• 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.
• Younsi, R., Kocaefe, D., Poncsak, S. & Kocaefe, Y. (2010). Computational and experimental analysis of high temperature thermal treatment of wood based on ThermoWood technology. International Communications in Heat and Mass Transfer, 37(1), 21-28.