GÜNTEKİN, Ergün Süleyman Demirel Üniversitesi - Orman Fakültesi - Orman Endüstri Mühendisliği, Turkey , CENGİZ, Yavuz Süleyman Demirel University - Mühendislik Fakültesi - Elektronik-Haberleşme Mühendisliği Bölümü, Turkey , AYDOĞAN, Turgay Süleyman Demirel University, Turkey , YILMAZ AYDIN, Tuğba Süleyman Demirel Üniversitesi - Orman Fakültesi - Orman Endüstri Mühendisliği, Turkey , ÖZDAMAR, İ. Halil Süleyman Demirel Üniversitesi - Orman Fakültesi - Orman Endüstri Mühendisliği, Turkey

Prediction of Elasticity for Turkish Red Pine (Pinus Brutia Ten.) Lumber Using Linear Modeling and Artificial Neural Networks (ANN)

25377

In this study, elasticity of Turkish Red Pine (Pinus brutia Ten.) lumbers was predicted using lineer modeling and artificial neural networks (ANN). The lumber samples represent 30-80 years old red pine trees harvested from a south west site in Turkey. Natural frequency values of lumbers in 38 mm x 89 mm in cross section and 3 meters in length were measured by stress wave device. Linear modeling and ANN were evaluated by employing several optimization techniques using some physical measurements from the logs and lumbers. Static elasticity values of the lumbers were determined using three point bending tests. Coefficients of determination between measured and predicted MOE s for linear modeling and ANN were 0.87 and 0.91, respectively. Among the ANN models studied the model which uses visual classes, density, width, annual ring width, moisture content, and natural frequency as inputs gave the highest coefficient of determination of 0.91. The results show that linear modeling and ANN can provide accurate elasticity prediction for Turkish Red Pine lumber coming from different logs.

64

Red Pine lumber , Elasticity , Linear modeling , Artificial neural networks

Journal Of Natural an‎d Applied Sciences

68