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.
The surface smoothness of the wood materials is very important for the assessment of the quality of the final products. Therefore, in this study, an artificial nerve network (YSA) model has been developed to model the effect of the type of wood, the number of knives, the feeding speed and the cutting depth on surface smoothness in the planning process. Different YSA models have been created and their performance has been assessed using the average absolute percentage error (MAPE), the average square error corner (RMSE) and the determination ratio (R2). The MAPE, RMSE and R2 values in the test phase of the proposed model were 7.27%, 0.57 and 0.903 respectively. As a result, YSA is an effective tool in predicting the surface smoothness of the planned wood and is quite useful instead of expensive and time-consuming research.
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.
Alan : Fen Bilimleri ve Matematik
Dergi Türü : Ulusal
Benzer Makaleler | Yazar | # |
---|
Makale | Yazar | # |
---|