Views
10
Downloands
2
Bu çalışmanın amacı yapay sinir ağı (YSA) yaklaşımı ile doğu kayını (Fagus orientalis Lipsky) ahşabının yüzey pürüzlülüğünü modellemektir. İlk olarak, yatay bant zımpara makinesinin çalışma parametreleri (60-80-100 zımpara numarası, 4-7-10 m/dk besleme hızı ve 0,1-0,2-0,3 mm kesme derinliği) belirlenmiştir. Numunelerin yüzey pürüzlülüğü deneysel olarak kaydedildikten sonra veriler eğitim ve test veri setlerine ayrılmıştır. Daha sonra, mevcut veriler Ra, Rq ve Rz’nin tahmin değerlerini doğru bir şekilde elde etmek için YSA yaklaşımı ile modellenmiştir. Deneysel sonuçlar ile teorik bulgular arasındaki karşılaştırma (RRa = 0,99869, RRq = 0,9982 ve RRz = 0,99882) birbirleriyle iyi bir uyum içinde olduğunu göstermektedir. Bu bağlamda, bu çalışma, kayın yüzey pürüzlülüğünün yapay sinir ağları yaklaşımı kullanılarak çok daha yüksek doğrulukta ve daha düşük hatalarda mükemmel bir şekilde tahmin edildiğini göstermiştir.
The aim of this study is to model the surface smoothness of the wood (Fagus orientalis Lipsky) with the approach of the artificial nerve network (YSA). First, the working parameters of the horizontal band cutting machine (60-80-100 cutting numbers, 4-7-10 m/min power speed and 0.1-0.2-0.3 mm cutting depth) are determined. After the surface smoothness of samples is experimentally recorded, the data is divided into training and test data sets. Later, the existing data was modeled with the YSA approach to obtain the predictive values of Ra, Rq and Rz correctly. The comparison between experimental results and theoretical findings (RRa = 0.99869, RRq = 0.9982 and RRz = 0.99882) shows that it is in good harmony with each other. In this context, this study has shown that the curve surface smoothness is perfectly predicted with much higher accuracy and lower errors using the artificial nerve network approach.
The aim of this study was to model the surface roughness of Oriental beech (Fagus orientalis Lipsky) wood with the aid of artificial neural network (ANN) approach. Firstly, the working parameters of a wide belt sanding machine were adjusted to be the sanding belt grit size of 60-100, feeding speed from 4 m/min to 10 m/min, and sanding cutting depth from 0.1 mm until 0.3 mm, respectively. Secondly, after the surface roughness of the samples was experimentally recorded, the data were divided into two basic cathagories: namely, (I) the training sets and (II) test data sets. Thirdly, they were modeled by the approach of artificial neural networks so that the fundamental surface roughness parameters (Ra, Rq and Rz) can be anticipated thoroughly. The comparisons between the experimental results and theoretical findings (RRa = 0.99869, RRq = 0.9982 and RRz = 0.99882) show well-agreement with each other’s. In this respect, this study declares that the surface roughness of the solid beech was perfectly predicted within far higher accuracy and relatively lower error by using the artificial neural networks approach.
Field : Fen Bilimleri ve Matematik
Journal Type : Ulusal
Article Detail 
Similar Articles
Download PDF
Journal Information
Listen Paper
Cite
Print This Page
Share
Mendeley
