Modeling of Wood Bonding Strength Based on Soaking Temperature and Soaking Time by means of Artificial Neural Networks
[ X ]
Tarih
2016
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Ismail SARITAS
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
Adhesive bonding of wood enablessufficient strength and durability to hold wood pieces together and thusproduce high quality wood products. However, it is well known that manyvariables have an important influence on the strength of an adhesive bonding.The objective of the present paper is to predict the bonding strength of spruce(Picea orientalis (L.) Link.) andbeech (Fagus orientalis Lipsky.) woodjoints subjected to soaking by using artificial neural networks. To obtain thedata for modeling, beech and spruce samples were subjected to the soaking atdifferent temperatures for different periods of time. In the ANN analysis, 70%of the total experimental data were used to train the network, 15% was used totest the validation of the network, and remaining 15% was used to test theperformance of the trained and validated network. A three-layer feedforwardback propagation artificial neural network trained by Levenberg–Marquardtlearning algorithm was found as the optimum network architecture for theprediction of the bonding strength of soaked wood samples. This architecturecould predict wood bonding strength with an acceptable level of the error.Consequently, modeling results demonstrated that artificial neural networks arean efficient and useful modeling tool to predict the bonding strength of woodsamples subjected to the soaking for different temperatures and durations.
Açıklama
Anahtar Kelimeler
Neural network, Bonding strength, Prediction, Wood, Soaking
Kaynak
International Journal of Intelligent Systems and Applications in Engineering
WoS Q Değeri
Scopus Q Değeri
Cilt
4
Sayı
Special Issue-1
