Prediction of tension properties of cork from its physical properties using neural networks

article

Iglesias, C.
Anjos, O.
Martínez, J.
Pereira, H.
Taboada, J.

Springer

IGLESIAS, C.[et al.] (2015) - Prediction of tension properties of cork from its physical properties using neural networks. European Journal of Wood and Wood Products. ISSN 0018-3768. 73:3. P. 347-356.

0018-3768

10.1007/s00107-015-0885-1

Prediction of tension properties of cork from its physical properties using neural networks

2017-07-22T16:20:51Z
2017-07-22T16:20:51Z
2015

A tool to predict the tensile properties of cork was applied in order to be used for material and application selection. The mechanical behaviour of cork under tensile stress was determined in the tangential and axial direction. Cork planks of two commercial quality classes were used and samples were taken at three radial positions in the planks.For the construction of the predictive model, nine properties were measured: mechanical properties (Young’s modulus, fracture stress and fracture strain) and the physical properties (porosity, number of pores, density, approximation of the pores to elliptical and circular shape and distance to the nearest pore). The aim of this research work was to predict the mechanical properties from the physical properties using neural networks.Initially, the problem was approached as a regression problem, but the poor correlation coefficients obtained made the authors define a classification problem. The criterion used for the classification problem was the test error rate, training the neural network with a variety of neurons in the hidden layer until the minimum error was achieved. The influence of each individual variable was also studied in order to evaluate their importance for the prediction of the mechanical properties.The results show that the Young’s modulus and fracture stress can be predicted with an error rate in test of 10.6 and 10.2 %, respectively, being the measure of the approximation of the pores to elliptical shape avoidable. Regarding the fracture strain, its prediction from physical properties implies an excessive error.
info:eu-repo/semantics/publishedVersion

restrictedAccess
http://creativecommons.org/licenses/by/4.0/

eng