DOI: https://doi.org/10.1016/j.compositesb.2016.04.036

Abstract:   The traditional regression method was compared with an artificial neural network for obtaining the static modulus of elasticity (MOEstatic) of Pinus radiata timber using the dynamic modulus of elasticity determined by ultrasound in the first case and ultrasonic wave propagation velocity in the second case.

Whereas the regression model is capable of explaining 70% of the variability of the samples at best, the artificial neural network can explain 80%, indicating that this type of tool improves the estimate of MOEstatic when it is obtained using the ultrasonic technique.