Prediction of the Bending Strength of a Laminated Veneer Lumber (LVL) Using an Artificial Neural Network
- PDF / 419,515 Bytes
- 16 Pages / 594 x 792 pts Page_size
- 3 Downloads / 310 Views
PREDICTION OF THE BENDING STRENGTH OF A LAMINATED VENEER LUMBER (LVL) USING AN ARTIFICIAL NEURAL NETWORK
M. Nazerian,* S. A. Razavi, A. Partovinia, E. Vatankhah, and Z. Razmpour
Keywords: LVL, bending strength, nanocellulose, modified starch, artificial neural network The application of an artificial neural networks (ANN) to predicting the bending strength of a laminated veneer lumber (LVL) manufactured under different conditions is considered. First, experimental studies were conducted, and then an ANN model was developed based on the experimental data obtained. LVL specimens of walnut wood, glued with urea-formaldehyde resins containing a chemically modified starch and nanocellulose, were obtained by pressing for different times. Experimental results for them showed that the direct effect of the press time, the square effect of the modified starch, and the joint effect of them had the highest statistical significance to the bending strength of LVL. The ANN model developed gave good predictions for the bending strength, well agreeing with experimental data.
1. Introduction Wood-based composites are usually employed instead of solid wood in various structural applications. To manufacture these products, aminoplast or phenoplast resins are mainly used. These synthetic resins gradually emit the poisonous dangerous formaldehyde, which is worrisome. Therefore, its release has to be decreased or even stopped choosing appropriate process parameters by replacing these resins by biobased adhesives. For this purpose, many investigations have been performed. Nemli [1] evaluated the effect of pressing temperature and time, the pressure, and resin type on the release of formaldehyde. Petinarakis and Kavvoura [2] studied the effect of various technological factors affecting this emission. Salem et al. [3] evaluated the release of formaldehyde gas from wood-based panels and flooring materials. It is believed Faculty of New Technologies Engineering, Shahid Beheshti University, Tehran, Iran * Corresponding author; tel.: +98 911 291 0860; e-mail: [email protected]
Russian translation published in Mekhanika Kompozitnykh Materialov, Vol. 56, No. 5, pp. 945-966, SeptemberOctober, 2020. Original article submitted February 12, 2020; revision submitted June 26, 2020. 0191-5665/20/5605-0649 © 2020 Springer Science+Business Media, LLC
649
that the origin of free formaldehyde emission from UF resin-based wooden products is the nonreacted formaldehyde and the return of amino–methylene bonds in the cured resin network. These returned bonds are also the main reason for the low water resistance of urea-formaldehyde (UF) resins [4]. Much attention to reducing the emission of formaldehyde from UF resins and increasing the physical and mechanical properties of wood-based panels has received their modification. Resin modification begins with selecting its synthesis parameters. The most important factor in synthesis of the resins is the urea-to-formaldehyde (U:F) molar ratio. This ratio affects the quantity of formaldehyde emission, v
Data Loading...
