Prediction of the equilibrium moisture content and specific gravity of thermally modified wood via an Aquila optimization algorithm back-propagation neural network model

The equilibrium moisture content and specific gravity of Uludag fir (Abies bornmüelleriana Mattf.) hornbeam (Carpinus betulus L.) woods were investigated following heat treatment at different temperatures times. Two prediction models established based on the Aquila optimization algorithm back-propagation neural network model. To demonstrate effectiveness accuracy proposed model, it was compared with a tent sparrow search algorithm-back-propagation an artificial network. results showed that model reduced root mean square error value original by 87% 97%, respectively, decision coefficients (R2) 0.99 0.98; as such, effect obvious. Therefore, this paper provides effective method for process parameters (such time, temperature, air pressure) in wood related fields.