Search

Multiple linear regression (MLR), adaptive network-based fuzzy inference system–ant colony optimization algorithm hybrid (ANFIS-ACOR) and artificial neural network–multilayer perceptron (ANN-MLP) were tested to model the bending strength of Glulam (glue-laminated timber) manufactured with a plane tree (Platanus orientalis L.) wood layer adhered with different weight ratios (WR) of modified starch/urea formaldehyde (UF) adhesive containing different levels of nano-ZnO (NC) used at different levels of the press temperature (Tem) and time (Tim). According to X-ray diffraction (XRD) and stress–strain curves, some changes in the behavior of the product were seen. After selecting the best model through determining statistics such as the determination coefficient (R2) and root mean square error (RMSE), mean absolute error (MAE) and sum of squares error (SSE), the production process was optimized to obtain the highest modulus of rupture (MOR) using the Genetic Algorithm (GA) combined with MLP. It was determined that the MLP had the best accuracy in estimating the response. According to the MLP-GA hybrid, the optimum input values for obtaining the best response include: WR—49.1%, NC—3.385%, Tem—199.4 °C and Tim—19.974 min. [ABSTRACT FROM AUTHOR]

The purpose of the present article is to study the bending strength of glulam prepared by plane tree (Platanus Orientalis-L) wood layers adhered by UF resin with different formaldehyde to urea molar ratios containing the modified starch adhesive with different NaOCl concentrations. Artificial neural network (ANN) as a modern tool was used to predict this response, too. The multilayer perceptron (MLP) models were used to predict the modulus of rapture (MOR) and the statistics, including the determination coefficient (R2), root mean square error (RMSE), and mean absolute percentage error (MAPE) were used to validate the prediction. Combining the ANN and the genetic algorithm by using the multiple objective and nonlinear constraint functions, the optimum point was determined based on the experimental and estimated data, respectively. The characterization analysis, performed by FTIR and XRD, was used to describe the effect of the inputs on the output. The results indicated that the statistics obtained show excellent MOR predictions by the feed-forward neural network using Levenberg–Marquardt algorithms. The comparison of the optimal output of the actual values obtained by the genetic algorithm resulting from the multi-objective function and the optimal output of the values estimated by the nonlinear constraint function indicates a minimum difference between both functions. [ABSTRACT FROM AUTHOR]

Multiple linear regression (MLR), adaptive network-based fuzzy inference system–ant colony optimization algorithm hybrid (ANFIS-ACOR) and artificial neural network–multilayer perceptron (ANN-MLP) were tested to model the bending strength of Glulam (glue-laminated timber) manufactured with a plane tree (Platanus orientalis L.) wood layer adhered with different weight ratios (WR) of modified starch/urea formaldehyde (UF) adhesive containing different levels of nano-ZnO (NC) used at different levels of the press temperature (Tem) and time (Tim). According to X-ray diffraction (XRD) and stress–strain curves, some changes in the behavior of the product were seen. After selecting the best model through determining statistics such as the determination coefficient (R2) and root mean square error (RMSE), mean absolute error (MAE) and sum of squares error (SSE), the production process was optimized to obtain the highest modulus of rupture (MOR) using the Genetic Algorithm (GA) combined with MLP. It was determined that the MLP had the best accuracy in estimating the response. According to the MLP-GA hybrid, the optimum input values for obtaining the best response include: WR—49.1%, NC—3.385%, Tem—199.4 °C and Tim—19.974 min.

The purpose of the present article is to study the bending strength of glulam prepared by plane tree (Platanus Orientalis-L) wood layers adhered by UF resin with different formaldehyde to urea molar ratios containing the modified starch adhesive with different NaOCl concentrations. Artificial neural network (ANN) as a modern tool was used to predict this response, too. The multilayer perceptron (MLP) models were used to predict the modulus of rapture (MOR) and the statistics, including the determination coefficient (R2), root mean square error (RMSE), and mean absolute percentage error (MAPE) were used to validate the prediction. Combining the ANN and the genetic algorithm by using the multiple objective and nonlinear constraint functions, the optimum point was determined based on the experimental and estimated data, respectively. The characterization analysis, performed by FTIR and XRD, was used to describe the effect of the inputs on the output. The results indicated that the statistics obtained show excellent MOR predictions by the feed-forward neural network using Levenberg–Marquardt algorithms. The comparison of the optimal output of the actual values obtained by the genetic algorithm resulting from the multi-objective function and the optimal output of the values estimated by the nonlinear constraint function indicates a minimum difference between both functions.