Search

The purpose of the present study is to offer an optimal model to predict the tensile index of the paper being consumed to make veneer impregnated with different weight ratios of modified starch (from 3.18 to 36.8%) to urea formaldehyde resin (WR) containing different formaldehyde to urea molar ratios (MR, from 1.16:1 to 2.84:1) enriched by different contents of silicon nano-oxide (NC, from 0 to 4%) using multiple linear regression (MLR) and adaptive neuro-fuzzy inference system (ANFIS) and compare the precision of these two models to estimate the response being examined (tensile index). Fourier-transform infrared spectroscopy (FTIR) and transmittance electron microscopy (TEM) were also used to analyze the results. The results of studying the adhesive structure using FTIR analysis showed that as the WR increased to the maximum level and MR increased to the average level (3%), more ether and methylene linkage forms due to cross-linking. TEM analysis also indicated that if an average level of silicon nano-oxide is applied, there will be more cross-linking due to the more uniform distribution and suitable interactions between the adhesive and nanoparticles. The modeling results showed that the ANFIS model estimates have been closer to the actual values compared to the MLR model. It can be concluded that the model offered by ANFIS has a higher potential to predict the tensile index of the paper impregnated with the combined adhesive of UF resin and modified starch. However, the MLR model could not offer a good estimate to predict the response. According to the preferred approach to predict the most effective property of resin coated paper, modelling would be useful to the research community and the results are beneficial in industrial applications without spending more cost and time. [ABSTRACT FROM AUTHOR]

The purpose of the present study is to offer an optimal model to predict the tensile index of the paper being consumed to make veneer impregnated with different weight ratios of modified starch (from 3.18 to 36.8%) to urea formaldehyde resin (WR) containing different formaldehyde to urea molar ratios (MR, from 1.16:1 to 2.84:1) enriched by different contents of silicon nano-oxide (NC, from 0 to 4%) using multiple linear regression (MLR) and adaptive neuro-fuzzy inference system (ANFIS) and compare the precision of these two models to estimate the response being examined (tensile index). Fourier-transform infrared spectroscopy (FTIR) and transmittance electron microscopy (TEM) were also used to analyze the results. The results of studying the adhesive structure using FTIR analysis showed that as the WR increased to the maximum level and MR increased to the average level (3%), more ether and methylene linkage forms due to cross-linking. TEM analysis also indicated that if an average level of silicon nano-oxide is applied, there will be more cross-linking due to the more uniform distribution and suitable interactions between the adhesive and nanoparticles. The modeling results showed that the ANFIS model estimates have been closer to the actual values compared to the MLR model. It can be concluded that the model offered by ANFIS has a higher potential to predict the tensile index of the paper impregnated with the combined adhesive of UF resin and modified starch. However, the MLR model could not offer a good estimate to predict the response. According to the preferred approach to predict the most effective property of resin coated paper, modelling would be useful to the research community and the results are beneficial in industrial applications without spending more cost and time.