Fateme Naderi

Bio: Fateme Naderi is an academic researcher from Shahid Beheshti University. The author has contributed to research in topics: Adaptive neuro fuzzy inference system & Materials science. The author has co-authored 2 publications.

Developing adaptive neuro-fuzzy inference system-based models to predict the bending strength of polyurethane foam-cored sandwich panels

Abstract: The aim of this paper was to improve the performance of the adaptive neuro-fuzzy inference system (ANFIS) and to predict the flexural strength of the sandwich panels made with thin medium density fiberboard as surface layers, and polyurethane foam as a core layer, by applying metaheuristic optimization methods. For this purpose, various models, namely ant colony optimization for the continuous domain (ACOR), differential evolution (DE), genetic algorithm (GA), and particle swarm optimization (PSO) were applied and compared, as different efficient bio-inspired paradigms, to assess their suitability for training the adaptive neuro-fuzzy inference system model. The predicted values of the flexural strength resulting from applying adaptive neuro-fuzzy inference system trained by ACOR, DE, GA, and PSO, were compared with the values derived from adaptive neuro-fuzzy inference system classical model. The molar ratio of formaldehyde to melamine and urea, sandwich panel thickness, and the weight ratio of the modified starch to MUF resin (OS/MUF weight ratio) were used as an input variables and the modulus of rupture was used as an output one. The developed hybrid models were used to predict the values of the modulus of rupture obtained from experimental tests. In order to evaluate and compare the performance of the models, three performance criteria were employed namely, determination coefficient (R2), root mean square error, and mean absolute percentage error. It was found that ANFIS–ACOR, ANFIS–DE, ANFIS–GA, and ANFIS–PSO showed different performance ratios compared to the predicting model. In addition, the ANFIS–GA model is found to be by far more accurate than the other hybrid models.

Modeling the Bending Strength of MDF Faced, Polyurethane Foam-Cored Sandwich Panels Using Response Surface Methodology (RSM) and Artificial Neural Network (ANN)

Abstract: The present study evaluates and compares predictions on the performance and the approaches of the response surface methodology (RSM) and the artificial neural network (ANN) so to model the bending strength of the polyurethane foam-cored sandwich panel. The effect of the independent variables (formaldehyde to urea molar ratio (MR), sandwich panel thickness (PT) and the oxidized protein to melamine-urea-formaldehyde synthesized resin weight ratio (WR)) was examined based on the bending strength by the central composite design of the RSM and the multilayer perceptron of the ANN. The models were statistically compared based on the training and validation data sets via the determination coefficient (R2), the root mean squares error (RMSE), the absolute average deviation (AAD) and the mean absolute percentage error (MAPE). The R2 calculated for the ANN and the RSM models was 0.9969 and 0.9960, respectively. The models offered good predictions; however, the ANN model was more precise than the RSM model, thus proving that the ANN and the RSM models are valuable instruments to model and optimize the bending properties of the sandwich panel.

Performance Evaluation of an Improved ANFIS Approach Using Different Algorithms to Predict the Bonding Strength of Glulam Adhered by Modified Soy Protein–MUF Resin Adhesive

Abstract: Despite studies on the potential replacement of synthetic resins by bio-based adhesives such as proteins in recent years, there is still no reliable method for estimating the strength of wood products made using the combined parameters in the literature. This limitation is due to the nonlinear relationship between strength and the combined components. In the present research, the application of artificial intelligence techniques was studied to predict the bonding strength of glulam adhered by protein containing different ratios of MUF (melamine–urea–formaldehyde) resin with different F-to-U/M molar ratios at different press temperatures. For this purpose, the ANFIS artificial intelligence model was used as basic mode or combined with ant colony optimization (ACOR), particle swarm optimization (PSO), differential evaluation (DE) and genetic algorithms (GA) to develop an optimal trained model to predict the bonding strength of glulam based on experimental results. Comparison of the obtained results with the experimental results showed the ability of the above methods to estimate the bonding strength of glulam in a reliable manner. Although the basic ANFIS alone and in combination with other algorithms was not able to achieve an ideal performance prediction to estimate bonding strength, the combination of GA and ANFIS offered an excellent ability compared to the combination of other algorithms combined with ANFIS. Hence, the developed ANFIS-GA model is introduced as the best prediction technique to solve bonding strength problems of laminated products. In addition, using the developed optimal model, a precise attempt was made to show the nature of the parameters used to produce glulam and determine the optimum limit.

Application of the Artificial Neural Network to Predict the Bending Strength of the Engineered Laminated Wood Produced Using the Hydrolyzed Soy Protein-Melamine Urea Formaldehyde Copolymer Adhesive

Abstract: The artificial neural network (ANN) was used to predict the modulus of rupture (MOR) of the laminated wood products adhered by melamine/urea formaldehyde (MUF) resin with different formaldehyde to melamine/urea molar ratios combined with different weight ratios of the protein adhesive resulting from the alkaline treatment (NaOH) of the soybean oil meal to MUF resin pressed at different temperatures according to the central composite design (CCD). After making the boards and performing the mechanical test to measure the MOR, based on experimental data, different statistics such as determination coefficient (R2), root mean square error (RMSE), mean absolute error (MAE) and sum of squares error (SSE) were determined, and then the suitable algorithm was selected to determine the estimated values. After comparing estimated values with the experimental values, the direct and interactive effects of the independent variables on MOR were determined. The results indicated that using suitable algorithms to train the ANN well, a very good estimate of the bending strength of the laminated wood products can be offered with the least error. In addition, based on the estimated and measured strengths and FTIR and TGA diagnostic analyses, it was found that the replacement of the MUF resin by the protein bio-based adhesive when using low F to M/U molar ratios, the MOR is maximized if a high range of temperature is used during the press.

Machine learning‐based model for predicting the material properties of nanostructured aerogels

Abstract: Data-driven modeling in material science rose to prominence in the last decade, and various supervised and unsupervised machine learning techniques have been employed for material development and deriving insights for decision-making purposes. In this context, machine learning can have prominent importance in the field of nanostructured aerogels for accelerated materials design and material properties prediction. Current attempts rely only on experimental approach, which have inherent shortcomings, including inefficiency due to the prolonged synthesis process, and necessity of analyzing microstructure and properties. In order to address the challenges associated with the traditional experimental approach, in this study, an artificial neural network (ANN) is employed to predict the material properties of nanostructured aerogels. Polyimide (PI) organic aerogels are selected for this purpose. Through understanding the contributing material and processing factors in PI aerogel synthesis, a dataset is prepared. Data preprocessing is performed, and through hyperparameter tuning, ANN is constructed and trained for a given dataset. Various material properties are predicted, including compressive modulus, density, and porosity. Results show that ANN is trained with high accuracy, which demonstrates the versatility and accuracy of model in materials properties prediction. This study can therefore pave the way for establishing a platform for data-driven materials innovation.

An Improved Optimization Model to Predict the MOR of Glulam Prepared by UF-Oxidized Starch Adhesive: A Hybrid Artificial Neural Network-Modified Genetic Algorithm Optimization Approach

Abstract: 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.

Comparison of the Estimation Ability of the Tensile Index of Paper Impregnated by UF-Modified Starch Adhesive Using ANFIS and MLR

Abstract: 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.

Comparative Analysis of ANN-MLP, ANFIS-ACOR and MLR Modeling Approaches for Estimation of Bending Strength of Glulam

Abstract: 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.