Comparative Analysis of ANN-MLP, ANFIS-ACO<sub>R</sub> and MLR Modeling Approaches for Estimation of Bending Strength of Glulam
Multiple linear regression (MLR), adaptive network-based fuzzy inference system–ant colony optimization algorithm hybrid (ANFIS-ACO<sub>R</sub>) and artificial neural network–multilayer perceptron (ANN-MLP) were tested to model the bending strength of Glulam (glue-laminated timber) manuf...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Journal of Composites Science |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2504-477X/7/2/57 |
| _version_ | 1797620116435763200 |
|---|---|
| author | Morteza Nazerian Masood Akbarzadeh Antonios N. Papadopoulos |
| author_facet | Morteza Nazerian Masood Akbarzadeh Antonios N. Papadopoulos |
| author_sort | Morteza Nazerian |
| collection | DOAJ |
| description | Multiple linear regression (MLR), adaptive network-based fuzzy inference system–ant colony optimization algorithm hybrid (ANFIS-ACO<sub>R</sub>) 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 (<i>Platanus orientalis</i> 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. |
| first_indexed | 2024-03-11T08:37:03Z |
| format | Article |
| id | doaj.art-4b7c5a1544b84e35b023842bd78c7c7a |
| institution | Directory Open Access Journal |
| issn | 2504-477X |
| language | English |
| last_indexed | 2024-03-11T08:37:03Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Composites Science |
| spelling | doaj.art-4b7c5a1544b84e35b023842bd78c7c7a2023-11-16T21:23:33ZengMDPI AGJournal of Composites Science2504-477X2023-02-01725710.3390/jcs7020057Comparative Analysis of ANN-MLP, ANFIS-ACO<sub>R</sub> and MLR Modeling Approaches for Estimation of Bending Strength of GlulamMorteza Nazerian0Masood Akbarzadeh1Antonios N. Papadopoulos2Department of Bio Systems, Faculty of New Technologies and Aerospace Engineering, Shahid Beheshti University, Tehran 1983969411, IranDepartment of Bio Systems, Faculty of New Technologies and Aerospace Engineering, Shahid Beheshti University, Tehran 1983969411, IranLaboratory of Wood Chemistry and Technology, Department of Forestry and Natural Environment, International Hellenic University, GR-661 00 Drama, GreeceMultiple linear regression (MLR), adaptive network-based fuzzy inference system–ant colony optimization algorithm hybrid (ANFIS-ACO<sub>R</sub>) 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 (<i>Platanus orientalis</i> 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.https://www.mdpi.com/2504-477X/7/2/57GlulamUF-modified starch adhesiveZnO nano particleMLRANN-MLPANFIS-ACO<sub>R</sub> |
| spellingShingle | Morteza Nazerian Masood Akbarzadeh Antonios N. Papadopoulos Comparative Analysis of ANN-MLP, ANFIS-ACO<sub>R</sub> and MLR Modeling Approaches for Estimation of Bending Strength of Glulam Journal of Composites Science Glulam UF-modified starch adhesive ZnO nano particle MLR ANN-MLP ANFIS-ACO<sub>R</sub> |
| title | Comparative Analysis of ANN-MLP, ANFIS-ACO<sub>R</sub> and MLR Modeling Approaches for Estimation of Bending Strength of Glulam |
| title_full | Comparative Analysis of ANN-MLP, ANFIS-ACO<sub>R</sub> and MLR Modeling Approaches for Estimation of Bending Strength of Glulam |
| title_fullStr | Comparative Analysis of ANN-MLP, ANFIS-ACO<sub>R</sub> and MLR Modeling Approaches for Estimation of Bending Strength of Glulam |
| title_full_unstemmed | Comparative Analysis of ANN-MLP, ANFIS-ACO<sub>R</sub> and MLR Modeling Approaches for Estimation of Bending Strength of Glulam |
| title_short | Comparative Analysis of ANN-MLP, ANFIS-ACO<sub>R</sub> and MLR Modeling Approaches for Estimation of Bending Strength of Glulam |
| title_sort | comparative analysis of ann mlp anfis aco sub r sub and mlr modeling approaches for estimation of bending strength of glulam |
| topic | Glulam UF-modified starch adhesive ZnO nano particle MLR ANN-MLP ANFIS-ACO<sub>R</sub> |
| url | https://www.mdpi.com/2504-477X/7/2/57 |
| work_keys_str_mv | AT mortezanazerian comparativeanalysisofannmlpanfisacosubrsubandmlrmodelingapproachesforestimationofbendingstrengthofglulam AT masoodakbarzadeh comparativeanalysisofannmlpanfisacosubrsubandmlrmodelingapproachesforestimationofbendingstrengthofglulam AT antoniosnpapadopoulos comparativeanalysisofannmlpanfisacosubrsubandmlrmodelingapproachesforestimationofbendingstrengthofglulam |