Rodríguez-Sánchez, Alejandro E.
Thumbnail Image
Preferred name
Rodríguez-Sánchez, Alejandro E.
Official Name
Rodríguez-Sánchez, Alejandro Esteban
Translated Name
Rodríguez-Sánchez, Alejandro E.
Main Affiliation
Scopus Author ID
57202719691

Research Output
Now showing 1 - 10 of 22
No Thumbnail Available
Publication

Evidential neural network for tensile stress uncertainty quantification in thermoplastic elastomers

2024 , Rodríguez-Sánchez, Alejandro E.

View
No Thumbnail Available
Publication

Modeling Nonlinear Compressive Stress Responses in Closed-Cell Polymer Foams Using Artificial Neural Networks: A Comprehensive Case Study

2022-06-14 , Rodríguez-Sánchez, Alejandro E.

Closed-cell polymer foams are versatile materials that have multiple applications in several industries due to their mechanical energy absorption capabilities, and they are used to design protective devices as engineering solutions or to produce packaging solutions to protect goods. Because most of these products and devices operate in compression, it is necessary to know the material behavior to compressive loadings for modeling and design purposes. In this work, the compressive response of a closed-cell expanded polypropylene polymer foam is modeled using feed-forward artificial neural network models as a case study. Practical considerations and a methodology that includes the basic steps to conduct the modeling of the compressive stress of foams of this class are presented. The modeling uses foam densities, loading rates, and strain as inputs in an artificial neural network system to model compressive stress in the foam. Results help conclude that feed-forward neural networks can model the response at compression for expanded polypropylene foams considering different variables since prediction errors close to the unity of the coefficient of determination R2 and error results below 2% regarding testing data were obtained.

View
No Thumbnail Available
Publication

Neural network-driven interpretability analysis for evaluating compressive stress in polymer foams

2024 , Rodríguez-Sánchez, Alejandro E. , Héctor Plascencia-Mora , Acevedo, Mario

This research presents a method to analyze how neural network models, applied to Expanded Polypropylene and Expanded Polystyrene foams, predict their compressive stress responses. By using SHAP values and Partial Dependence Plots, the study elucidates the models’ decision-making processes. It focuses on three main features for both materials: density, loading rate, and strain, with an additional feature concerning loading and unloading for Expanded Polystyrene foam. The findings highlight that increased density and loading rate are closely correlated with higher compressive responses, and strain emerges as the most influential factor for the response of both materials. Partial Dependence Plots reveal a linear relationship with density, whereas other variables demonstrate non-linear relationships. These results validate the use of neural networks in analyzing material behavior, showing that the models’ outputs are in line with empirical observations. In conclusion, as presented, the integration of interpretability tools with neural network models offers a robust method for material response analysis, contributing to a deeper understanding of material science.

View
No Thumbnail Available
Publication

An Artificial Neural Networks approach to predict low-velocity impact forces in an elastomer material

2020 , Rodríguez-Sánchez, Alejandro E.

The study of the impact phenomenon on rubber-like materials has been traditionally related to lumped parameter modeling or discrete Finite Element models that require experimentation associated with the material behavior at a level of constitutive modeling, and additional testing to validate their operation in case of engineering applications. This article presents an Artificial Neural Network approach to predict and simulate the low-velocity impact force in a thermoplastic elastomer material. Neural network models were trained and validated with experimental data obtained from impact tests in a modified Charpy apparatus. An experimental setup and a data acquisition procedure were set out to record the impact forces on elastomer specimens. The coefficient of determination R2, the Root Mean Square Error, and the Maximum Absolute Error measures were implemented as error functions to evaluate the performance of the neural networks regarding experimental data. Results show that the proposed method helps to predict and derive impact force curves within the range of the training data, since errors below 1% regarding experimental values were obtained. The results also demonstrate that the neural networks can simulate impact force curves within the range of the experimental values without the need to involve parameters of material strain-rate sensitivity. In addition, the approach was tested in another material, and the corresponding results show good prediction capabilities since errors below 1% were obtained. Therefore, it is concluded that the presented artificial neural models, and the approach, could be useful to create solution spaces for low-velocity impact responses of thermoplastic elastomers.

View
No Thumbnail Available
Publication

Neural networks modeling of strain energy density and Tsai-Wu index in laminated composites

2024 , Elías Ledesma-Orozco , Julio C. Galvis-Chacón , Rodríguez-Sánchez, Alejandro E.

In laminated composite materials design, optimization mainly targets the stacking sequence configuration, which is defined by the lamina thickness and fiber orientations within each layer. Recent studies emphasize the increasing role of Machine Learning in promoting innovative composite designs by facilitating the accurate modeling of essential properties such as strength and stiffness. This study introduces two metamodels that utilize feed-forward artificial neural networks, taking laminate thickness and fiber steering angles as input parameters. The output variables, including strain energy density and the Tsai-Wu failure index, enable the prediction of stacking sequence configurations for laminated materials, a capability confirmed in a case study. The results showcase neural network models with the ability to predict these variables, achieving coefficients of determination above 0.90 for testing data. Consequently, this modeling approach has the potential to be a tool for designers, aiding in decision-making processes for the subsequent optimization of stiffness and strength in structural components made of laminated composite materials.

View
No Thumbnail Available
Publication

Neural networks-based modeling of compressive stress in expanded polystyrene foams: A focus on bead size parameters

2024 , Pech-Mendoza, Héctor , Rodríguez-Sánchez, Alejandro E. , Hector Plascencia Mora

Expanded polystyrene is used in diverse applications, notably for protective and structural purposes. Its cushioning and mechanical strength excel under compressive loads, especially when optimally designed. A key factor influencing its compressive stress is the initial density, which plays a significant role in determining the material’s mechanical properties. This aspect is primarily determined by the bead size distribution. Although there is a vast body of literature on modeling the stress response of expanded polystyrene, there is limited emphasis on predictions that account for this factor, which is also relevant for the manufacturing of the material. Recent literature has emphasized the capability of artificial neural networks in predicting the compressive behaviors of expanded polystyrene, incorporating various factors. In this study, artificial neural network models were used to predict the compressive stress responses of polystyrene foams, with a focus on bead size distribution parameters. Specimens of two distinct initial densities were examined using micrographs to identify bead diameters and distributions, which were then used as model inputs. Compression tests on these specimens were conducted at two different rates. The collected data facilitated the development of predictive models for the material’s compressive behavior. The model predictions closely match experimental findings, with error metrics showing deviations compared to the experimental data. This highlights the utility of artificial neural networks in modeling the compressive behavior of polystyrene foams, particularly when bead size and related parameters are considered.

View
No Thumbnail Available
Publication

An optimization of part distortion for a structural aircraft wing rib: an industrial workflow approach

2020 , Leonardo Barcenas , Elias Ledesma-Orozco , Sjoerd Van-der-Veen , Francisco Reveles-Arredondo , Rodríguez-Sánchez, Alejandro E.

Inherent residual stresses in the raw material of large monolithic structural components cause distortion when parts are machined. This is a frequent problem in the manufacturing life cycle of aircraft parts that has resulted in recurring concession, rework or scrap, which cost millions of euros to the aerospace industry. In this study an industrial workflow was implemented to predict and optimize part distortion after the machining of a representative structural aircraft-component. This was carried out by means of the following steps: i) characterization of inherent residual stresses of a material using a modified layer removal method; ii) generation of residual stress profiles using part-distortion measurements; and iii) optimization of distortion using Finite Element Analysis to derive an optimal part location. The workflow was validated with three experiments from two aluminum 7050-T7451 specimens with different residual stress states. A prediction of distortion with a Finite Element model resulted in 0.44 mm from the higher residual stresses while from the lower residual stresses the maximum distortion was 0.36 mm. The experimental testing was carried out in a CNC center to validate the numerical results. Good agreement from the numerical results in regards experimental tests led to propose the optimal part location which decreased the distortion up to 0.12 mm.

View
No Thumbnail Available
Publication

Neural network-driven interpretability analysis for evaluating compressive stress in polymer foams

2024 , Rodríguez-Sánchez, Alejandro E. , Plascencia Mora, Héctor , Acevedo, Mario

This research presents a method to analyze how neural network models, applied to Expanded Polypropylene and Expanded Polystyrene foams, predict their compressive stress responses. By using SHAP values and Partial Dependence Plots, the study elucidates the models’ decision-making processes. It focuses on three main features for both materials: density, loading rate, and strain, with an additional feature concerning loading and unloading for Expanded Polystyrene foam. The findings highlight that increased density and loading rate are closely correlated with higher compressive responses, and strain emerges as the most influential factor for the response of both materials. Partial Dependence Plots reveal a linear relationship with density, whereas other variables demonstrate non-linear relationships. These results validate the use of neural networks in analyzing material behavior, showing that the models’ outputs are in line with empirical observations. In conclusion, as presented, the integration of interpretability tools with neural network models offers a robust method for material response analysis, contributing to a deeper understanding of material science.

View
No Thumbnail Available
Publication

A neural networks metamodeling approach to address part distortion in aircraft aluminum structures

2021 , Rodríguez-Sánchez, Alejandro E.

View
No Thumbnail Available
Publication

Modeling of compressive stress in AlSi10Mg alloys using feed-forward neural networks

2024 , Rodríguez-Sánchez, Alejandro E. , Acevedo, Mario

Abstract This study addresses the challenge of modeling compressive stress in AlSi10Mg composites by introducing a method that employs feedforward artificial neural networks (ANNs) and their interpretability, which helps to simulate and analyze material behavior under various conditions. The main objective is to develop a predictive ANN model that can effectively simulate material responses under several factors, incorporating diverse testing parameters and material specifications related with its synthesis. An optimized ANN model, featuring eleven neurons in its hidden layer, was used and demonstrated high predictive accuracy, achieving R 2 values exceeding 0.94. Additionally, a SHAP interpretability analysis was conducted to assess the influence of key factors such as strain and material conditions on the stress response. The results highlight the significant role of material synthesis processes, compared to the strain rate, in the stress response. In conclusion, this method presents a comprehensive tool for studying complex stress behaviors in AlSi10Mg-based composites , offering insights that could guide future material development and research.

View