Rodríguez-Sánchez, Alejandro E.

Main Affiliation
Preferred name
Rodríguez-Sánchez, Alejandro E.
Official Name
Rodríguez-Sánchez, Alejandro Esteban
ORCID
0000-0003-3397-5261
Scopus Author ID
57202719691

Settings

Now showing 1 - 10 of 41
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Deep Learning Automated Measurements of Expanded Polystyrene Beads Size Using Low‐Resolution Micrography
    (Wiley, 2025-07-04)
    Rodríguez-Sánchez, Alejandro E.  
    ;
    Héctor Plascencia‐Mora
    <jats:title>ABSTRACT</jats:title><jats:p>The analysis of microscopic characteristics of closed‐cell polymeric foams, particularly bead size, is relevant for understanding properties such as thermal insulation, energy absorption, and compressive structural strength of these materials. This study presents an automated method based on Deep Learning models to measure the bead size of Expanded Polystyrene foams in low‐resolution micrographs. The results of this approach were compared with manual measurements at two expanded polystyrene foam densities: 8.5 and 24 kg/m<jats:sup>3</jats:sup>. Hypothesis tests, including Student's <jats:italic>t</jats:italic>‐test, Levene's test, and Mann–Whitney <jats:italic>U</jats:italic> test, were conducted and showed no significant differences between manual and automatic measurements. Student's <jats:italic>t</jats:italic>‐test and Levene's test indicated that both methods have comparable means and variances, while the Two One‐Sided Test confirmed that they were equivalent for bead size measurement. Additionally, the Mann–Whitney <jats:italic>U</jats:italic> test revealed no differences in medians, and Bland–Altman plot analyses demonstrated no systematic bias between the methods. Taken together, these results suggest that the proposed Deep Learning‐based method is a reliable and precise substitute for the manual method in measuring the bead size of expanded polystyrene, making it suitable for practical use in the bead microstructural analysis of expanded polystyrene material.</jats:p>
      36
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Uncertainty quantification of compressive stress response in expanded polystyrene foams using evidential neural networks
    (SAGE Publications, 2026-01-09)
    Rodríguez-Sánchez, Alejandro E.  
    <jats:p>This study investigates the application of Deep Evidential Regression in shallow feed-forward neural networks to model and quantify the compressive stress response of expanded polystyrene foam. This foam material, widely utilized for impact protection and packaging, exhibits distinct mechanical behavior characterized by elasticity, plateau, and densification stages during compressive loading. This research adopts a data-driven approach, leveraging artificial neural networks enhanced with evidential learning to predict the distribution of stress responses, thereby addressing both aleatoric and epistemic uncertainties. The methodology involves organizing stress-strain data into training, validation, and test sets, adding noise to simulate real-world conditions, and training models with evidential layers. Results demonstrate that the proposed models maintain high predictive accuracy, with coefficients of determination exceeding 0.90 for noisy test data and above 0.99 for noise-free data. The evidential regression models also provide robust uncertainty quantification, essential for applications where data quality varies. This study’s findings highlight the efficiency and effectiveness of Deep Evidential Regression in enhancing the reliability of stress-strain predictions for EPS foam, offering significant potential for broader application to similar foam materials.</jats:p>
      31Scopus© Citations 1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    La posibilidad de explicación científica a partir de modelos basados en redes neuronales artificiales
    (2024)
    Rodríguez-Sánchez, Alejandro E.  
    <jats:p>En inteligencia artificial, las redes neuronales artificiales son modelos muy precisos en tareas como la clasificación y la regresión en el estudio de fenómenos naturales, pero se consideran “cajas negras” porque no permiten explicación directa de aquello que abordan. Este trabajo revisa la posibilidad de explicación científica a partir de estos modelos y concluye que se requieren de otros esfuerzos para entender su funcionamiento interno. Esto plantea retos para acceder a la explicación científica a través de su uso, pues la naturaleza de las redes neuronales artificiales dificulta a primera instancia la comprensión científica que puede extraerse de estas.</jats:p>
      13
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Classification of Rugosity in Plasmonic Metallic Thin Films Using Deep Learning for Speckle Images
    (2024)
    C.N. Magaña-Barocio
    ;
    Marlen Gonzalez
    ;
    M.C. Peña-Gomar
    ;
    M. Torres.Cisneros
    ;
    Rodríguez-Sánchez, Alejandro E.  
    <jats:p>In this work, we report, for the first time, to the best of our knowledge, the classification of metallic samples with different roughness values. As a reference, the <jats:italic>R<jats:sub>a</jats:sub></jats:italic> and <jats:italic>R<jats:sub>q</jats:sub></jats:italic> values were obtained using a Mitutoyo roughness meter. About 2,000 Speckle images were obtained for each sample. They were processed and used as inputting neural networks such as ResNet50 and EfficientNet. We obtained 99.63 % accuracy in classifying the samples with the ResNet50 model and 99.48 % accuracy for the EfficientNet model. These accuracies can be compared with the 99.926 % and 99.932 % values obtained for aluminum and steel surfaces in a similar work that used an optics system, image processing, and a CNN.</jats:p>
      29
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
      11
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Neural network-driven interpretability analysis for evaluating compressive stress in polymer foams
    (2024)
    Rodríguez-Sánchez, Alejandro E.  
    ;
    Plascencia Mora, Héctor
    ;
    Acevedo, Mario  
    <jats:p> 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. </jats:p>
    Scopus© Citations 2  18
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
      25
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
      22Scopus© Citations 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Part distortion optimization of aluminum-based aircraft structures using finite element modeling and artificial neural networks
    (CIRP Journal of Manufacturing Science and Technology, 2020)
    Rodríguez-Sánchez, Alejandro E.  
    ;
    Elias Ledesma-orozco
    ;
    Sergio Ledesma
    Currently, in the aircraft design, thinner structures are required to reduce weight, which in turn presents challenges for the manufacturing of parts and components. One of the identified problems in manufacturing is the machining distortion phenomenon, which causes the generation of scrap during the production of mechanical and structural components. This study presents the use of a finite element procedure, artificial neural network models, and the simulated annealing algorithm to optimize machining distortion phenomena in aluminum-based structures. A finite element procedure that simulates machining distortion by considering residual stresses and machining locations is used to generate training and validation data sets for the construction of an artificial neural network model. Once the performance of the artificial neural network is validated, simulated annealing is used in combination with the neural network model to find the optimum parameters of the machining locations and the residual stresses conditions that reduce distortion phenomena caused by machining. A case study of a specimen that has complex geometrical features, such as those that present in the design of aircraft structures, was used for the validation of the models. The results show that the proposed approach predicts the machining distortion of the specimen obtaining errors below 3% regarding experimental observations. Numerical results not only predict maximum distortions, but the evidence shows that the finite element can estimate the distribution of the distortion presented experimentally in the case study. Additionally, the optimization results helped to reduce the distortions 80% or more for high levels of deformation. Therefore, the proposed method in this study helps in the prediction and optimization of machining distortion of aluminum-based structures.
      7Scopus© Citations 30