Ingeniería Civilhttps://hdl.handle.net/20.500.12724/205712026-05-13T08:37:56Z2026-05-13T08:37:56ZFlexural behavior of steel and polypropylene fiber-reinforced concrete beams with low longitudinal reinforcement ratiosLa Torre Esquivel, DarwinDe Andrade Silva, FlávioDel Savio, Alexandre Almeidahttps://hdl.handle.net/20.500.12724/244412026-04-17T00:15:00Z2025-01-01T00:00:00ZFlexural behavior of steel and polypropylene fiber-reinforced concrete beams with low longitudinal reinforcement ratios
La Torre Esquivel, Darwin; De Andrade Silva, Flávio; Del Savio, Alexandre Almeida
The use of fiber-reinforced concrete in structural applications is currently under development. It has been proven that high steel fibers and low reinforcing steel lower the structure's ductility since localized cracks are generated. It is hypothesized that this can be solved by using less rigid fibers such as polypropylene. In this research, a comparative study of the influence of synthetic and metallic fibers in normal resistance reinforced concrete with a low reinforcement ratio is carried out. This study focuses on the structural behavior and development of cracking at the service limit state (ELS) and the ultimate limit state (ELU). To this end, an extensive experimental campaign was conducted, comprising, first, the characterization of the material and, second, the testing of reinforced concrete beams. The variables used are (1) the material of the fibers: polypropylene (PP) and steel (ST), (2) the volume of fibers: 0.33 %, 0.66 % and 1.00 %, and (3) the size of the beams: 1.6 and 3.2 m long. The results show that concrete with 1 % steel fibers exhibited higher post-cracking stiffness than with PP fibers, increasing by 104 % and 71 % in 4.00 m beams, respectively, due to its greater residual strength. A higher fiber volume (1 %) increased the yield moment by up to 50 % and the maximum load by 22 %-25 %. However, it reduced ductility, especially with 1 % steel fibers, where it decreased by up to 63 % in 1.60 m beams due to crack localization. In 4.00 m beams, fiber-reinforced concrete showed better flexural performance, with similar maximum load increases as in 1.60 m beams, but with a smaller ductility reduction (24 % with steel fibers and 11 % with PP fibers), indicating that the greater span promotes better strain redistribution.
2025-01-01T00:00:00ZDataset for training neural networks in concrete crack detection: laboratory-classified beam and column imagesDel Savio, Alexandre AlmeidaLuna Torres, Ana FelícitaCárdenas Salas, Daniel EnriqueVergara Olivera, MónicaUrday Ibarra, Gianella Taniahttps://hdl.handle.net/20.500.12724/244472026-04-17T00:15:00Z2025-01-01T00:00:00ZDataset for training neural networks in concrete crack detection: laboratory-classified beam and column images
Del Savio, Alexandre Almeida; Luna Torres, Ana Felícita; Cárdenas Salas, Daniel Enrique; Vergara Olivera, Mónica; Urday Ibarra, Gianella Tania
The construction industry is increasingly incorporating artificial intelligence into processes for the efficiency and accuracy of structural analysis and monitoring. However, obtaining high-quality datasets to train algorithms for detecting concrete cracks in structural components remains challenging, as such cracks normally develop over an extended period under real-world conditions. We introduce a curated dataset of 1,132 manually classified images of concrete cracks in beams and columns. These images were captured in a controlled laboratory environment using a static IP camera and annotated using the LabelImg tool. The dataset includes five object classes representing distinct cracks and failures in beams and columns and corresponding.txt files containing classification and coordinates data. This dataset is designed to facilitate developing and validating of neural network-based computer vision models for automated crack detection. It is a very useful resource for researchers in structural engineering, which enables further developments in automated structural health monitoring and contributes to the overall use of AI in the construction industry.
2025-01-01T00:00:00ZDevelopment of antioxidant films based on anthocyanin microcapsules extracted from purple corn cob and incorporated into a chitosan matrixBustamante Bernedo, Milagros SofíaGutiérrez Pineda, EduartHuamán-Castilla, Nils LeanderSolis, José LuisGómez León, Mónica MarcelaMontoya Matos, Israel RogerYácono Llanos, Juan CarlosPacheco-Salazar, David G.https://hdl.handle.net/20.500.12724/232782026-04-17T00:15:00Z2025-01-01T00:00:00ZDevelopment of antioxidant films based on anthocyanin microcapsules extracted from purple corn cob and incorporated into a chitosan matrix
Bustamante Bernedo, Milagros Sofía; Gutiérrez Pineda, Eduart; Huamán-Castilla, Nils Leander; Solis, José Luis; Gómez León, Mónica Marcela; Montoya Matos, Israel Roger; Yácono Llanos, Juan Carlos; Pacheco-Salazar, David G.
Biodegradable food packaging films were prepared from chitosan incorporated with microencapsulated anthocyanins powder (MAP) that was extracted from purple corn cob using the casting method. Anthocyanins extracts were microencapsulated with maltodextrin, gum arabic, and soy protein using a spray-drying method. The film based on chitosan and MAP (CHt@MAP) was prepared through citric acid cross-linking and plasticization with glycerol. The structural analysis of the CHt@MAP film revealed a semicrystalline structure by X-ray diffraction. The interactions were mainly via electrostatic and hydrogen bonding, as confirmed by Fourier-transform infrared. Based on scanning electron microscopy, the morphology of the films revealed evidence of the presence of MAP on the surface and cross-section. The microcapsules inside the films produced an increase in thickness (0.18–0.21 mm), lower water vapor permeability (12.4–8.5 × 10−10 g m−1s−1Pa−1), and reduced elongation at break (217 % to 165 %), as well as tensile strength (1.3 to 0.45 MPa) compared to the chitosan film. Furthermore, the antioxidant activity of CHt@MAP film was high, with a radical scavenging activity of 56 %. It also exhibited a strong barrier to UV and visible light. The results indicate that the CHt@MAP film preserves the shelf life of blueberries at room temperature and could be used as an active packaging film for foods.
2025-01-01T00:00:00ZLand-Cover Semantic Segmentation for Very-High-Resolution Remote Sensing Imagery Using Deep Transfer Learning and Active Contour LossChicchon, MiguelLeón Trujillo, Francisco JamesSipiran, IvánMadrid Argomedo, Manuel Ricardohttps://hdl.handle.net/20.500.12724/232112026-04-17T00:15:00Z2025-01-01T00:00:00ZLand-Cover Semantic Segmentation for Very-High-Resolution Remote Sensing Imagery Using Deep Transfer Learning and Active Contour Loss
Chicchon, Miguel; León Trujillo, Francisco James; Sipiran, Iván; Madrid Argomedo, Manuel Ricardo
An accurate land-cover segmentation of very-high-resolution aerial images is essential for a wide range of applications, including urban planning and natural resource management. However, the automation of this process remains a challenge owing to the complexity of images, variability in land surface features, and noise. In this study, a method for training convolutional neural networks and transformers to perform land-cover segmentation on very-high-resolution aerial images in a regional context was proposed. We assessed the U-Net-scSE, FT-U-NetFormer, and DC-Swin architectures, incorporating transfer learning and active contour loss functions to improve performance on semantic segmentation tasks. Our experiments conducted using the OpenEarthMap dataset, which includes images from 44 countries, demonstrate the superior performance of U-Net-scSE models with the EfficientNet-V2-XL and MiT-B4 encoders, achieving an mIoU of over 0.80 on a test dataset of urban and rural images from Peru.
2025-01-01T00:00:00Z