Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 9
Encontrada(s) 1 página(s)

UCrea Repositorio Abierto de la Universidad de Cantabria
Publicación Artículo científico (JournalArticle)

Enhancing stress measurements accuracy control in the construction of long-span bridges

  • Gaute Alonso, Álvaro
  • García Sánchez, David
  • Ramos Gutiérrez, Óscar Ramón|||0000-0002-9800-2375
  • Ntertimanis, Vasileios
This paper introduces new contributions for construction procedures designed to enhance the robustness and precision of stress control in active anchorage and short presetressing units for long span bridges, particularly addressing potential technical risks. The primary focus is on optimizing stress management for bridge stays, suspension cables, and short prestressing units by emphasizing a unifed parameter: stress. The contributions of this research encompass (1) the introduction of advanced load cells for stress control in active anchorages and (2) the implementation of a novel synchronized multi-strain gage load cell network for short prestressing units, crucial in situations where prestressing losses can attain signifcant magnitudes. To validate these advancements, the authors present (3) a practical experience and results obtained from applying these methodologies in monitoring the structural response during the construction of the Tajo Bridge using the cable-stayed cantilever technique., This work has received funding from the Horizon Europe research and innovation program un-der the grant agreement 101103698 (LIAISON project).
UCrea Repositorio Abierto de la Universidad de Cantabria
Publicación Artículo científico (JournalArticle)

Enhancing pavement crack segmentation via semantic diffusion synthesis model for strategic road assessment

  • Cano Ortiz, Saúl|||0000-0003-1383-180X
  • Sainz Ortiz, Eugenio
  • Lloret Iglesias, Lara
  • Martínez Ruiz del Árbol, Pablo|||0000-0002-7737-5121
  • Castro Fresno, Daniel|||0000-0001-5658-3901
Computer-aided deep learning has significantly advanced road crack segmentation. However, supervised models face challenges due to limited annotated images. There is also a lack of emphasis on deriving pavement condition indices from predicted masks. This article introduces a novel semantic diffusion synthesis model that creates synthetic crack images from segmentation masks. The model is optimized in terms of architectural complexity, noise schedules, and condition scaling. The optimal architecture outperforms state-of-the-art semantic synthesis models across multiple benchmark datasets, demonstrating superior image quality assessment metrics. The synthetic frames augment these datasets, resulting in segmentation models with significantly improved efficiency. This approach enhances results without extensive data collection or annotation, addressing a key challenge in engineering. Finally, a refined pavement condition index has been developed for automated end-to-end defect detection systems, promoting more effective maintenance planning., This work has been co-financed by the Ministry of Science and Innovation (ES) through the State Plan for Scientific and Technical Research and Innovation 2021-23 under the project MAPSIA [TED2021-129749B–I00]. Also, by the Horizon Europe Research and Innovation Framework program of the European Union under the project LIAISON [101103698].
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Enhancing pavement crack segmentation via semantic diffusion synthesis model for strategic road assessment

  • Cano Ortiz, Saúl
  • Sainz-Ortiz, Eugenio
  • Lloret Iglesias, Lara
  • Martínez Ruiz del Arbol, P.
  • Castro-Fresno, Daniel
Computer-aided deep learning has significantly advanced road crack segmentation. However, supervised models face challenges due to limited annotated images. There is also a lack of emphasis on deriving pavement condition indices from predicted masks. This article introduces a novel semantic diffusion synthesis model that creates synthetic crack images from segmentation masks. The model is optimized in terms of architectural complexity, noise schedules, and condition scaling. The optimal architecture outperforms state-of-the-art semantic synthesis models across multiple benchmark datasets, demonstrating superior image quality assessment metrics. The synthetic frames augment these datasets, resulting in segmentation models with significantly improved efficiency. This approach enhances results without extensive data collection or annotation, addressing a key challenge in engineering. Finally, a refined pavement condition index has been developed for automated end-to-end defect detection systems, promoting more effective maintenance planning., This work has been co-financed by the Ministry of Science and Innovation (ES) through the State Plan for Scientific and Technical Research and Innovation 2021-23 under the project MAPSIA [TED2021-129749B–I00]. Also, by the Horizon Europe Research and Innovation Framework program of the European Union under the project LIAISON [101103698]., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Artículo científico (JournalArticle)

Leveraging a deep learning generative model to enhance recognition of minor asphalt defects

  • Cano Ortiz, Saúl
  • Sainz-Ortiz, Eugenio
  • Lloret Iglesias, Lara
  • Martínez Ruiz del Arbol, P.
  • Castro-Fresno, Daniel
Deep learning-based computer vision systems have become powerful tools for automated and cost-effective pavement distress detection, essential for efficient road maintenance. Current methods focus primarily on developing supervised learning architectures, which are limited by the scarcity of annotated image datasets. The use of data augmentation with synthetic images created by generative models to improve these supervised systems is not widely explored. The few studies that do focus on generative architectures are mostly non-conditional, requiring extra labeling, and typically address only road crack defects while aiming to improve classification models rather than object detection. This study introduces AsphaltGAN, a novel class-conditional Generative Adversarial Network with attention mechanisms, designed to augment datasets with various rare road defects to enhance object detection. An in-depth analysis evaluates the impact of different loss functions and hyperparameter tuning. The optimized AsphaltGAN outperforms state-of-the-art generative architectures on public datasets. Additionally, a new workflow is proposed to improve object detection models using synthetic road images. The augmented datasets significantly improve the object detection metrics of You Only Look Once version 8 by 33.0 % , 3.8 %, 46.3 %, and 51.8 % on the Road Damage Detection 2022 dataset, Crack Dataset, Asphalt Pavement Detection Dataset, and Crack Surface Dataset, respectively., This work has been co-financed by the Ministry of Science and Innovation (ES) through the State Plan for Scientific and Technical Research and Innovation 2021-23 under the project MAPSIA [TED2021-129749B-I00]. Also, by the Horizon Europe Research and Innovation Framework program of the European Union under the project LIAISON [101103698]., Peer reviewed
DIGITAL.CSIC. Repositorio Institucional del CSIC
Publicación Tesis doctoral (DoctoralThesis)

Mapsia. Automatic pavement distress detection using artificial intelligence-based algorithms, Mapsia. Monitorización automatizada de patologías superficiales en pavimientos flexibles mediante algoritmos basados en inteligencia artificial

  • Cano Ortiz, Saúl
Programa de Doctorado en Ingeniería Civil., [EN] A deep learning-based computer vision system has been designed to detect, locate, and classify road defects. An image dataset with annotations of multiple distresses has been created. These pictures have been used to train object detection and semantic segmentation models. Due to class imbalance and the costly nature of labeling, multiple conditional generative models capable of creating synthetic images have been implemented to balance and increase the contribution of minority defects. Finally, a pavement condition index has been developed, which acts as an indicator of maintenance needs. All results have been included in a tool. This thesis proposes an innovative methodology, and a pavement management system powered by Artificial Intelligence, which will allow administrations and road maintenance companies to ensure low-cost, automatic, robust, and efficient maintenance., [ES] Se ha diseñado un sistema de visión artificial basado en aprendizaje profundo que detecta, localiza, y clasifica defectos. Se ha creado un banco de imágenes con anotaciones con múltiples defectos. Las imágenes se han utilizado para entrenar modelos de detección de objetos y segmentación semántica. Debido al desbalanceo de clases y al costoso etiquetado, se han implementado múltiples modelos generativos condicionales capaces de crear imágenes sintéticas para balancear e incrementar la contribución de defectos minoritarios. Por último, se ha confeccionado un índice de condición del pavimento que actúa como indicador de necesidad de mantenimiento. Todos los resultados se han incluido en una herramienta. Esta tesis propone una metodología innovadora y un sistema de gestión de pavimentos potenciado por Inteligencia Artificial, que permitirá garantizar un mantenimiento de bajo coste, automático, robusto, y eficiente, a las administraciones y empresas de conservación de carreteras., The accomplishment of this thesis has been possible thanks to the MAPSIA project [TED2021-129749B-I00], co-financed by the Ministry of Science and Innovation (ES) and the European Union (NextGenerationEU) through the State Plan for Scientific and Technical Research and Innovation 2021-23. Also, thanks to the Horizon Europe Research and Innovation Framework program of the European Union under the project LIAISON [101103698]. The international stay at RWTH University (Rheinisch-Westfaelische Technische Hochschule Aachen, Germany) was made possible through the generous support of the Erasmus+ PhD traineeship., Peer reviewed
UCrea Repositorio Abierto de la Universidad de Cantabria
Publicación Libro o Monografía (Book)

Neutral infrastructure governance

  • Pérez Hernando, María Antonia
  • García Sánchez, David
One of the activities that can most influence climate neutrality is the activity of executing projects in general and infrastructure projects in particular. Environmental concepts have long been included in all project work, but neutrality is something more and to approach it it is necessary to define a governance framework that includes this concept in detail throughout the life cycle of the project. A method is proposed to define the neutral governance framework, which is based on defining the project based on indicators of neutrality, zero emissions, circularity of materials, etc. And to show its validity, it is applied to the contracting of the construction of the A-67 motorway project, Capacity expansion, in Spain. Very good improvements have been made in infrastructure governance and contributing to climate neutrality., Special thanks to the European Commission, which has made it possible to develop the application of infrastructure governance based on risk indicators, through the RAGTIME, FORESEE and LIAISON projects.
UCrea Repositorio Abierto de la Universidad de Cantabria
Publicación Artículo científico (JournalArticle)

Leveraging a deep learning generative model to enhance recognition of minor asphalt defects

  • Cano Ortiz, Saúl|||0000-0003-1383-180X
  • Sainz Ortiz, Eugenio
  • Lloret Iglesias, Lara
  • Martínez Ruiz del Árbol, Pablo|||0000-0002-7737-5121
  • Castro Fresno, Daniel|||0000-0001-5658-3901
Deep learning-based computer vision systems have become powerful tools for automated and cost-effective pavement distress detection, essential for efficient road maintenance. Current methods focus primarily on developing supervised learning architectures, which are limited by the scarcity of annotated image datasets. The use of data augmentation with synthetic images created by generative models to improve these supervised systems is not widely explored. The few studies that do focus on generative architectures are mostly non-conditional, requiring extra labeling, and typically address only road crack defects while aiming to improve classification models rather than object detection. This study introduces AsphaltGAN, a novel class-conditional Generative Adversarial Network with attention mechanisms, designed to augment datasets with various rare road defects to enhance object detection. An in-depth analysis evaluates the impact of different loss functions and hyperparameter tuning. The optimized AsphaltGAN outperforms state-of-the-art generative architectures on public datasets. Additionally, a new workflow is proposed to improve object detection models using synthetic road images. The augmented datasets significantly improve the object detection metrics of You Only Look Once version 8 by 33.0%, 3.8%, 46.3%, and 51.8% on the Road Damage Detection 2022 dataset, Crack Dataset, Asphalt Pavement Detection Dataset, and Crack Surface Dataset, respectively., This work has been co-financed by the Ministry of Science and Innovation (ES) through the State Plan for Scientific and Technical Research and Innovation 2021-23 under the project MAPSIA [TED2021-129749B-I00]. Also, by the Horizon Europe Research and Innovation Framework program of the European Union under the project LIAISON [101103698].
UCrea Repositorio Abierto de la Universidad de Cantabria
Publicación Tesis doctoral (DoctoralThesis)

Mapsia : monitorización automatizada de patologías superficiales en pavimientos flexibles mediante algoritmos basados en inteligencia artificial, Mapsia : automatic pavement distress detection using artificial intelligence-based algorithms

  • Cano Ortiz, Saúl|||0000-0003-1383-180X
Se ha diseñado un sistema de visión artificial basado en aprendizaje profundo que detecta, localiza, y clasifica defectos. Se ha creado un banco de imágenes con anotaciones con múltiples defectos. Las imágenes se han utilizado para entrenar modelos de detección de objetos y segmentación semántica. Debido al desbalanceo de clases y al costoso etiquetado, se han implementado múltiples modelos generativos condicionales capaces de crear imágenes sintéticas para balancear e incrementar la contribución de defectos minoritarios. Por último, se ha confeccionado un índice de condición del pavimento que actúa como indicador de necesidad de mantenimiento. Todos los resultados se han incluido en una herramienta. Esta tesis propone una metodología innovadora y un sistema de gestión de pavimentos potenciado por Inteligencia Artificial, que permitirá garantizar un mantenimiento de bajo coste, automático, robusto, y eficiente, a las administraciones y empresas de conservación de carreteras., A deep learning-based computer vision system has been designed to detect, locate, and classify road defects. An image dataset with annotations of multiple distresses has been created. These pictures have been used to train object detection and semantic segmentation models. Due to class imbalance and the costly nature of labeling, multiple conditional generative models capable of creating synthetic images have been implemented to balance and increase the contribution of minority defects. Finally, a pavement condition index has been developed, which acts as an indicator of maintenance needs. All results have been included in a tool. This thesis proposes an innovative methodology, and a pavement management system powered by Artificial Intelligence, which will allow administrations and road maintenance companies to ensure low-cost, automatic, robust, and efficient maintenance., The accomplishment of this thesis has been possible thanks to the MAPSIA project [TED2021-129749B-I00], co-financed by the Ministry of Science and Innovation (ES) and the European Union (NextGenerationEU) through the State Plan for Scientific and Technical Research and Innovation 2021-23. Also, thanks to the Horizon Europe Research and Innova tion Framework program of the European Union under the project LIAISON [101103698]. The international stay at RWTH University (Rheinisch-Westfaelische Technische Hochschule Aachen, Germany) was made possible through the generous support of the Erasmus+ PhD traineeship.
UCrea Repositorio Abierto de la Universidad de Cantabria
Publicación Libro o Monografía (Book)

Metodología para la definición y cálculo de indicadores de sostenibilidad y circularidad e incorporación en los procesos de licitación de infraestructuras de transporte terrestre

  • Mateo Sanz, Beatriz
  • García Sánchez, David
  • Pérez Hernando, María Antonia
  • Romero Díaz, Inmaculada
  • Ortega Villarm Andrés
Los procesos de licitación constituyen una herramienta eficaz para promover el avance hacia prácticas más sostenibles y circulares. Las administraciones de infraestructuras de transporte, como grandes organismos públicos, pueden impulsar y facilitar un desarrollo más sostenible a través de sus procedimientos de contratación. La contratación sostenible tiene como finalidad lograr un equilibrio adecuado entre los aspectos económicos, sociales y ambientales en todas las etapas del proceso de contratación. El proyecto Horizon Europe LIAISON (GA nº 101103698) tiene como objetivo proporcionar conocimientos y soluciones técnicas para reducir las emisiones derivadas de la infraestructura de transporte. El proyecto describe los elementos que deben considerarse en un proceso real de licitación según el ciclo de vida de la infraestructura: licitación de la redacción del proyecto, de la construcción de la obra y de la asistencia técnica, incorporando en el proceso indicadores de sostenibilidad y circularidad. Con este fin, dentro del proyecto LIAISON se ha desarrollado una metodología para la definición y cálculo de los indicadores de sostenibilidad y circularidad que pueden incorporarse en el proceso de licitación, utilizando los datos de un proyecto real de ampliación de una autovía española. Los indicadores se han clasificado en cinco categorías: riesgo, ambiental, de circularidad, social y de coste, y se determinan por unidad de obra, teniendo en cuenta la mano de obra, la maquinaria y los materiales. El cálculo se realiza para todas las unidades de obra con el fin de obtener el valor final de los indicadores correspondientes al proyecto. Esta metodología se está incorporando en los documentos de licitación de un segundo proyecto que consiste en la reposición de la capa de rodadura de un tramo de prueba de una carretera nacional española, utilizándose una mezcla con un bioligante experimental, que se está desarrollando dentro del proyecto LIAISON como una de las soluciones circulares para la infraestructura del transporte. El proceso de licitación cuenta con tres tipos de contratos: Contrato de redacción del proyecto, Contrato de ejecución de las obras y Contrato de asistencia técnica. El proyecto incorporará indicadores de sostenibilidad y circularidad para la elaboración de la memoria, el presupuesto y el pliego de prescripciones técnicas que se deberán cumplir en el contrato de ejecución de obras, con el fin de utilizarlos en la evaluación de las ofertas. El cumplimiento de los indicadores durante la ejecución de la obra se controlará a través del contrato de asistencia técnica., Proyecto Horizon Europe LIAISON "Lowering transport environmental impact along the whole life cycle of the future transport infrastructure" Grant agreement ID: 101103698