Pasar al contenido principal

Resultados relacionados

Resultados totales (Incluyendo duplicados): 16
Encontrada(s) 1 página(s)

Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

A top-down approach for a multi-scale identification of risk areas in infrastructures: particularization in a case study on road safety

  • Rúa Fernández, Erik
  • Comesaña Cebral, Lino Jose
  • Arias Sánchez, Pedro
  • Martínez Sánchez, Joaquín
Introduction: Transport infrastructures have an important function in society and the development of a country. In Spain, the most used modes of traveler transport are road and rail, far ahead of other means of transport such as air or maritime transport. Both rail and road infrastructures can be affected by numerous hazards, endangering their performance and the safety of users. This study proposes a methodology with a multiscale top-down approach to identify the areas affected by fire, landslide, and safety in road and rail infrastructures in Galicia (Northwest Spain)., Methodology: The methodology is developed in three steps, coinciding with the three scales considered in this work: network-, system-, and object-level. In the first step, risk areas are identified and prioritized, resulting in the most critical safety risk in a motorway section. This area defines a study scenario composed of a location (A-55 motorway) and the associated risk (road safety). In the second step, the road safety factors within this scenario are selected, hierarchized, and weighted using a combination of Multi-Criteria Decision-Making methods including the Analytical Hierarchy Process and the Best–Worst Method. Finally, a risk map is generated based on the weighting of infrastructure-related safety factors and compared to real historical accident data for validation. The methodology is based on road and risk assessment standards and only information in the public domain is used., Results: Results show that only 3 segments out of 153 were classified incorrectly, which supports a probability higher than 95% of agreement with real data (at 5% significance level). In a conclusion, the overall methodology exhibits a high potential for hazard prevention and road-safety enhancement., Agencia Estatal de Investigación | Ref. PID2019-108816RB-I00, Agencia Estatal de Investigación | Ref. PRE2020-096222
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Reliability-based structural assessment of historical masonry arch bridges: The case study of Cernadela bridge

  • Bouzas Rodriguez, Óscar
  • Conde Carnero, Borja
  • Campos e Matos, Jose
  • Solla Carracelas, Maria Mercedes
  • Cabaleiro Núñez, Manuel
Nowadays, several historical masonry arch bridges present a deficient state of conservation due to degradation processes induced by natural or human actions. Usually, these constructions have significant economic, cultural, and heritage value. Therefore, they shall be thoroughly assessed to verify their structural integrity and safety condition. For this purpose, reliability-based structural assessments are typically performed. However, the associated outcomes (i.e., reliability index and probability of failure) highly rely on the accuracy of the structural parameters uncertainty quantification. This work presents a study regarding the influence of the scattering of the arches' thickness dimensions in the load-carrying capacity assessment of the Cernadela Bridge, a historical stone bridge located in Galicia, Spain. The study first involved a comprehensive experimental campaign to characterize the outer and inner bridge geometry through geomatic techniques, i.e., terrestrial laser scanning and ground penetrating radar. Subsequently, a limit analysis model was developed, considering only the arches' outer (visible) data. From this initial structural assessment, a reliability index of 2.38 was obtained. The influence of the uncertain structural parameters, both geometric features and material properties, in the collapse load was investigated through a global variance-based sensitivity analysis (i.e., Sobol' indices) complemented by a surrogate modeling strategy based on the Kriging approach. Finally, the measured inner geometry of the arches was introduced in the computational model through Bayesian inference procedures. Thus, two new structural assessments were performed: first, by considering the updated distributions of all arches thicknesses, and second, by considering only the updated distributions of the non-influential ones. Reliability indexes of 1.51 and 2.33 were derived, thus highlighting the importance of a proper uncertainty quantification process and the relevance of the sensitivity analysis outcomes to identify the critical parameters on the bridge mechanical response., Ministerio de Ciencia e Innovación | Ref. TED2021-130497A-I00, Ministerio de Ciencia e Innovación | Ref. RYC2019-026604-I
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Instance and semantic segmentation of point clouds of large metallic truss bridges

  • Lamas Novoa, Daniel
  • Justo Dominguez, Andrés
  • Soilán Rodríguez, Mario
  • Cabaleiro Núñez, Manuel
  • Riveiro Rodríguez, Belén
Several methods have been developed for the semantic segmentation of reinforced concrete bridges, however, there is a gap for truss bridges. Therefore, in this study a state-of-the-art methodology for the instance and semantic segmentation of point clouds of truss bridges for modelling purposes is presented, which, to the best of the authors' knowledge, is the first such methodology. This algorithm segments each truss element and classifies them as a chord, diagonal, vertical post, interior lateral brace, bottom lateral brace, or strut. The algorithm consists of a sequence of methods, including principal component analysis or clustering, that analyse each point and its neighbours in the point cloud. Case studies show that by adjusting only six manually measured parameters, the algorithm can automatically segment a truss bridge point cloud., Agencia Estatal de Investigación | Ref. PID2021-124236OB-C3, Agencia Estatal de Investigación | Ref. RYC2021-033560-I, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Deterministic and probabilistic-based model updating of aging steel bridges

  • Barros Gonzalez, Brais
  • Conde Carnero, Borja
  • Cabaleiro Núñez, Manuel
  • Riveiro Rodríguez, Belén
Numerical modeling is a very useful tool in different fields of bridge engineering, such as load-carrying capacity assessment or structural health monitoring. Developing a reliable computational model that accurately represents the actual bridge mechanical behavior entails advanced FEM-based modeling complemented by a comprehensive experimental campaign that provides the necessary supporting information and allows validating simulation outcomes. This paper proposes a unified approach aimed at the experimental characterization and FE model updating of aging steel bridges. It first involves the realization of an extensive experimental campaign aimed at the bridge's geometrical, material, and dynamic behavior characterization. Then, a model calibration framework is developed, where deterministic (optimization) and probabilistic (Bayesian inference) approaches are employed, and techniques such as global variance-based sensitivity analysis and Kriging-based surrogate modeling are further implemented in order to enhance the identification process and reduce the overall computational burden. The methodology has been validated in a historical riveted steel bridge in O Barqueiro, north of Galicia, Spain. The results show a good agreement in the identified model parameter values and a noticeable correlation between numerical and experimental modal properties, with an average relative error in frequencies of 0.34% and 0.44% for the deterministic and probabilistic approaches and an average MAC (Modal Assurance Criterion) ratio of 0.96., Fundación BBVA, Agencia Estatal de Investigación | Ref. PRE2019-087331, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Design and testing of a decision tree algorithm for early failure detection in steel truss bridges

  • Barros Gonzalez, Brais
  • Conde Carnero, Borja
  • Cabaleiro Núñez, Manuel
  • Riveiro Rodríguez, Belén
This paper develops a methodology for damage identification in steel truss bridges that uses vibration-based monitoring data and a model-based decision tree algorithm. The methodology resorts to a calibrated FE model with an optimization-based parameter identification procedure to simulate and analyze all the potential damages that might affect the structure. The effect of environmental conditions on the modal parameters is also accounted for, which is modeled as structure stiffness variations using the Young’s modulus and forecasted using a surrogate modeling strategy. The feasibility of the methodology is demonstrated on a full-scale bridge in Vilagarcía de Arousa, Spain. The underlying hypotheses used in the algorithm implementation were validated, and the error ponderation and selection bound employed to detect and identify damage were optimized. The results show an average success rate of 95.0% and an average false positive rate of 1.0% in identifying damage indicating its robustness to be extrapolated to other case studies., Agencia Estatal de Investigación | Ref. PRE2019-087331, Fundación BBVA, Universidade de Vigo/CISUG, Ministerio de Universidades | Ref. CAS21/00203
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Automated production of synthetic point clouds of truss bridges for semantic and instance segmentation using deep learning models

  • Lamas Novoa, Daniel
  • Justo Dominguez, Andrés
  • Soilán Rodríguez, Mario
  • Riveiro Rodríguez, Belén
The cost of obtaining large volumes of bridge data with technologies like laser scanners hinders the training of deep learning models. To address this, this paper introduces a new method for creating synthetic point clouds of truss bridges and demonstrates the effectiveness of a deep learning approach for semantic and instance segmentation of these point clouds. The method generates point clouds by specifying the dimensions and components of the bridge, resulting in high variability in the generated dataset. A deep learning model is trained using the generated point clouds, which is an adapted version of JSNet. The accuracy of the results surpasses previous heuristic methods. The proposed methodology has significant implications for the development of automated inspection and monitoring systems for truss bridges. Furthermore, the success of the deep learning approach suggests its potential for semantic and instance segmentation of complex point clouds beyond truss bridges., Agencia Estatal de Investigación | Ref. PID2021-124236OB-C33, Agencia Estatal de Investigación | Ref. RYC2021-033560-I, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Towards standardized guidelines in digital data acquisition for monitoring and maintenance of European transport infrastructures

  • Justo Dominguez, Andrés
  • Sánchez Rodríguez, Ana
  • Varela, María
  • Arias Sánchez, Pedro
The digital transformation of the architecture, engineering, and construction sector is associated with an enormous production of data. The appearance of new technologies is leading the way for more sustainable and interconnected infrastructures. Therefore, data analytics is crucial to know the current state of infrastructure and will help towards the efficient management of assets. The main issue is how to collect and exploit meaningful data throughout the lifecycle of infrastructure assets to further allow human experts and computers to make accurate diagnostics, predictions, and decisions. This contribution presents the insights gained in the course of IM‐SAFE project, showing the strategy followed to create guidelines for data collection to monitor and maintain critical assets in the infrastructure network (bridges and tunnels). It tackled a variety of surveying technologies, from destructive and non‐destructive, to chemical methods, among others. The results obtained will support the European Committee for Standardization (CEN) in the standards for monitoring and maintenance of bridges and tunnels, accelerating the adoption of new standards by public authorities and stakeholders in transport infrastructure., Universidade de Vigo | Ref. PREUVIGO‐21, Agencia Estatal de Investigación | Ref. FJC2020‐046370‐I, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Multi-objective optimization-based model calibration of masonry bridges

  • Barros Gonzalez, Brais
  • Conde Carnero, Borja
  • Cabaleiro Núñez, Manuel
  • Solla Carracelas, Maria Mercedes
  • Riveiro Rodríguez, Belén
Multi-objective optimization-based model calibration can be an intermediate solution between the computationally expensive probabilistic approaches and the single-objective optimization strategies that do not allow uncertainty quantification of the obtained solutions. This work addresses the multi-objective model calibration of two historic stone arch bridges using high-fidelity computational FE models. To implement the methodology, a five-step approach is proposed: experimental characterization through non-destructive testing techniques, non-parametric asbuilt geometric modeling, macro-finite element modeling, sensitivity analysis, and multiobjective optimization. The preferred solution among the Pareto front solutions is selected based on two different classical criteria, and the set of optimal solutions is further statistically analyzed to assess the validity of the identification process. The results show an average frequency error of 0.97 % and 0.70 % and an average MAC of 0.97 and 0.96 for each case study, respectively, thus highlighting the adequacy of the proposed methodology., Agencia Estatal de Investigación | Ref. PID2021-124236OB-C33, Agencia Estatal de Investigación | Ref. PRE2019-087331, Agencia Estatal de Investigación | Ref. RYC2019-026604-I, Xunta de Galicia | Ref. ED431F 2021/08, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

A novel fully removable walkway system with non-invasive anchors for structural health inspection and maintenance of historic steel structures

  • Cabaleiro Núñez, Manuel
  • Conde Carnero, Borja
  • González Gaya, Cristina
  • Barros Gonzalez, Brais
Historic steel structures are generally heritage constructions that must be preserved, where invasive operations such as welding or drilling cannot be performed. Any auxiliary structures installed on these constructions must be easily removable. In addition, historic steel structures such as riveted bridges are difficult to access, making it very difficult to take measurements using contact techniques or to perform structural health inspections. One of the most common needs is the installation of walkways for inspection and especially for maintenance and repair purposes. In this sense, clamp-based connections are a technique for fabricating dismountable systems that allow anchoring to existing structures without performing invasive operations such as welding or drilling. This study proposes, develops, simulates, and tests a novel non-invasive detachable anchorage system for the assembly of temporary walkways for inspecting and maintaining historic steel structures without additional scaffolding. In addition, a methodology is proposed for the easy and correct installation of the proposed system by combining it with LiDAR techniques. The developed system has been assembled and tested in laboratory tests and two real case studies., Agencia Estatal de Investigación | Ref. TED2021-130497A-I00, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Anticipating the collapse of urban infrastructure: a methodology based on Earth Observation and MT-InSAR

  • Rodriguez Antuñano, Ignacio
  • Martínez Sánchez, Joaquín
  • Cabaleiro Núñez, Manuel
  • Riveiro Rodríguez, Belén
Large-scale infrastructure monitoring and vulnerability assessment are crucial for the preservation and maintenance of built environments. To ensure the safety of urban infrastructure against natural and man-made disasters, constant monitoring is crucial. To do so, satellite Earth observation (EO) is being proposed, particularly radar-based imaging, because it allows large-scale constant monitoring since radar signals are not blocked by clouds and can be collected during both day and night. The proposed methodology for large-scale infrastructure monitoring and vulnerability assessment is based on MT-InSAR time series analysis. The homogeneity of the year-to-year displacement trend between each point and its surrounding points is evaluated to determine whether the area is a stable or vulnerable zone. To validate the methodology, four case studies of recently collapsed infrastructures are analyzed. The results indicate the potential of the proposed methodology for predicting and preventing structural collapses., Ministerio de Ciencia e Innovación | Ref. PID2021-124236OB-C33
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Model updating of in‐service bridges using multidisciplinary research ‐ case studies in Spain

  • Riveiro Rodríguez, Belén
  • Bouzas Rodriguez, Óscar
  • Barros Gonzalez, Brais
  • Conde Carnero, Borja
  • Cabaleiro Núñez, Manuel
  • Sánchez Rodríguez, Ana
  • Arias Sánchez, Pedro
This paper presents several experiences focused to create and update accurate numerical models of ageing bridges in Spain. The experimental campaigns included integration of various NDT technologies such as laser scanning, ultrasounds, etc., combined with vibration‐based methods such as Operational Modal Analysis. From these multi‐source data it was possible to create an accurate numerical model of each structure, which was lately subjected to a calibration using the actual dynamic response of the structure. Thus, the updated structural model presents the same behaviour as the real construction, offering a powerful tool to more accurately predict the safety level of the structure. On the other hand, structural assessments based on reliability analysis has been proved to improve the quality and accuracy of safety analysis due to the consideration of the possible deviations presented in the parameters of a structure. These works were compiled as case‐studies in Spain within IM‐SAFE project., Agencia Estatal de Investigación | Ref. PRE2019-087331
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

BIM methodology for cost analysis, sustainability, and management of steel structures with reconfigurable joints for industrial structures

  • Pereiro Matalobos, Javier
  • Cabaleiro Núñez, Manuel
  • Conde Carnero, Borja
  • Riveiro Rodríguez, Belén
One of the main objectives set for future factories, and for Industry 4.0, is to reduce the CO2 footprint of industrial plants and their buildings as much as possible. This objective must be compatible with economic savings, an essential requirement for investments in industrial production plants and their buildings. Industrial structures represent an important part of investments in industrial facilities and equipment. In order to achieve the objectives mentioned above, it is necessary to use fully reconfigurable and reusable structures. This work aims to propose and apply a methodology using BIM (Building Information Modelling) technology that allows for the analysis, control, and monitoring of economic profitability and sustainability ratios over time (for structures with reconfigurable joints compared to those with welded joints). The proposed methodology was applied to three different case studies, where various reconfigurations of the structures were done over time, obtaining the structure’s economic profitability with reconfigurable joints from the third reconfiguration and environmental sustainability from the second reconfiguration. The results demonstrate that the BIM methodology presented in this work and applied to industrial structures is a fully adequate tool for analyzing the structures’ costs and sustainability and controlling for monitoring these structures throughout the different reconfigurations., Agencia Estatal de Investigación | Ref. TED2021-130497A-I00, Universidade de Vigo/CISUG
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Combined use of GPR and Other NDTs for road pavement assessment: an overview

  • Elseicy , Ahmed Mossad Ibrahim
  • Alonso Díaz, Alex
  • Solla Carracelas, Maria Mercedes
  • Rasol, Mezgeen
  • Santos Assunçao, Sonia
Roads are the main transportation system in any country and, therefore, must be maintained in good physical condition to provide a safe and seamless flow to transport people and goods. However, road pavements are subjected to various defects because of construction errors, aging, environmental conditions, changing traffic load, and poor maintenance. Regular inspections are therefore recommended to ensure serviceability and minimize maintenance costs. Ground-penetrating radar (GPR) is a non-destructive testing (NDT) technique widely used to inspect the subsurface condition of road pavements. Furthermore, the integral use of NDTs has received more attention in recent years since it provides a more comprehensive and reliable assessment of the road network. Accordingly, GPR has been integrated with complementary NDTs to extend its capabilities and to detect potential pavement surface and subsurface distresses and features. In this paper, the non-destructive methods commonly combined with GPR to monitor both flexible and rigid pavements are briefly described. In addition, published work combining GPR with other NDT methods is reviewed, emphasizing the main findings and limitations of the most practical combination methods. Further, challenges, trends, and future perspectives of the reviewed combination works are highlighted, including the use of intelligent data analysis., Xunta de Galicia | Ref. ED431F 2021/08, Ministerio de Ciencia e Innovación | Ref. RYC2019–026604-I
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

Gaussian Copula-based Bayesian network approach for characterizing spatial variability in aging steel bridges

Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Artículo científico (JournalArticle)

A review of GPR application on transport infrastructures: troubleshooting and best practices

  • Solla Carracelas, Maria Mercedes
  • Pérez Gracia, Vega
  • Fontul, Simona
The non-destructive testing and diagnosis of transport infrastructures is essential because of the need to protect these facilities for mobility, and for economic and social development. The effective and timely assessment of structural health conditions becomes crucial in order to assure the safety of the transportation system and time saver protocols, as well as to reduce excessive repair and maintenance costs. Ground penetrating radar (GPR) is one of the most recommended non-destructive methods for routine subsurface inspections. This paper focuses on the on-site use of GPR applied to transport infrastructures, namely pavements, railways, retaining walls, bridges and tunnels. The methodologies, advantages and disadvantages, along with up-to-date research results on GPR in infrastructure inspection are presented herein. Hence, through the review of the published literature, the potential of using GPR is demonstrated, while the main limitations of the method are discussed and some practical recommendations are made., Ministerio de Ciencia e Innovación | Ref. RYC2019–026604–I
Investigo. Repositorio Institucional de la Universidade de Vigo
Publicación Tesis doctoral (DoctoralThesis)

Deep learning-based interpretation of ground penetrating radar data for pavement condition monitoring, Interpretación basada en el aprendizaje profundo de datos georradar para la evaluación del estado de pavimentos, Interpretación baseada na aprendizaxe profunda dos datos do radas de penetración terrestre para a avaliación do estado do pavimento

  • Elseicy , Ahmed Mossad Ibrahim
Road pavements are vital elements that should be in good physical condition to provide a safe and seamless flow to transport people and goods. However, they are subjected to various internal defects because of aging, environmental conditions, changing traffic load, and poor maintenance. Therefore, regular pavement inspections are performed to ensure their serviceability. Ground Penetrating Radar (GPR) is one of the nondestructive techniques that is widely used for inspecting road pavements subsurface. It is used to assess the condition of the pavement and the thickness of its layers. Furthermore, it can identify subsurface defects, such as cracks, voids, and subgrade settlements. Nevertheless, the current practice is to interpret GPR data using heuristic methods which are time-consuming and highly dependent on the user experience. Moreover, the output of the processing cannot be easily integrated with CAD and BIM software due to lake of data interoperability. Recently, deep learning-based methods have been applied to interpret GPR data and to overcome the interpretation subjectivity challenge. However, choosing a suitable network architecture and post-processing techniques for feature extraction is still undergoing investigation. This research aims to apply state-of-the-art deep learning techniques to process GPR data of the road pavements automatically. The target features are pavement layer thickness and road defects, such as cracks, delamination, voids, and moisture damages. The proposed algorithms aim to reduce the processing time and detect the hidden patterns of the data, which will help to eliminate the interpretation subjectivity. Moreover, the results are automatically exported as a georeferenced 3D dataset with semantic labels instead of representing them as labeled radargrams or tabular reports. The labeled dataset can be integrated with the existing building information modeling (BIM) and geographic information systems (GIS) applications., Los pavimentos de las carreteras son elementos vitales que deben estar en buenas condiciones físicas para proporcionar un flujo seguro y sin problemas al transporte de personas y mercancías. Sin embargo, están sujetos a diversos defectos internos debido al envejecimiento, las condiciones ambientales, los cambios en la carga de tráfico y un mantenimiento deficiente. Por lo tanto, se realizan inspecciones periódicas de los pavimentos para garantizar su capacidad de servicio. El radar de penetración terrestre o georradar (GPR por sus siglas en inglés) es una de las técnicas no destructivas más utilizadas para inspeccionar el subsuelo de las carreteras. Se utiliza para evaluar el estado del pavimento y el espesor de sus capas. Además, puede identificar defectos en el subsuelo, como pueden ser grietas, huecos y asentamientos de la subrasante. Sin embargo, la práctica actual consiste en interpretar los datos del GPR mediante métodos heurísticos que requieren mucho tiempo y dependen en gran medida de la experiencia del usuario. Además, el resultado del procesamiento no se puede integrar fácilmente en software CAD y BIM debido a la falta de interoperabilidad de los datos. Recientemente, se han aplicado métodos basados en el aprendizaje profundo para interpretar los datos GPR y superar el desafío de la subjetividad en la interpretación. Sin embargo, la elección de una arquitectura de red adecuada y las técnicas de post-procesamiento para la extracción de características todavía se están investigando y no existe una metodología de confianza. La investigación de este trabajo doctoral tiene como objetivo aplicar técnicas de aprendizaje profundo de última generación para procesar automáticamente los datos GPR en pavimentos de carreteras. Las características objetivo son el grosor de la capa del pavimento y los defectos de la carretera (grietas, delaminación, vacíos, humedad). Los algoritmos propuestos tienen como objetivo reducir el tiempo de procesamiento y detectar los patrones ocultos en las señales radar registradas, lo que ayudará a eliminar la subjetividad en la interpretación. Además, los resultados se exportarán automáticamente como un conjunto de datos 3D georreferenciados con etiquetas semánticas en lugar de representarlos como radargramas etiquetados o informes tabulares. El conjunto de datos etiquetados puede integrarse con las aplicaciones existentes de modelado de información de edificios (BIM) y de sistemas de información geográfica (GIS)., Os pavimentos das estradas son elementos vitais que deben estar en boas condicións físicas para proporcionar un fluxo seguro e sen problemas para o transporte de persoas e mercadorías. Con todo, están suxeitos a diversos defectos internos debido ao envellecemento, as condicións ambientais, os cambios na carga de tráfico e un mantemento deficiente. Por tanto, realízanse inspeccións periódicas dos pavimentos para garantir a súa capacidade de servizo. O radar de penetración terrestre ou xeorradar ( GPR polas súas siglas en inglés) é unha das técnicas non destrutivas máis utilizadas para inspeccionar o subsolo das estradas. Utilízase para avaliar o estado do pavimento e o espesor das súas capas. Ademais, pode identificar defectos no subsolo, como gretas, ocos e asentamentos da subrasante. Con todo, a práctica actual consiste en interpretar os datos do GPR mediante métodos heurísticos. Estes métodos consomen moito tempo e dependen en gran medida da experiencia do usuario. Ademais, o resultado do procesamento non pode integrarse facilmente no software CAD e BIM debido á falta de interoperabilidade dos datos. Recentemente, aplicáronse métodos baseados na aprendizaxe profunda para interpretar os datos GPR e superar o desafío da subxectividade na interpretación. Con todo, a elección dunha arquitectura de rede adecuada e as técnicas de posprocesamento para a extracción de características seguen sendo obxecto de investigación. A investigación neste traballo de doutoramento ten como obxectivo aplicar técnicas de aprendizaxe profunda de última xeración para procesar automaticamente os datos GPR en pavimentos de estradas. As características obxectivo son o espesor da capa do pavimento e os defectos da estrada (gretas, delaminación, baleiros e humidade). Os algoritmos propostos teñen como obxectivo reducir o tempo de procesamento e detectar os patróns ocultos nos sinais radar rexistrados, o que axudará a eliminar a subxectividade na interpretación. Ademais, os resultados exportaranse automaticamente como un conxunto de datos 3D xeorreferenciado con etiquetas semánticas en lugar de representarse como radargramas etiquetados ou informes tabulares. O conxunto de datos etiquetados pódese integrar coas aplicacións existentes de modelado de información de edificios (BIM) e sistemas de información xeográfica (GIS)., Ministerio de Ciencia e Innovación | Ref. PREP2022-000030, Agencia Estatal de Investigación | Ref. PID2022-138526OB-I00, Agencia Estatal de Investigación | Ref. TED2021-130183B-I00