Rendimiento de los métodos de detección de daños estructurales basados en la función de respuesta en frecuencia y la densidad espectral de potencia

Acaban de publicarnos un artículo en DYNA, revista indexada en el JCR. Se trata de comparar el rendimiento de los métodos de detección de daños estructurales basados en la función de respuesta en frecuencia y la densidad espectral de potencia. El trabajo se enmarca dentro del proyecto de investigación HYDELIFE que dirijo como investigador principal en la Universitat Politècnica de València.

Los recientes sucesos catastróficos han despertado un gran interés en la comunidad científica en relación con la evaluación y predicción de la respuesta estructural a lo largo del ciclo de vida de las infraestructuras. Se están realizando esfuerzos para desarrollar sistemas adecuados de monitorización de las estructuras que ayuden a prevenir futuras pérdidas de vidas humanas y económicas. Aquí se presentan dos métodos no destructivos de detección de daños: el basado en la función de respuesta en frecuencia y el basado en la función de densidad espectral. El desempeño en la detección de daños de ambos métodos se compara a través de un caso de estudio concreto, en el que se analizan diferentes escenarios de daños en un puente en celosía 2D. La fiabilidad de cada método se estudia en términos de diferentes errores de predicción. Los resultados numéricos muestran que el método PSD para la detección de daños en una estructura de puente en celosía de acero proporciona resultados más precisos y robustos en comparación con el basado en el método FRF.

Abstract:

Recent catastrophic events have aroused great interest in the scientific community regarding evaluating and predicting the structural response along the life cycle of infrastructures. Efforts are put into developing adequate health monitoring systems to help prevent future human life and economic losses. Here, two non-destructive damage detection methods are presented: the Frequency Response Function-based and the Spectral Density Function-based methods. The damage detection performance of both methods is compared through a particular case study, where different damage scenarios are analyzed in a 2D truss bridge. The reliability of each method is studied in terms of different prediction errors. Numerical results show that the PSD method for damage detection on a steel truss bridge structure provides more accurate and robust results when compared to that based on FRF.

Keywords:

Structural Health Monitoring, Power Spectral Density Function, Frequency Response Function, Construction, Structures, Damage detection, Non-destructive

Reference:

HADIZADEH-BAZAZ, M.; NAVARRO, I.J.; YEPES, V. (2022). Performance comparison of structural damage detection methods based on Frequency Response Function and Power Spectral Density. DYNA, 97(5):493-500. DOI:10.6036/10504

Como el artículo se encuentra en abierto, os paso el documento para que os lo podáis descargar.

Descargar (PDF, 822KB)

Machine learning aplicado a la construcción: Un análisis de los avances científicos y del futuro próximo

Acaban de publicarnos un artículo en la revista Automation in Construction, que es la revista indexada de mayor impacto JCR en el ámbito de la ingeniería civil. En este caso se ha realizado un análisis bibliométrico del estado del arte y de las líneas de investigación futura del Machine Learning en el ámbito de la construcción. El trabajo se enmarca dentro del proyecto de investigación HYDELIFE que dirijo como investigador principal en la Universitat Politècnica de València. En este caso, se trata de una colaboración con grupos de investigación de Chile, Brasil y España.

El artículo lo puedes descargar GRATUITAMENTE hasta el 11 de octubre de 2022 en el siguiente enlace: https://authors.elsevier.com/c/1fdIq3IhXMtgv2

Los complejos problemas industriales, junto con la disponibilidad de una infraestructura informática más robusta, presentan muchos retos y oportunidades para el aprendizaje automático (Machine Learning, ML) en la industria de la construcción. Este artículo revisa las técnicas de ML aplicadas a la construcción, principalmente para identificar las áreas de aplicación y la proyección futura en esta industria. Se analizaron estudios desde 2015 hasta 2022 para evaluar las últimas aplicaciones de ML en la construcción. Se propuso una metodología que identifica automáticamente los temas a través del análisis de los resúmenes utilizando la técnica de Representaciones Codificadoras Bidireccionales a partir de Transformadores para posteriormente seleccionar manualmente los temas principales. Hemos identificado y analizado categorías relevantes de aplicaciones de aprendizaje automático en la construcción, incluyendo aplicaciones en tecnología del hormigón, diseño de muros de contención, ingeniería de pavimentos, construcción de túneles y gestión de la construcción. Se discutieron múltiples técnicas, incluyendo varios algoritmos de ML supervisado, profundo y evolutivo. Este estudio de revisión proporciona directrices futuras a los investigadores en relación con las aplicaciones de ML en la construcción.

Highlights:

  • State-of-the-art developed using natural language processing techniques.
  • Topics analyzed and validated by experts for consistency and relevance.
  • Topics deepened through application of bigram analysis and clustering in addition to traditional bibliographic analysis.
  • Identified five large areas, and detailed two to three groups of relevant lines of research.

Abstract:

Complex industrial problems coupled with the availability of a more robust computing infrastructure present many challenges and opportunities for machine learning (ML) in the construction industry. This paper reviews the ML techniques applied to the construction industry, mainly to identify areas of application and future projection in this industry. Studies from 2015 to 2022 were analyzed to assess the latest applications of ML techniques in construction. A methodology was proposed that automatically identifies topics through the analysis of abstracts using the Bidirectional Encoder Representations from Transformers technique to select main topics manually subsequently. Relevant categories of machine learning applications in construction were identified and analyzed, including applications in concrete technology, retaining wall design, pavement engineering, tunneling, and construction management. Multiple techniques were discussed, including various supervised, deep, and evolutionary ML algorithms. This review study provides future guidelines to researchers regarding ML applications in construction.

Keywords:

Machine learning; BERT; Construction; Concretes; Retaining walls; Tunnels; Pavements; Construction management

Reference:

GARCÍA, J.; VILLAVICENCIO, G.; ALTIMIRAS, F.; CRAWFORD, B.; SOTO, R.; MINTATOGAWA, V.; FRANCO, M.; MARTÍNEZ-MUÑOZ, D.; YEPES, V. (2022). Machine learning techniques applied to construction: A hybrid bibliometric analysis of advances and future directions. Automation in Construction, 142:104532. DOI:10.1016/j.autcon.2022.104532

Evaluación de la sostenibilidad de las técnicas de mejora del terreno

Acaban de publicarnos un artículo en la revista Journal of Cleaner Production, revista de ELSEVIER indexada en el primer decil del JCR.

El terreno no siempre es adecuado o competente para soportar una cimentación superficial directa. En muchos casos, para evitar costosas cimentaciones profundas, está indicado sustituir, mejorar o reforzar dicho terreno. Este trabajo se centra en evaluar la contribución a la sostenibilidad entre diferentes técnicas de mejora del suelo y el resultado de su aplicación a la cimentación de una vivienda unifamiliar como alternativa a la construida. Se compara el rendimiento del ciclo de vida en materia de sostenibilidad entre el diseño de referencia (sin intervención), el relleno y la compactación del suelo, las columnas de suelo-cemento, la inclusión rígida de micropilotes y el clavado de viguetas prefabricadas. Para caracterizar la sostenibilidad, se propone un conjunto de 37 indicadores que integran los aspectos económicos o ambientales de cada alternativa de diseño y sus impactos sociales. Se obtiene un ranking de sostenibilidad para las diferentes alternativas basado en el método ELECTRE IS para la toma de decisiones multicriterio (MCDM). Se evalúa la sensibilidad de los resultados obtenidos frente a diferentes métodos MCDM (TOPSIS, COPRAS) y diferentes ponderaciones de criterios. La evaluación proporciona una visión transversal, comparando la capacidad y fiabilidad de cada técnica para priorizar la solución de consolidación del terreno que mejor contribuye a la sostenibilidad en el diseño de la subestructura de un edificio.

El trabajo se enmarca dentro del proyecto de investigación HYDELIFE que dirijo como investigador principal en la Universitat Politècnica de València.

Podéis leer una versión preliminar el artículo en la siguiente dirección: https://doi.org/10.1016/j.jclepro.2022.131463

Highlights

  • Evaluation of soil consolidation techniques for a single-family house’s foundation.
  • A deep foundation is compared to four alternatives that consider soil improvement.
  • 37 indicators characterize the sustainability of substructure in residential buildings.
  • The aggregation of the different sustainability criteria is applied in 3 MCDM methods.
  • Nailing precast joists into the ground achieves the best sustainability result.

Abstract

The soil is not always suitable or competent to support a direct shallow foundation in construction. In many cases, to avoid costly deep foundations, it is indicated to replace, improve, or reinforce such soil. This paper focuses on evaluating the contribution to sustainability between different soil improvement techniques and the outcome of their application to the foundation of a single-family house as an alternative to the one built. The life-cycle performance in sustainability is compared between the baseline design (without intervention), backfilling and soil compaction, soil-cement columns, rigid inclusion of micropiles, and nailing of precast joists. To characterize sustainability, a set of 37 indicators is proposed that integrate the economic or environmental aspects of each design alternative and its social impacts. A sustainability ranking is obtained for the different alternatives based on the ELECTRE IS method for multi-criteria decision-making (MCDM). The sensitivity of the obtained results is evaluated against different MCDM methods (TOPSIS, COPRAS) and different criteria weights. The evaluation provides a cross-cutting view, comparing the ability and reliability of each technique to prioritize the ground consolidation solution that best contributes to the sustainability in the design of a building’s substructure.

Keywords

Sustainability; Construction; Multi-criteria decision analysis; Life cycle assessment; Modern methods of construction; Soil improvement; Foundations; ELECTRE IS; TOPSIS; COPRAS

Reference:

SÁNCHEZ-GARRIDO, A.J.; NAVARRO, I.J.; YEPES, V. (2022). Evaluating the sustainability of soil improvement techniques in foundation substructures. Journal of Cleaner Production, 351: 131463. DOI:10.1016/j.jclepro.2022.131463

Descargar (PDF, 7.31MB)

Hacia un mapa de conocimiento algorítmico de optimización de la industria AEC-AI (Arquitectura, Ingeniería, Construcción e Inteligencia Artificial)

Acaban de publicarnos un artículo en la revista IEEE Access, revista de alto impacto indexada en el JCR. En este caso se ha realizado un análisis conceptual macroscópico de la industria AEC-AI (Arquitectura, Ingeniería, Construcción e Inteligencia Artificial). El trabajo se enmarca dentro del proyecto de investigación HYDELIFE que dirijo como investigador principal en la Universitat Politècnica de València.

La industria de la arquitectura, la ingeniería y la construcción (AEC) constituye uno de los sectores productivos más relevantes, por lo que también produce un alto impacto en los equilibrios económicos, la estabilidad de la sociedad y los desafíos globales en el cambio climático. En cuanto a su adopción de tecnologías, aplicaciones y procesos también se reconoce por su status-quo, su lento ritmo de innovación, y los enfoques conservadores. Sin embargo, una nueva era tecnológica -la Industria 4.0 alimentada por la IA- está impulsando los sectores productivos en un panorama sociopolítico y de competencia tecnológica global altamente presionado. En este trabajo, desarrollamos un enfoque adaptativo para la minería de contenido textual en el corpus de investigación de la literatura relacionada con las industrias de la AEC y la IA (AEC-AI), en particular en su relación con los procesos y aplicaciones tecnológicas. Presentamos un enfoque de primera etapa para una evaluación adaptativa de los algoritmos de IA, para formar una plataforma integradora de IA en la industria AEC, la industria AEC-AI 4.0. En esta etapa, se despliega un método adaptativo macroscópico para caracterizar la “Optimización”, un término clave en la industria AEC-AI, utilizando una metodología mixta que incorpora el aprendizaje automático y el proceso de evaluación clásico. Nuestros resultados muestran que el uso eficaz de los metadatos, las consultas de búsqueda restringidas y el conocimiento del dominio permiten obtener una evaluación macroscópica del concepto objetivo. Esto permite la extracción de un mapeo de alto nivel y la caracterización de la estructura conceptual del corpus bibliográfico. Los resultados son comparables, a este nivel, a las metodologías clásicas de revisión de la literatura. Además, nuestro método está diseñado para una evaluación adaptativa que permita incorporar otras etapas.

Abstract:

The Architecture, Engineering, and Construction (AEC) Industry is one of the most important productive sectors, hence also produce a high impact on the economic balances, societal stability, and global challenges in climate change. Regarding its adoption of technologies, applications and processes is also recognized by its status-quo, its slow innovation pace, and the conservative approaches. However, a new technological era – Industry 4.0 fueled by AI- is driving productive sectors in a highly pressurized global technological competition and sociopolitical landscape. In this paper, we develop an adaptive approach to mining text content in the literature research corpus related to the AEC and AI (AEC-AI) industries, in particular on its relation to technological processes and applications. We present a first stage approach to an adaptive assessment of AI algorithms, to form an integrative AI platform in the AEC industry, the AEC-AI industry 4.0. At this stage, a macroscopic adaptive method is deployed to characterize “Optimization,” a key term in AEC-AI industry, using a mixed methodology incorporating machine learning and classical evaluation process. Our results show that effective use of metadata, constrained search queries, and domain knowledge allows getting a macroscopic assessment of the target concept. This allows the extraction of a high-level mapping and conceptual structure characterization of the literature corpus. The results are comparable, at this level, to classical methodologies for the literature review. In addition, our method is designed for an adaptive assessment to incorporate further stages.

Keywords:

Architecture, engineering and construction, AEC, artificial intelligence, literature corpus, machine learning, optimization algorithms, knowledge mapping and structure

Reference:

MAUREIRA, C.; PINTO, H.; YEPES, V.; GARCÍA, J. (2021). Towards an AEC-AI industry optimization algorithmic knowledge mapping. IEEE Access, 9:110842-110879. DOI:10.1109/ACCESS.2021.3102215

Descargar (PDF, 6.14MB)

Special Issue “Deep Learning and Hybrid-Metaheuristics: Novel Engineering Applications”

 

 

 

 

 

Mathematics (ISSN 2227-7390) is a peer-reviewed open access journal which provides an advanced forum for studies related to mathematics, and is published monthly online by MDPI. The European Society for Fuzzy Logic and Technology (EUSFLAT) and International Society for the Study of Information (IS4SI) are affiliated with Mathematics and their members receive a discount on article processing charges.

  • Open Access—free for readers, with article processing charges (APC) paid by authors or their institutions.
  • High Visibility: Indexed in the Science Citation Indexed Expanded – SCIE (Web of Science) from Vol. 4 (2016) and Scopus.
  • Rapid Publication: manuscripts are peer-reviewed and a first decision provided to authors approximately 16.4 days after submission; acceptance to publication is undertaken in 4.6 days (median values for papers published in this journal in the first half of 2020).
  • Recognition of Reviewers: reviewers who provide timely, thorough peer-review reports receive vouchers entitling them to a discount on the APC of their next publication in any MDPI journal, in appreciation of the work done.

 

Impact Factor: 1.747 (2019) (First decile JCR)

Special Issue “Deep Learning and Hybrid-Metaheuristics: Novel Engineering Applications”

Deadline for manuscript submissions: 30 April 2021.

Special Issue Editors

Prof. Dr. Víctor Yepes Website SciProfiles
Guest Editor
ICITECH, Universitat Politècnica de València, Valencia, Spain
Interests: multiobjective optimization; structure optimization; lifecycle assessment; social sustainability of infrastructures; reliability-based maintenance optimization; optimization and decision-making under uncertainty
Special Issues and Collections in MDPI journals
Dr. José Antonio García Website
Guest Editor
Pontificia Universidad Católica de Valparaíso, Chile
Interests: optimization; deep learning; operations research; artificial intelligence applications to industrial problems

Special Issue Information

Dear Colleagues,

Hybrid metaheuristic methods have shown very good performances in different combinatorial problems. Additionally, the rise of machine learning techniques has created a space to develop metaheuristic algorithms that use these techniques in order to tackle NP-hard problems and improve the convergence of algorithms. In this Special Issue, we invite researchers to submit papers in this optimization line, applying hybrid algorithms to industrial problems, including but not limited to industrial applications, and challenging problems arising in the fields of big data, construction, sustainability, transportation, and logistics, among others.

Deep learning techniques have also been important tools in extracting features, classifying situations, predicting events, and assisting in decision making. Some of these tools have been applied, for example, to Industry 4.0. Among the main techniques used are feedforward networks (FNN), convolutional networks (CNN), long-term short memory (LSTM), autoencoders (AE), enerative adversarial networks, and deep Q-networks (DQNs). Contributions on practical deep learning applications and cases are invited to this Special Issue, including but not limited to applications to the industry of computational vision, natural language processing, supervised learning applied to industry, unsupervised learning applied to industry, and reinforcement learning, among others.

Prof. Dr. Víctor Yepes
Dr. José Antonio García
Guest Editors

 

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI’s English editing service prior to publication or during author revisions.

Keywords

  • Construction
  • Smart cities
  • Optimization
  • Deep learning

Impacto de la crisis económica en la construcción: lo que opinan los estudiantes

ABSTRACT:

The current economic crisis has specially affected the Spanish construction industry, causing the loss of 1.2 million jobs in the last four years. The increase in the unemployment rate is particularly worrisome for recent graduates in the construction industry. This fact leads to changes in the university degrees related to construction: undergraduate students should be prepared for a new professional environment and recent graduate find it hard to enter the labor market. Low employment opportunities entail a lack of motivation that can cause a significant decrease in the achievement of learning outcomes. This paper seeks to analyze the impact of the crisis in the construction industry from the point of view of the students of a M.Sc. in Construction Management, analyzing the evolution of student’s perception on unemployment and their motivations to enroll in the master degree. For this purpose, a questionnaire was handed out to students of three consecutive classes of the M.Sc. in Construction Management at the Universitat Politècnica de València (Spain) from 2010 to 2012. A statistical analysis of the survey was developed. This way, some interesting points can be highlighted on the impact of crisis on young construction professionals.

KEYWORDS:

Construction; Economic Crisis; Employment; Motivation; Labor Market; M.Sc. Degree

REFERENCIA:

TORRES-MACHÍ, C.; PELLICER, E.; YEPES, V.; PICORNELL, M. (2013). Impact of the economic crisis in construction: a perspective from graduate students. Procedia – Social and Behavioral Sciences, 89:640-645.

Descargar (PDF, 199KB)

 

 

Appraisal of infrastructure sustainability by graduate students using an active-learning method

file.FeedFileLoaderAppraisal of infrastructure sustainability by graduate students using an active-learning method

Abstract:

Currently many university programs in the construction field do not take sustainability into account from a holistic viewpoint. This may cause a lack of sensitivity from future professionals concerning sustainability. Academics in construction must endeavor to instill a culture of sustainability in the curricula of their students. Therefore, this study proposes an active-learning method that allows graduate students in the construction field to take into consideration infrastructure sustainability from a variety of perspectives in a participatory process. The students applied an analytical hierarchical process to determine the appraisal degree of each criterion. A cluster statistical analysis was carried out, aiming to identify the profiles that influence decision-making. This method was applied to two classes of graduate students enrolled in the Master of Planning and Management in Civil Engineering at the Universitat Politècnica de València. This method identified a correlation between the profiles toward sustainability and the characteristics of the chosen infrastructure. It was also found that the method fulfills educational purposes: most of the students obtained more than 65% of the target learning outcomes. This approach promotes awareness and sensitivity to different points of view of the sustainability in a participatory context. It can be replicated in other contexts so as to obtain appraisals regarding various criteria that help enhance decision-making.

Highlights

  • Proposal of a method that allows students to consider infrastructure sustainability.
  • Participatory learning method that promotes integral sustainability.
  • Students profiles’ identification influencing decision making toward sustainability.
  • The profiles of evaluators influence the prioritization among alternatives.

Reference:

PELLICER, E.; SIERRA, L.A.; YEPES, V. (2016). Appraisal of infrastructure sustainability by graduate students using an active-learning method. Journal of Cleaner Production, 113:884-896. DOI:10.1016/j.jclepro.2015.11.010

Os dejo a continuación la versión autor del artículo:

Descargar (PDF, 593KB)

Developing learning manuals for European construction project managers

Maturity model in management competences
Maturity model in management competences (Milosevic et al, 2007)

There is a need for supplementary learning and training in management applied to the construction industry, as many authors, professionals and organisations have already recognised. The assessment and up-keeping of management competencies are essential for the performance of individuals and organisations that work in the construction sector. Most of the universities syllabuses focus in traditional construction courses that do not deal with the most relevant features of management for engineers and architects in the construction industry; these graduate courses mainly cover an assortment of design-oriented issues, leaving no room for managerial topics. Thus, management is a crucial issue for professionals in the construction sector; currently, an engineer or an architect must have some knowledge of every managerial issue valuable in construction. Taking the complete life cycle of the infrastructure as a reference, a holistic attitude must be pursued. Therefore, a model for management and administration in construction is proposed in this paper. This model displays two dimensions: life cycle (per phase) and organisational level. The former is linked to time through the four well-known phases of the construction process: feasibility, design, construction and operation. The latter considers four organisational levels that can be found in the construction sector: life cycle, company, project (or team) and individual. In order to test the appropriateness and usefulness of the model, two applications are implemented. The first one is the analysis of the outputs of a European project which goal was to produce seven basic books for construction managers; this project was developed by several universities and professional associations of the European Union. The second one is the design of a new syllabus in civil engineering (M.Sc. degree) with a specialisation of 30 ECTS; right now, this proposal is being discussed in the School of Civil Engineering at the Universidad Politécnica de Valencia (Spain) to get it implemented in 2010 due to the new academic scenario according to the Bologna process. The model presented in this paper offers an innovative framework for orientation to organisations, professionals and academicians in order to improve the knowledge of management and administration in the construction industry.

Reference:

PELLICER, E.; YEPES, V.; TEIXEIRA, J.C.; CATALÁ; J. (2009). Developing learning manuals for European construction project managers, in Gómez, L.; Martí, D; Candel I. (eds.): Proceedings of International Conference on Education and New Learning Technologies, EDULEARN 09, pp. 2374-2384. 6-8 July, Barcelona, Spain. ISBN: 978-84-612-9802-0. (link)

Descargar (PDF, 393KB)

Environmental Assessment of Concrete Structures

2014-11-12 16.38.05In recent decades, with the objective of reaching a more sustainable development, worldwide society has increased its concern about environmental protection. Nevertheless, there are still economic sectors, such as the construction industry, which produce significant environmental impacts. Life Cycle Assessment (LCA) is a tool that enables identifying environmental issues related to both finished products and services, and allows focusing efforts to resolve them. The main objective of this paper is to asses LCA applicability on concrete structures so that construction’s environmental performance can be improved. For this purpose, an attempt is made to provide a decision-making tool for construction-sector stakeholders with reliable and accurate environmental data. The research methodologies used in this paper are based on a literature review and are applied to a case study. This review was performed to collect information on LCA methodologies currently in use and their practical application. The case study subsequently described in this paper involved identification of the most sustainable type of slab for a reinforced concrete structure in a residential building, using two different databases. It was observed that, depending on the database selected and inherent assumptions, results varied. Therefore it was concluded that in order to avoid producing incorrect results when applying LCA, it is highly recommended to develop a more constrained methodology and grant access to reliable construction-sector data. (link)