Search

The application of deep learning in construction has attracted increasing attention among researchers in recent years. In this review article, comprehensive scientometric analysis and critical review were performed to analyze the state- of-the-art literature on the application of deep learning in construction. This research used the science mapping method to quantitatively and systematically analyze 423 related bibliographic records retrieved from the Scopus database, and further, a critical review was performed on the collected themes of all the related publications. The results of the critical review indicate that deep convolution neural networks, you only look once, single-shot detectors, recurrent neural networks, residual neural networks, and fast region-based convolution neural networks have been the most widely used deep-learning methods in the construction industry. The most commonly addressed problems in the construction industry using deep-learning methods include classification of construction equipment, worker's safety helmet detection, ergonomics analysis, image enhancement, and feature extraction. This paper provides an in-depth understanding and big-picture overview of the existing literature along with the challenges and future direction of research on deep learning in construction. Key words: scientometric analysis, deep learning, critical review, construction industry, Introduction As the construction industry moves towards adopting advanced computer technologies to improve the efficiency of its operations, artificial intelligence is becoming increasingly popular among researchers who are developing innovative [...]

In northern Canada, due to the harsh weather and high labor cost, contractors prefer to using modular construction approach to complete heavy industrial projects, where mobile crane are used for onsite module installations. In current practice, module lifts are often planned manually by rigging engineers. With a large number of heavy lifts to be analyzed per project, the planning process is tedious and error prone. This paper represents a data-driven crane management system with three features: (1) identification of design errors in lifting planning; (2) responses to design changes; and (3) dynamic 3D trajectory-based lifting visualization. It covers two types of crane operations: pick from a fixed location, and pick and walking operation. This developed system helps reduce lifting time and improves safety and quality, where various lifting scenarios need to be analyzed. The system has been implemented at a collaborator company for demonstration and validation. Key words: heavy industrial project, crane management system, 4D visualization, 3D motion planning, lift path planning. Dans le nord du Canada, en raison des conditions meteorologiques difficiles et du cout eleve de la main- d'oeuvre, les entrepreneurs preferent utiliser une approche de construction modulaire pour realiser des projets industriels lourds, ou des grues mobiles sont utilisees pour les installations de modules sur place. Dans la pratique actuelle, les levage de module sont souvent planifies manuellement par les ingenieurs en montage. Avec un grand nombre de charges lourdes a analyser par projet, le processus de planification est fastidieux et sujet aux erreurs. Le present document presente un systeme de gestion de grue axe sur les donnees et comportant trois caracteristiques : (i) la determination des erreurs de conception dans la planification du levage; (ii) les reponses aux changements de conception; et (iii) la visualisation dynamique du levage fondee sur la trajectoire 3D. Ce systeme couvre deux types de grutage: la prise a un endroit fixe (PEF) et la prise et la marche (PM). Il permet de reduire le temps de levage et d'ameliorer la securite et la qualite, ou divers scenarios de levage doivent etre analyses. Le systeme a ete mis en oeuvre dans une entreprise collaboratrice aux fins de demonstration et de validation. [Traduit par la Redaction] Mots-cles : projet industriel lourd, systeme de gestion de grue, visualisation 4D, planification de mouvement 3D, planification de chemin de levage., Introduction In northern Alberta, the oil and gas reserve has led to mega heavy industrial construction projects that contributed to the growth of Canada's economy. The impact of the oil [...]

ObjectiveIn this proof-of-concept study we sought to explore whether the combination of conditioning procedure based on a surreptitious reduction of a noxious stimulus (SRPS) could enhance rTMS hypoalgesic effects [i.e., increase heat pain threshold (HPT)] and augment intervention expectations in a healthy population.MethodsForty-two healthy volunteers (19–35 years old) were enrolled in a randomized crossover-controlled study and were assigned to one of two groups: (1) SRPS and (2) No SRPS. Each participant received two consecutive sessions of active or sham rTMS over the M1 area of the right hand on two visits (1) active, (2) sham rTMS separated by at least one-week interval. HPT and the temperature needed to elicit moderate heat pain were measured before and after each rTMS intervention on the right forearm. In the SRPS group, conditioning consisted of deliberately decreasing thermode temperature by 3°C following intervention before reassessing HPT, while thermode temperature was held constant in the No SRPS group. Intervention expectations were measured before each rTMS session.ResultsSRPS conditioning procedure did not enhance hypoalgesic effects of rTMS intervention, neither did it modify intervention expectations. Baseline increases in HPT were found on the subsequent intervention session, suggesting variability of this measure over time, habituation or a possible “novelty effect.”ConclusionUsing a SRPS procedure in healthy volunteers did not enhance rTMS modulating effects on experimental pain sensation (i.e., HPT). Future studies are therefore needed to come up with a conditioning procedure which allows significant enhancement of rTMS pain modulating effects in healthy volunteers.

The research in value-oriented design reports the importance of displaying the interdependencies between product components and stakeholders' values, where it argues that the display of interdependencies is indispensable for the optimal decision-making and for the success of the value-oriented design. However, applications for value visualization in the construction industry lack one or both of the following: (1) the support for multi-value assessment and visualization and (2) the ability to visualize value(s) over time. These two shortcomings hinder the construction industry from fully embracing sustainable value-oriented design. Hence, this paper proposes a visualization framework to bridge the gap in the practice of value visualization regarding (i) the number of visualized values and (ii) time-based multiple-value visualization. The paper also contains a case study that utilizes a condominium building to show the implementation of the proposed framework and demonstrate how results can be interpreted and utilized in the design process. Key words: value visualization, value-oriented design, multiple-value visualization, construction industry, sustainability, building information modelling (BIM). La recherche en conception axee sur la valeur demontre l'importance d'afficher les interdependances entre les composants du produit et les valeurs des parties prenantes et on fait valoir que l'affichage des interdependances est indispensable pour la prise de decision optimale et pour le succes de la conception axee sur la valeur. Toutefois, les applications de visualisation de la valeur dans l'industrie de la construction sont depourvues de l'un ou l'autre des elements suivants: (1) le soutien pour l'evaluation et la visualisation de plusieurs valeurs et (2) la capacite de visualiser les valeurs au fil du temps. Ces deux lacunes empechent l'industrie de la construction d'adopter une conception axee sur la valeur durable. Par consequent, cet article propose un cadre de visualisation pour combler l'ecart dans la pratique de la visualisation de la valeur concernant (i) le nombre de valeurs visualisees et (ii) la visualisation de valeurs multiples basee sur le temps Le document contient egalement une etude de cas qui utilise un immeuble en copropriete pour montrer la mise en aeuvre du cadre propose et demontrer comment les resultats peuvent etre interpretes et utilises dans le processus de conception. [Traduit par la Redaction] Mots-cles: visualisation de la valeur, conception axee sur la valeur, visualisation de plusieurs valeurs, industrie de la construction, durabilite, modelisation des donnees du batiment (MDB)., Introduction The concept of value is a cornerstone that has facilitated successful societal development and civilizational advancement. This concept has been debated since the era of Greek philosophers who sought [...]

The construction of industrial projects involves fabricating and installing massive quantities of pipelines. The design data of pipelines is complex, usually unique for each project and not easily available to researchers and the public for confidentiality reasons. As a result, an industrial pipelines data generator able to realistically simulate pipelines structures will lessen the dependence on real-life data. This article describes an industrial pipelines data generator that was developed using topological and physical properties of pipelines from real industrial projects. This generator can simulate the properties (the type of component, length, diameter, running direction, and the connectivity relationships between components) of real industrial pipelines. Its application in construction engineering and management research, more specifically in the experimental analysis of an optimization algorithm, was described by the authors in previous work [1]. The data generator can be used to develop benchmark problem instances for optimization problems and for simulation studies of construction operations in industrial projects.