Hazard recognition is critical for construction safety, especially for accident prevention. Traditional methods often fail to capture the dynamic and interdependent nature of construction hazards. To address this issue, this paper proposes a network-based framework that conceptualizes construction hazards as dynamic interactions between objects with hazardous attributes. A link prediction model using

Healthcare facilities are complex systems where operational efficiency depends on space, processes, resources, and logistics. While many studies propose process-simulation-based improvements, few dynamically consider the built space’s effect on process efficiency. The critical challenge here is the effective integration of data from these disparate domains. This article addresses this challenge by

This paper presents a method for automatic detection and quantification of full cross-sectional dimensions of structural components using oblique photography and the SAM-dimension (Segment Anything Model-dimension) model. Unlike traditional methods that measure only a single cross-section, this approach enables full cross-sectional dimension detection across the entire component, enhancing efficiency

Engineering structural damage often exhibits diverse and complex features across multiple scales within small-scale regions of interest (ROI), complicating post-earthquake assessments. This paper proposes an interpretable deep learning (DL) framework for semantic segmentation of multicategory damage. Energy-derivative attention modules are integrated into convolutional neural networks (CNNs) to enhance

Recent urban revitalisation requires advanced utility management and innovative technology to achieve high-precision utility management. This paper introduces an automated framework that surpasses traditional methods of subsurface utility detection by integrating Ground Penetrating Radar (GPR), deep learning, and Augmented Reality (AR) to provide an advanced solution for subsurface detection and visualization

The measurement of ultrasonic surface velocity in concrete and the ultrasonic Time Of Flight method for estimating the depth of surface opening cracks in concrete are important techniques for maintenance of constructions, which are currently performed manually. This paper demonstrates the possibility to automate these measurements by means of an Unmanned Aerial Vehicle (UAV) equipped with a robotic

The built environment is a key leverage point for policy intervention to combat climate change and the statutory reporting of financial and non-financial indicators over the asset lifecycle is increasingly required. This poses significant information management challenges in a sector characterised by complexity. Contributions to-date which address Life Cycle Asset Information Management (LCAIM) remain

As construction workflows become increasingly dynamic, there is a growing need for Digital Twins (DTs) to support integrated, real-time workflow monitoring. However, establishing DTs in construction remains challenging due to fragmented data sources and the lack of systematic semantic integration methods. This paper investigates how semantic web ontologies can be systematically applied to establish

Effective knowledge management in construction safety is essential yet challenging. Despite emerging technologies to collect valuable data automatically, it continues to rely on manual input. The heterogeneity of data sources in construction makes it additionally difficult, resulting in a high number of incidents due to late changes in the design. Presented is a unified ontology for construction safety

Construction site monitoring relies on robust image classification to enhance safety, track progress, and optimize resource management. However, the amount of clutter and the high cost of manual labeling pose significant challenges. This paper presents an approach to multi-object classification in construction sites using Adaptive Active Transfer Learning. The Weighted Active Transfer Learning with

Increasing the Degrees Of Freedom (DOFs) of Kinetic Façade Systems (KFS) potentially enhances environmental adaptability but presents challenges in mechanical feasibility and optimization complexity due to high-dimensional design spaces. This paper investigates the mechanism design and optimization strategies for multi-DOF KFS, and assesses the performance trade-offs associated with increased motion

With the increasing demand for precise control in 3D concrete printing, coordinating material rheological properties and printing parameters has become a critical challenge. This paper addresses how to intelligently optimize printing parameters to adapt to varying concrete material attributes and improve printing quality. A dual-path framework co-driven by physical information equations (PIE) and machine

Wire-arc directed energy deposition (DED-Arc), also known as wire arc additive manufacturing (WAAM), brings about unprecedented opportunities in the construction sector to improve material efficiency, enhance automation and reduce embodied carbon. To address the current standardisation gap, a normative framework for the use of DED-Arc in construction is proposed in this paper. The current standardisation

Aging bridges urgently need maintenance, as many exceed their lifespans. Traditional inspections are manual, time-consuming, costly, and error-prone. This has prompted a shift toward integrating advanced technologies to automate inspection processes and provide more efficient and accurate maintenance solutions. This paper introduces a multi-stage automated inspection system for bridge maintenance designed

Design Science Research (DSR) is a methodological framework that goes beyond the traditional divide between empirical studies and theoretical research, with its roots in the early development of artificial intelligence and design practice. The rise of emerging technologies in the construction field has significantly boosted DSR-applied research within this sector. This paper examines the applicability

To enhance the efficiency and accuracy of composite box girder bridge design and achieve rapid and high-precision cross-section design, an effective intelligent algorithm is imperative. However, the development of intelligent design for steel-concrete composite box girder bridges is constrained by data scarcity and the performance of existing generative models. This paper introduces a pre-trained Vision

Highway work zones are prone to intrusion events that threaten workers' safety and disrupt operations. Existing intrusion detection systems often produce high false alarms, causing alarm fatigue and reduced responsiveness. To address this, a data-driven intrusion detection method is proposed to distinguish real vehicle intrusions from non-hazardous events using inertial measurement unit (IMU) sensors

Distributed fiber optic sensors (DFOS) hold significant potential for automation in construction, particularly in identifying and quantifying cracks through strain distributions. However, interpreting these distributions is challenging, especially when strain peaks overlap and there is nonlinearity in the cable-structure interface. To address this problem, this paper develops a deep learning model

The traditional inspection of reinforcing steel bars (rebar) in construction often suffers from inaccuracies, inefficiencies, and challenges posed by environmental factors, leading to project delays and increased costs. This paper presents a method for improving rebar inspection by integrating Augmented Reality (AR), Internet of Things (IoT) technologies, and Building Information Modeling (BIM). The

Effective compaction quality significantly impacts pavement durability and performance, with uneven compaction often resulting from traditional empirical approaches that adjust vibration modes and rolling periods. This paper investigates the effects of vibratory roller amplitude optimization on asphalt pavement compaction and develops predictive models for intelligent compaction (IC) parameters and

Builders of the past naturally adjusted geometries to fit existing surfaces. Today, replicating these forms during the 3D digitization of historical elements poses a significant challenge for BIM operators. Achieving a precise fit for the geometry of a cross-vault facilitates the implementation of the Scan-to-BIM approach for repetitive objects with significant variations in their geometry. This paper

Reuse is not commonly adopted in practice, despite its acknowledged benefits, partly due to the complexity of the design process, considering geometric constraints and fluctuating stock availability. A multi-objective optimization framework for algorithm-based stock assignment and path generation is developed, specifically for one-dimensional material systems (e.g., piping, timber, steel), to maximize

There is substantial potential for future underground construction operations to be performed by autonomous robots. This paper proposes a 360-degree digital reconstruction framework for robotic-built underground structures using in-pipe rotating ground penetrating radar (GPR). Unlike conventional ground-level applications, placing GPR inside pipes significantly reduces signal attenuation by shortening

Machine learning (ML), graph deep learning (GDL), natural language processing (NLP), generative, and image deep learning (IDL) methods are promising for automating space function and space access element classification for building analysis. Benchmarking these five methods is currently infeasible primarily due to a lack of datasets with diverse data representation formats. This paper introduces SFC-A68

Material transportation and on-site assembly are the building lifecycle phases that produce significant carbon emissions. However, traditional methods for capturing and recording these emissions lack automation, traceability, and immutability. This limitation hinders project stakeholders from data-driven decision-makings to promote sustainable construction practices and effectively implement regulations

This paper addressed the challenge of inverse design in structural engineering, focusing on predicting reinforcement and thickness parameters for piecewise developable reinforced concrete shells. Specifically, it investigates whether pre-trained machine learning models can more effectively predict rebar directions and thicknesses from displacement data compared to models trained from scratch. To answer

Industrialised construction, through the offsite manufacturing of standardised components, is emerging as a response to the growing demand for the mass production of high-performance buildings. A review of existing research and projects reveals a significant gap in the development of façade systems compatible with Prefabricated Prefinished Volumetric Construction (PPVC)—the most advanced form of offsite

Road intersections are critical components of urban infrastructure networks, ensuring safe and efficient traffic flow. However, their construction frequently experiences delays and cost overruns, often due to inadequate schedule planning. To mitigate these issues, the integration of Building Information Modeling (BIM) and Lean Construction has emerged as a promising strategy. Despite the recognized

The Architecture, Engineering, and Construction (AEC) industry faces data integration challenges due to fragmented silos and diverse data representations, hindering cross-domain queries and early detection of design constraints. Semantic Web Technologies (SWTs) address data integration challenges.

The emergence of 3D computer vision presents a promising paradigm for structural health monitoring of segmental tunnel linings. For automated inspection and analysis, it is first necessary to segment the associated point clouds into individual tunnel segments. Whilst 3D deep learning (DL) networks are suitable for such tasks, the similarity of segment geometries renders generic 3D DL network architectures

While model generalization and specialization are a critical concern in computer vision, balancing them in data-scarce construction settings remains challenging due to their unique nature. This paper proposes a multi-domain learning approach where a model acquires domain-generic visual knowledge from various domain datasets, while maintaining domain-specific predictabilities for each individual domain

Digital Twin (DT) technology has emerged as a next-generation smart building management solution, seamlessly bridging traditional Building Automation Systems (BAS) with Industry 4.0 innovations such as Building Information Modelling (BIM), artificial intelligence (AI), big data, Internet of Things (IoT), and Extended Reality (XR). However, current DT applications in building operations remain nascent

This paper focuses on the cost minimization of the multi-mode resource-constrained repetitive project scheduling problem with multiple crews, crew interruptions, and soft logic. The resource allocation of each crew is considered. To explore the impact of different construction strategies on project costs, mixed-integer linear programming (MILP) and constraint programming (CP) models are developed representing

Real-time monitoring is critical for smart construction management, yet environmental complexities degrade surveillance video quality. Traditional visual information fidelity (VIF) algorithms depend on reference images, which limits their use in no-reference scenarios such as autonomous systems and industrial inspection. Grounded in information theory, this paper proposes an algorithm that integrates

Accurate prediction of TBM tunneling performance is crucial for improving construction efficiency. This paper proposes a fusion prediction method based on multimodal decomposition and multi-Deep Learning. First, tunneling data are preprocessed to build a sample database. Then, an improved ISTL model is developed to decompose tunneling performance into trend, seasonal, cycle, and residual components

Prefabricated bridges are preferred in modern construction for their rapid assembly, cost-efficiency, and minimal environmental impact. However, traditional alignment methods, such as total stations and levels, are time-consuming and labor-intensive. This paper proposes a UAV-based alignment measurement system using artificial markers for vertical alignment in prefabricated bridges. The key contributions

Given the remarkable comprehensive ability, Large Language Models (LLMs) offer a promising solution for automatic geotechnical design. However, addressing multimodal geotechnical design assignments involving both text and image is still challenging for existing LLMs. This paper develops a framework integrating multiple LLMs, the multi-GeoLLM, for multi-modal geotechnical design. It can understand multimodal

Timely and comprehensive pavement rutting detection is crucial for road safety and maintenance. Traditional methods often fail to capture full morphological characteristics and severity of rutting. This paper proposes an area-based pavement rutting detection method using unsupervised deep learning. An adaptive point cloud rasterization strategy and multi-feature mapping enhance surface detail preservation

Rapid deployment equipment is crucial in emergency rescue operations during natural disasters such as earthquakes and floods. However, traditional equipment often has limitations such as complex operations, long deployment times, and high manpower requirements. This paper designs a deployable bridge for post-disaster rescue, with its core component being a bistable Miura-ori unit. Bistable characteristics

An automated framework for structural health monitoring is presented in this paper, encompassing modal identification, health monitoring, and damage localization while accounting for environmental and operational variations. The proposed framework automates the modal identification process using covariance-driven stochastic subspace identification, coupled with a Gaussian mixture model clustering approach

The progressions of industrial revolutions have enabled diverse digital technologies in architecture, engineering, construction and operation (AECO), with Building Information Modelling (BIM) gaining notable attention. Concurrently, the circular economy (CE) has emerged as a crucial strategy for addressing socio-economic issues such as waste, resource depletion, and climate change. However, limitations

Leakage detection (LD) in water pipelines is crucial for reducing water wastage. Acoustic methods for pipeline monitoring are gaining increasing popularity. However, challenges like noise, reverberation, and time-varying factors in pipelines hinder feature extraction. To ameliorate this problem, this paper introduces a feature representation method named EF_Mel spectrogram and proposes a multi-dimensional

Current structural damage segmentation models are often trained based on substantial pixel-level labels for specific structural components and damage types. To address this issue, this paper establishes a transformer-based large vision model for universal structural damage segmentation, incorporating a pre-trained transformer-based frozen backbone and a fine-tuned CNN-based segmentation head. A synthetic

The increasing demand for automated rebar cage assembly in the construction industry highlights the need for flexible rebar grasping solutions. This paper proposes a grasp detection method that enables robotic arms to autonomously grasp rebars from the top layer of stacks, eliminating the need for complex delivery systems. To support this, a synthetic dataset pipeline incorporating domain randomization

As deep space exploration advances, agencies such as National Aeronautics and Space Administration (NASA) and The European Space Agency (ESA), along with other nations, have developed mid-to-long-term plans for lunar habitation, including the construction of lunar infrastructure. This article reviews existing lunar construction concepts and designs, analyzing their importance for sustained human presence

Siltation diagnosis of drainage pipelines is crucial for preventing urban flooding. However, the existing intelligent siltation diagnosis algorithms often exhibits limitations in handling multivariate data sequences and extracting multifaceted features, leading to partial distortion in outputs. To address these shortcomings, a neural network architecture consisting of inception network (BCI), residual

Digital transformation is employed to create digital models that reflect the current state of infrastructure. Conventional semantic structure from motion methods effectively generated digital models of bridges segmented by components through semantic segmentation. However, these methods encounter significant challenges in the digital transformation of pedestrian suspension bridges: the inaccurate modeling

This paper presents an AI framework for automated detection of personal protective equipment (PPE) compliance in complex construction and industrial environments. Ensuring health and safety standards is essential for protecting workers engaged in construction, repair, or inspection activities. The framework leverages deep learning techniques for worker detection and pose estimation to enable accurate

This paper introduces an automated framework for generating safety risk management guidance using a Large Language Model (LLM) enhanced by Retrieval-Augmented Generation (RAG). Reference documents related to specific work activities and equipment are retrieved from 64,740 construction accident cases, generating tailored safety risk management guidance using LLM. This study confirmed that domain adaptation

The construction industry is a major contributor to global greenhouse gas emissions, with embodied carbon playing a key role. This paper introduces EcoSphere, an integrated software for automating sustainable urban development by analyzing trade-offs between embodied and operational carbon emissions, construction costs, and environmental impacts. It leverages National Structure Inventory data, computer

Visual simultaneous localization and mapping technology assumes that the surrounding objects are stationary, making it inapplicable to dynamic objects. In environments with dynamic objects, accurately estimating their shape and displacement remains challenging. This paper develops a method for estimating the 3D shapes and displacements of dynamic objects using a monocular camera and demonstrates its

Efficient identification of at-risk construction workers is crucial for reducing fall-from-height (FFH) accidents. However, current methods of evaluating worker FFH risk rely on manual inspections, which are ineffective because of the complex nature of construction sites. To address this issue, this paper presents a technique for FFH risk assessment using physiological data. A virtual reality experiment

Architects need efficient generative methods for handling complex architectural layout design tasks to spare more attention to the aesthetics of buildings. High expertise requirements of the input conditions and the large size of datasets bring challenges for architects using generative architectural design methods. This paper presents a hybrid model that integrates Graph Neural Networks (GNNs) for

Relocatable modular buildings (RMBs) are gaining recognition for their innovation, efficiency, and sustainability, especially in addressing urgent needs during natural disasters or pandemics. Their inherent flexibility, mobility, and scalability enable rapid deployment and adaptation to changing needs. However, managing multiple modular units and their relocation and reconfiguration over time presents

Large language models (LLMs) agents can function as autonomous, interactive, goal-oriented systems, but in the building energy sector, there is currently no structured paradigm that researchers and engineers can follow to create, access, and share effective LLM agents without starting from scratch. This paper introduces a JSON-based agent schema designed to structure the description of LLM agents.

Prefabricated Off-site Fit-out (POF) plays a critical but often overlooked role in Modular Prefabricated Construction (MPC). Due to fragmented and asymmetric information, inconsistent production and intralogistics operations, and production uncertainty, the POF faces significant synchronization challenges. To address these challenges, this paper proposes the Graduation Intelligent Manufacturing System

The design of lightweight Ultra-High-Performance Concrete (UHPC) requires pursuing superior material efficiency, which involves striking a delicate balance between ultra-high compressive strength and reduced material density. This paper compiled a comprehensive dataset of 176 ordinary UHPC and 72 lightweight UHPC and proposed a framework that integrates both transfer learning and Bayesian Optimization-enhanced

Assessing cradle-to-site embodied carbon (EC) emissions enables stakeholders to make carbon-reduction decisions early. Discrete event simulation (DES) is useful for analyzing cradle-to-site EC by simulating construction operations. However, developing a DES model for cradle-to-site EC assessment in construction projects is time-consuming and error-prone. Therefore, this paper proposes an automated

Building information modeling (BIM) enhances communication in the architecture, engineering, and construction industry and automates drawing generation. However, optimizing the placement of drawing elements remains a challenge. This paper proposes a framework using proximal policy optimization to improve BIM drawing element placement, focusing on floor plan-type drawings in the construction documentation

Transfer learning has emerged as a powerful tool and rapidly advanced numerous fields with cutting-edge technologies. This paper provides a comprehensive review of transfer learning applications in smart construction, analyzing its utilization to enrich the construction industry's knowledge. A systematic analysis of 366 publications from 2015 to 2024 highlights the growth and importance of transfer