This study systematically elaborates on the core connotation and implementation pathways of the intelligent construction system from the contractors' perspective. It analyzes a digitally-driven intelligent construction framework and proposes replicable and scalable systematic solutions for intelligent construction in practical engineering projects. Furthermore, by integrating theory with practice, it validates the significant effectiveness of intelligent construction systems in enhancing efficiency, optimizing management, and mitigating risks. It can provide a reference for industry transformation and upgrading, promote the deep integration of intelligent construction technologies with engineering practices, and ultimately support the achievement of high-quality project delivery and whole-lifecycle value enhancement.
The safety hazards associated with hydropower construction are diverse and often occur in complex and variable spatial contexts. Human visual assessments based on experience are prone to cognitive and psychological biases. Existing studies face key limitations, including unimodal models failing to capture cross-modal hazard features, the limited generalization ability of small models, and the poor domain adaptability of general-purpose pre-trained models. To address these challenges, this study establishes the first multimodal image-text dataset for safety hazards in hydropower engineering. By leveraging the Qwen2.5-VL model, we implement efficient domain adaptation through LoRA and instruction tuning. A multimodal large model fine-tuned for the intelligent recognition of safety hazards in hydropower construction was proposed. Comparative experiments across hazard types, modalities, and model architectures reveal that: (1) data imbalance has a limited impact on performance differences across hazard types, (2) textual descriptions generally convey more critical hazard-related information than visual features, and (3) domain-specific fine-tuning and effective multimodal fusion are identified as key factors in enhancing hazard recognition performance.
Accurate detection of cracks in concrete structures is essential for ensuring civil engineering safety. Traditional manual inspection and machine vision methods suffer from high subjectivity, low efficiency, and poor adaptability to complex environments. In recent years, machine learning (ML) has significantly improved the precision and automation of crack detection. This review provides a systematic examination of ML-based crack detection through a unique four-stage pipeline-data acquisition, preprocessing, model training, and evaluation. Additionally, the integration of multimodal data and unmanned aerial vehicle (UAV)-based inspection has expanded the scope and applicability of detection technologies. Despite these advancements, challenges remain, including limited accuracy for fine crack detection, immature dynamic monitoring techniques, and lack of industry standards. Future research should focus on optimizing model design, incorporating temporal analysis and uncertainty quantification, and developing intelligent structural health assessment systems. This review offers a technical reference for applying machine learning in crack detection and highlights future directions for interdisciplinary integration and standardization.
Residential construction projects are characterized by high complexity, fragmented communication, and vulnerability to delays and budget overruns due to inefficient manual coordination. This paper presents Civil2PM, an adaptive, on-premises multi-agent project lifecycle management (PLM) system built to autonomously oversee the entire life cycle of residential construction projects. The system is designed to ensure robust cyber-security, maintain cost-efficiency, and seamlessly integrate with existing building information modeling (BIM) and enterprise resource planning (ERP) infrastructure. It employs compact yet high-performance large language models (LLMs), Phi-4-14B, and Qwen3-30B-A3B, running locally to ensure both speed and data sovereignty. These models are orchestrated through the LangChain framework, enhanced with agentic retrieval-augmented generation (ARAG), and supported by a dual-protocol architecture comprising the agent-to-agent (A2A) and model context protocol (MCP). The A2A protocol enables secure, structured communication among specialized artificial intelligence (AI) agents (initiation, tracking, and reporting), while MCP provides standardized and isolated access to enterprise data sources. Civil2PM was trained and contextualized on 3500 real-world residential construction project cards, enabling it to autonomously generate project plans, track progress, issue communications, and update databases. By automating these processes, the system significantly reduces human errors in project coordination. A multi-phase evaluation with 11 medium and large construction enterprises demonstrated the system's capability to reduce coordination latency, improve schedule adherence, and eliminate dependence on costly cloud application programming interface (APIs). This work contributes a novel agentic-AI-driven architecture for residential construction sector, merging compact LLMs, multi-agent coordination, and secure local deployment to address pressing economic and operational challenges.
This paper presents a methodology for automating reverberation time prediction in university classrooms through a parametric building information modeling (BIM) model associated with the visual programming, integrating analysis, and optimization of acoustic performance, evaluating its accuracy by comparing results with survey data from two classrooms, considering geometry, occupancy, and materials. The model was enhanced into a data-enriched version, with acoustic data incorporated and later extracted to a spreadsheet for analysis. The results were submitted to statistical validation, attesting strong correlation despite minor discrepancies, confirming the model's reliability. The workflow demonstrates efficiency and reproducibility, contributing to acoustic simulation integration and providing validation criteria for future research from architects and engineers.
Autonomous mobile robots (AMRs) have demonstrated significant potential for addressing a variety of real-world applications, ranging from logistics and inspections to construction and service tasks. Although modern AMRs are equipped with advanced mobility and task execution capabilities, their deploymen t remains largely confined to repetitive and pre-defined processes with limited flexibility. The challenge lies in enabling robots to dynamically interpret missions, manage context-dependent variables, and autonomously activate their capabilities in complex and unstructured environments. This study presents Auto-Mission, a solution-oriented intelligent control methodology that bridges user-defined missions and autonomous execution for mobile robots. Unlike the capability-oriented research, which advances specific robotic technologies, Auto-Mission addresses the practical challenge for enabling end users to define and deploy autonomous missions without close human supervision. This method systematically integrates existing capabilities, navigation, localization, and task execution into a coherent framework that is platform-independent, with the platform adaptation required only at the mission execution layer. Auto-Mission is built on a location-based map framework, where a mission is defined as a list of destinations coupled with specific tasks to be performed at each location. By leveraging spatial and accessibility data from the map, Auto-Mission computes optimal navigation paths, simulates mission workflows, and manages the real-time execution of tasks. Unlike rigid pre-recorded automation schemes, Auto-Mission introduces adaptability by dynamically integrating robot states, environmental contexts, and mission-specific goals. The methodology is designed to be universally applicable across diverse AMR platforms, with the customization required only at the mission execution layer for robot-specific commands and operational data handling. This study details the architecture of Auto-Mission, its integration with mobile robotic systems, and its potential to significantly enhance the deployment flexibility of AMRs in practical applications.
This paper analyzes the current status and challenges of engineering digitalization and proposes a solution for building an artificial intelligence automated production line control platform for engineering “intelligent construction” (referred to as engineering production line control platform). It deeply explores the meaning and goals of the platform and innovatively puts forward the platform construction idea of “one database, one line, one factory”. This paper constructs a framework for the platform and verifies the feasibility of the overall solution through a case study of the digitalization of pumped storage power plants within a major construction group company. This paper provides valuable insights for promoting the construction, application, and promotion of integrated engineering digitalization.
The role of large language models (LLMs) in the architecture, engineering, and construction (AEC) sector has been increasing rapidly over the past few years, as they are being used as assistants, analyzers, and chat agents to optimize building designs through their context-based text-generation capabilities. In this paper, we present ProSpect, a software tool developed to capture architects' human-centered social design intentions (SDIs) by integrating building information modeling (BIM) and LLMs. The aim is to enable architects to clearly and explicitly integrate qualitative design intentions into BIM models. This work builds on our previously developed formalization framework, ProFormalize, which provides a domain-specific language to capture design intentions that particularly elicit human-centered criteria (e.g., curiosity and comfort). We present the development of ProSpect, following a co-creation approach and a case study-driven methodology that aim to empirically assess the validity of our framework and the usability of our software tool, comparing its LLM-based (latest) version with its wizard-based (previous) version. Our study shows that the LLM-based solution is more efficient at capturing and representing SDIs, achieving approximately 9% higher accuracy on trained prompts than on untrained ones.
To investigate the characteristics and propagation patterns of cracks in water diversion tunnels during operation, this study utilized tunnel engineering projects in southwestern China. Based on the intelligent inspection data for lining surface defects, combined with mechanical models and numerical simulation methods, the distribution characteristics and propagation processes of lining cracks under internal water pressure were analyzed. The results indicate that cracks are the primary defect type, with lengths concentrated in the range of 0–5 m, and are predominantly distributed at the top of the tunnel entrance section. Owing to the influence of the surrounding rock stress, the tunnel top becomes a high-risk area for crack initiation, and the local stress significantly increases after the lining cracks. Meanwhile, the circumferential stress exhibited a decreasing trend along the tunnel length, resulting in the formation of more cracks at the inlet. Numerical simulations show that the deformation of cracks at the top of the tunnel entrance is most severe, and the crack propagation follows a pattern of “depth extension-penetration through the lining-turn toward the inner wall”. The simulation results agree well with the mechanistic analysis of the inspection results.
With the rapid expansion of highway infrastructure, effective emergency management has emerged as a critical challenge for public transportation safety. Existing resource allocation methodologies are often inadequate for addressing highway incidents, particularly in mountainous regions characterized by complex geological conditions, dynamic weather patterns, and extensive bridge and tunnel networks. This study aims to investigate the intricate relationship between highway emergencies and personnel allocation by systematically identifying the key factors influencing resource distribution. Employing a sophisticated methodological approach, this study integrates the random forest (RF) model with cost management principles to comprehensively assess the significance of various influencing factors. The Shapley additive explanations (SHAP) theory is leveraged to quantify the nuanced contributions of individual factors to emergency staffing, thereby enhancing the interpretability of the model. Through one- and two-dimensional partial dependency plots, we conducted a detailed analysis of the correlations among the critical determinants. The research findings revealed macro-level traffic dynamics and established meaningful connections between specific emergency scenarios and targeted response strategies. By providing localized decision-making insights, this study establishes a robust analytical framework that bridges highway incident characteristics with coordinated emergency responses. Finally, we propose a comprehensive framework that offers high predictive accuracy, logical transparency, and practical adaptability in the highway emergency resource allocation.
The built environment plays a fundamental role in shaping human life and functioning. As key stakeholders throughout the building life cycle, humans both influence and are influenced by the built environment. Recently, there has been growing interest in human-centric approaches aimed at enhancing productivity, safety, and user experience. Among various methods for studying human factors in buildings, electroencephalography (EEG) has emerged as a powerful tool for capturing the real-time cognitive states. EEG provides valuable insights into critical issues such as mental fatigue, stress, attention, and emotional responses, with applications in safety management, work efficiency, decision-making, and occupant comfort. This paper first reviews fundamental EEG technologies and signal processing methodologies. Subsequently, by examining applications across distinct phases of the building life cycle, we evaluate EEG's potential applications and practical implementations in human-centric building research, synthesizing current advancements in study topics and experimental designs. Moreover, we identify the critical challenges hindering EEG adoption in building lifecycle management and propose practical mitigation strategies. The findings contribute to advancing the use of EEG in building life cycle management and provide valuable insights into how EEG can enhance building design, operation, and occupant satisfaction.
Road infrastructure is vital to Ethiopia's economic growth and regional integration, yet it faces persistent challenges such as resource limitations, stakeholder misalignment, and weak risk management. This study investigates the critical success factors (CSFs) affecting road construction performance in Dessie, Ethiopia, and explores the role of intelligent construction (IC) technologies in addressing these issues. A mixed-methods approach was adopted, beginning with qualitative interviews of 10 industry professionals, followed by a survey of 135 engineers, managers, and policymakers. Twenty-six CSFs were identified and grouped into six domains: resource, stakeholder, communication, risk, budget, and time management. Quantitative analysis using the relative importance index (RI) and reliability testing $(\alpha = 0.885)$ revealed the material quality, stakeholder trust, and timely procurement as the most influential factors. A hybrid project framework is proposed, integrating traditional methods with IC tools such as building information modeling (BIM), artificial intelligence (AI)-driven risk forecasting, and drone-assisted monitoring. The findings show that IC integration enhances planning accuracy, stakeholder coordination, and project resilience. This study presents a practical, adaptable model for improving construction performance in emerging economies and supports data-driven strategies aligned with local conditions. The results aim to inform policymakers, contractors, and planners working toward sustainable and technology-driven infrastructure development in Ethiopia.
Solid gravity energy storage (SGES) is a method of energy storage technology that combines the prospects of operation safety, cost-effectiveness, and adaptive application. There are different systems within the SGES technology, which are grouped into three categories: mountain gravity energy storage (MGES), under-ground cavern energy storage (UCES), and structural building energy storage (SBES). However, there is a lack of studies comparing the round-trip efficiency of these SGES systems. To address this issue, this study first conducted academic review on differing SGES technologies, and simplified physical models were established to derive corresponding theoretical equations for determining the round-trip energy storage efficiency. Then, primary factors of influence on energy storage efficiency along with technical benefits and drawbacks of each system were then analyzed, revealing a variety of possible effects on efficiency and how to best utilize each SGES system, based on theoretical data.
With the rapid expansion of hydropower projects, the safety and stability of hydraulic tunnels have become critical challenges. Traditional deformation monitoring and disaster prevention methods are insufficient for addressing the growing lengths of tunnels, large diameters, high water pressures, and complex geological conditions. An investigation of technologies designed to enhance the construction, operation, and maintenance of tunnels in complex environments has been systematically conducted. The research addresses three primary aspects: (1) the coordinated deformation mechanisms and failure modes of the rock-lining system, in which a novel nonlinear reinforcement program has been developed to optimize support design and reduce unnecessary reinforcement; (2) the improvement of intelligent monitoring systems, where multisensor fusion and artificial intelligence (AI)-based predictive analysis have been integrated to enhance real-time data acquisition and feedback accuracy; (3) the advancement of intelligent disaster prevention through robotic inspection technologies and digital twin (DT)-based risk assessment. The integration of emerging technologies, such as machine learning, automation, and real-time structural monitoring, significantly enhances tunnel stability and operational efficiency. Despite these advancements, further research is needed to refine multiscale modeling techniques, enhance AI-driven monitoring systems, and develop more adaptive robotic inspection solutions to ensure the long-term safety and sustainability of tunnels.
Rocks are heterogeneous by nature, and the assumption of homogeneity cannot accurately explain the microscopic mechanism underlying macroscopic phenomena correctly. Digital core technology captures the geometrical structure of rocks at the microscale, providing an important tool for the quantitative characterization and multiscale study of the physical and mechanical properties of rocks. This review summarizes the process of the digital core construction method in sequence, covering imaging technology, image processing, and reconstruction. The benefits and drawbacks of the involved methods are compared. Furthermore, the application of the digital core in numerical modeling for rock mechanics is reviewed. Although extensive efforts have been made in digital core reconstruction and its application, several challenges remain to be addressed. On the basis of this review, future research will likely focus on the development of large-scale and high-precision digital cores, integrating them with advanced constitutive models, multiphysics fields, and three-dimensional (3D) printing technology to further improve their credibility.
Building information modeling (BIM) and robotic technologies are revolutionizing the construction industry. The integration of BIM and robotics has the potential to enhance workforce skills, improve safety, and optimize construction processes. However, despite these promising benefits, a significant gap in systematic reviews on applying this integration within the industry is evident. This research addresses this crucial gap through a comprehensive and rigorous systematic literature review following the preferred reporting items for systematic review and meta-analysis (PRISMA) methodology. In our search within the Web of Science (WoS) database using a detailed search query, we identified 200 articles. After applying specific inclusion and exclusion criteria, we selected 22 papers for review. This paper thoroughly examines the current applications of BIM and robotics in construction, focusing on specific scenarios where these technologies converge. It also delves into the mechanisms of data transfer, both real-time and otherwise, highlighting how BIM and robotics interact, and the efficiency gains achieved through their integration. Additionally, the paper explores future research directions, challenges, and opportunities within this domain, aiming to provide insights into how these emerging technologies can continue to evolve and address the construction industry's forthcoming needs.
To address potential uncertainties and disruptions in the production process of prefabricated components that may lead to supply delays or interruptions, this study evaluates the logistics resilience of prefabricated buildings, aiming to increase their adaptability and risk resistance in the face of uncertainty and unexpected events. To this end, this study employs a systematic literature review (SLR) to establish a logistics resilience evaluation index system, encompassing predictive capability, responsiveness, adaptability, recovery capability, and learning ability. Decision-making trial and evaluation laboratory (DEMATEL) is subsequently used to determine the weight of each indicator, which is combined with the preference ranking organization method for enrichment of evaluations II (PROMETHEE II) model for multicriteria decision analysis (MCDA) to construct a logistics resilience evaluation study for prefabricated buildings. Finally, four representative prefabricated building projects are selected for analysis to calculate the logistics resilience of prefabricated buildings. The study results indicate that the logistics resilience ranking of the target projects is as follows: Project A > Project C > Project B > Project D, indicating that the resilience of Projects A, C, B, and D decreases sequentially when facing uncertain events. This study demonstrates that rational logistics resilience evaluation and optimization can significantly improve construction efficiency and overall risk resistance in prefabricated building projects.
Generative artificial intelligence (GenAI) is seen as an efficient way to enhance architecture, engineering, and construction (AEC) organizations through the generation of novel content and the automation of processes and tasks. Rapid advancement in GenAI is giving rise to new potential applications in AEC organizations, and this requires a detailed understanding and a strategic planning technique to evaluate the usefulness of GenAI to organizations. This study aims to address this gap by examining GenAI literature in the AEC industry to determine how GenAI contributes to the enhancement of AEC organizations. To achieve the aim, this article identifies how GenAI is used in AEC organizations, and proposes a strengths-weaknesses-opportunities-threats (SWOT) process and elements for the strategic evaluation of GenAI in AEC organizations. The research methodology consists of a systematic review process. The findings categorized 79 journal articles and conference papers, which revealed that GenAI was being explored to create architectural and structural designs of buildings, optimize construction processes, and enhance risk management and work safety. There are limitations in the capability of GenAI models to meet project management needs. These include low quality datasets used for training, cost, time, and computation resources required to implement GenAI effectively, and ethics and privacy issues when using GenAI in AEC organizations and projects. Additionally, a SWOT process is proposed, and twenty SWOT elements are developed and described: four elements for strengths, five elements for weaknesses, five elements for opportunities, and six elements for threats. The proposed elements aim at providing a foundation for AEC organizations to assess and achieve their strategic GenAI implementation goals. This article identifies the areas of research focus along with a SWOT process and elements that may be useful to researchers and industry practitioners focusing on GenAI and SWOT in the AEC industry.
To increase the printing and mechanical performance attributes of three-dimensional-printed concrete (3DPC), fiber addition has proven to be a highly effective method. Among various fiber types, glass fibers have been explored for use in 3DPC because of their favorable properties and affordability. However, detailed studies on the impacts of glass fibers, especially the impact of fiber length on the performance of 3DPC, remain limited. In this research, 3D-printed mortar (3DPM) mixtures with varying water-to-cement (W/C) ratios (0.24–0.32) and glass fiber lengths (5.00–25.00 mm) were prepared to examine their printability and mechanical performance. The findings revealed that a suitable reduction in the W/C ratio positively influences printability and strength. Crucially, an increase in the glass fiber length notably increased the extrudability, dimensional stability, and buildability, increasing the flexural strength by approximately 75.0% but causing a maximum decrease in the compressive strength of approximately 22.0%. A comparison of the strengths of the printed and casted samples revealed that the extrusion and stacking processes had a profound influence on both the flexural and compressive strengths, with the flexural strength potentially increasing by 92.6% and the compressive strength decreasing by up to 46.8%. This suggests that engineering applications of glass fiber-reinforced 3DPC shall consider decreased compressive strength, and methods such as reducing the W/C ratio and using strength-boosting admixtures may be applied.
