Search Results (94)

Construction sites report the highest rate of industrial accidents, prompting the active development of smart safety management systems based on deep learning-based computer vision technology. To support the digital transformation of construction sites, securing site-specific datasets is essential. In this study, raw data were collected from an actual earthwork site. Key construction equipment and terrain objects primarily operated at the site were identified, and 89,766 images were processed to build a site-specific training dataset. This dataset includes annotated bounding boxes for object detection and polygon masks for instance segmentation. The performance of the dataset was validated using representative models—YOLO v7 for object detection and Mask R-CNN for instance segmentation. Quantitative metrics and visual assessments confirmed the validity and practical applicability of the dataset. The dataset used in this study has been made publicly available for use by researchers in related fields. This dataset is expected to serve as a foundational resource for advancing object detection applications in construction safety. Full article

To overcome the absence of a standardized budget quota system for high-standard farmland projects and the resultant extended compilation cycles and high workloads, this study systematically analyzes quota consumption and innovatively proposes an integrated DEMATEL-ISM-BN and gray clustering analytical model. Through a literature review and engineering feature analysis, a hierarchical factor system was established, encompassing six dimensions (environmental, technical, labor, machinery, material, and management) and 24 indicators. The DEMATEL-ISM method quantified factor weights and structured them into a five-level hierarchy, while Bayesian networks (BNs) enabled probabilistic productivity predictions (29% conservative, 45% moderate, and 26% advanced). Gray clustering was integrated to derive a comprehensive representative consumption value, and validation across six regions demonstrated a comprehensive productivity index of 0.986 (CV = 2.6%) for 17 earthwork projects, confirming model robustness. This research constructs a standardized “factor structure analysis–probabilistic deduction–regional clustering” framework, providing a theoretical foundation for precise budget compilation in high-standard farmland and proposing a novel methodological paradigm for quota consumption research. Full article

Autonomous earthwork machinery is gaining traction as a means to boost productivity and safety on space-constrained urban sites, yet the fast-growing literature has not been fully integrated. To clarify current knowledge, we systematically searched Scopus and screened 597 records, retaining 157 peer-reviewed papers (2015–March 2025) that address autonomy, integrated control, or risk mitigation for excavators, bulldozers, and loaders. Descriptive statistics, VOSviewer mapping, and qualitative synthesis show the output rising rapidly and peaking at 30 papers in 2024, led by China, Korea, and the USA. Four tightly linked themes dominate: perception-driven machine autonomy, IoT-enabled integrated control systems, multi-sensor safety strategies, and the first demonstrations of fleet-level collaboration (e.g., coordinated excavator clusters and unmanned aerial vehicle and unmanned ground vehicle (UAV–UGV) site preparation). Advances include centimeter-scale path tracking, real-time vision-light detection and ranging (LiDAR) fusion and geofenced safety envelopes, but formal validation protocols and robust inter-machine communication remain open challenges. The review distils five research priorities, including adaptive perception and artificial intelligence (AI), digital-twin integration with building information modeling (BIM), cooperative multi-robot planning, rigorous safety assurance, and human–automation partnership that must be addressed to transform isolated prototypes into connected, self-optimizing fleets capable of delivering safer, faster, and more sustainable urban construction. Full article

Earthwork construction presents significant challenges due to its unique characteristics, including irregular topography, inhomogeneous geotechnical properties, dynamic operations involving heavy equipment, and continuous terrain updates over time. Existing methods often fail to accurately capture these complexities, support semantic attributes, simulate realistic equipment–environment interactions, and update the model dynamically during construction. Moreover, most current digital solutions lack an integrated framework capable of linking geotechnical semantics with construction progress in a continuously evolving terrain. This study introduces a novel, voxel-based digital twin framework tailored for earthwork construction. Unlike previous studies that relied on surface, mesh, or layer-based representations, our approach leverages semantically enriched voxelization to encode spatial, material, and behavioral attributes at a high resolution. The proposed framework connects the physical and digital representations of the earthwork environment and is structured into five modules. The data acquisition module gathers terrain, geotechnical, design, and construction data. Virtual models are created for the earthwork in as-planned and as-built models. The digital twin core module utilizes voxels to create a realistic earthwork environment that integrates the as-planned and as-built models, facilitating model–equipment interaction and updating models for progress monitoring. The visualization and simulation module enables model–equipment interaction based on evolving as-built conditions. Finally, the monitoring and analysis module provides volumetric progress insights, semantic material information, and excavation tracking. The key innovation of this framework lies in multi-resolution voxel modeling, semantic mapping of geotechnical properties, and supporting dynamic updates during ongoing construction, enabling model–equipment interaction and material-specific construction progress monitoring. The framework is validated through real-world case studies, demonstrating its effectiveness in providing realistic representations, model–equipment interactions, and supporting progress information and operational insights. Full article

Optimized earth-rock allocation is key in the construction of large-scale navigation channel projects. This paper analyzes the characteristics of a large-scale navigation channel project and establishes an earth-rock allocation system in phases and categories without a transit field. Based on the physical characteristics of the earthwork and stonework used to design a differentiated transport strategy, a synergistic optimization model is built with economic and ecological benefits. As a solution, this paper proposes a sustainable earth-rock allocation optimization method that integrates the improved ant colony algorithm and firefly algorithm, and establishes a two-stage hybrid optimization framework. The application of the Pinglu Canal Project shows that ant colony optimization via division and cooperation combined with the firefly algorithm reduces the transportation cost by 0.128% compared with traditional ant colony optimization; improves the stability by 57.46% (standard deviation) and 59.09% (coefficient of variation) compared with ant colony optimization through division and cooperation; and effectively solves the problems of precocious convergence and local optimization of large-scale earth-rock allocation. It is used to successfully construct an earth-rock allocation model that takes into account the efficiency of the project and the protection of the ecological system in a dynamic environment. Full article

Smart construction technology integrates artificial intelligence, Internet of Things, UAVs, and building information modeling to improve productivity and quality in construction. In road embankment earthworks, ground compaction quality is critical for structural stability and maintenance. This study proposes a methodology combining UAV photogrammetry with intelligent compaction quality management systems to evaluate surface flatness and compaction homogeneity in real-time. High-resolution UAV images were used to generate digital elevation models, from which surface roughness was extracted using terrain element analysis and fast Fourier transform. Local terrain changes were interpreted through contour gradient, outline gradient, and tangential gradient curvature analysis. Field tests were conducted at a pilot site using a vibratory roller, followed by four compaction quality assessments: plate load test, dynamic cone penetration test, light falling weight deflectometer, and compaction meter value. UAV-based flatness analysis revealed that, when surface flatness met the standard, a strong correlation was observed, with results from conventional field tests and intelligent compaction data. The proposed method effectively identified poorly compacted zones and spatial inhomogeneity without interrupting construction. These findings demonstrate that UAV-based terrain analysis can serve as a nondestructive real-time monitoring tool and contribute to automated quality control in smart construction environments. Full article

Excavator operations play a critical role in the productivity of earthworks, yet traditional methods often rely heavily on operators’ intuition and experience, which can lead to inconsistent outcomes. This study investigates how machine guidance (MG) providing real-time feedback relating to excavation depth and slope can modify operators’ actions and improve performance compared with conventional excavation methods. A controlled experiment was conducted at an active construction site, in which four footings were excavated using the two approaches under similar conditions. The results demonstrated that MG excavation reduced the total duration of the work from 3650 s to 2652 s and decreased the number of excavation cycles from 68 to 57, underscoring the impact of timely, precise guidance on efficiency. Moreover, the average fill factor improved from 3.04 under conventional methods to 3.47 with MG, suggesting more consistent and optimal loading of the bucket. These findings confirm that real-time feedback can enhance operator confidence, reduce unnecessary movements, and foster systematic excavation strategies. This study thus provides empirical evidence that MG can significantly optimize excavation performance, highlighting the need for broader adoption of this technology in modern construction practices. Full article

With advancement in Unmanned Aerial Vehicle (UAV) photogrammetry, productivity in construction management can now be achieved with accuracy and is less labour-intensive. In the basement construction of buildings, prudent earthwork activities are often necessary, setting the basis of the building footprint. As such, monitoring earthwork volume estimation becomes important to avoid over- or under-cutting the earth. Conventional methods by means of land surveying are time-consuming, labour-intensive, and susceptible to varying degrees of accuracy. Moreover, earthwork sites often have multiple activities ongoing that increase the complexity of volume estimation through land surveying. This study explores the use of UAV photogrammetry to estimate earthwork excavation volume in a complex urban earthwork site in Singapore over time and discusses the feasibility, challenges and productivity enhancements of integrating the technology into the construction process. In this study, the earthwork site and controlled trials show that the models reconstructed with UAV photogrammetry data can produce volume measurements that fulfil the stakeholder’s accuracy tolerance of 5% between the estimated and actual volume. The filtering of unwanted objects in the model, such as columns, cranes and trucks, was successful but was insufficient for objects that occluded large areas of the soil surface. The integration of UAV photogrammetry with a highly automated acquisition and processing workflow for earthwork monitoring brings about productivity enhancements in time and labour efforts and improves the efficiency and consistency of models. Furthermore, the digitalisation of earthwork sites into point clouds and three-dimensional (3D) models increases data visualisation and accessibility, facilitates project team collaboration, and enables cross-platform compatibility into Building Information Modelling (BIM), which can significantly aid in reporting and decision-making processes. Full article

The productivity of the construction industry is about half that of the manufacturing industry, and the labor shortage in the construction industry is serious; therefore, improving productivity using information and communication technology (ICT) is an urgent issue. In addition, in civil engineering works, the number of projects that handle multiple types of soil and sand is increasing due to the recycling of construction waste soil; thus, traceability management is important to ensure quality. This paper presents a system that uses sensing on soil-transporting dump trucks and ICT to record which soil was piled up where with the aim of improving the efficiency of traceability management in earthwork construction. This system automatically creates traceability data by linking sensing data and data from the compaction management system via an application. This eliminates the need to record and manage the earthwork location, which was previously required manually to create traceability data, and reduces the labor and manpower required for traceability management. The created traceability data are automatically assigned attribute information such as the construction date and soil information; consequently, they can be used to check the construction history in the future. Full article

Geoenvironmental engineered barriers, such as geotechnical and hydraulic layered structures called liners, are essential for protecting the environment from pollution. Liners are usually compacted clay liners (CCL), geomembranes (GM), geosynthetic clay liners (GCL), or a combination of these liners (composite liners), which require significant attention concerning materials, techniques, and procedures to perform adequately. This work reviews the function of geotechnical and hydraulic barriers as liners and highlights the lack of investigation and problematic aspects of them. In addition, the work provides an overview of the literature around earthworks which are liners’ specific configurations, such as landfills, dams, ponds, wastewater lagoons, and vertical barriers. Furthermore, the main investigations, issues, and perspectives are demonstrated, and are discussed alongside the trending research areas and sustainable new materials. This work highlights different directives in several countries for liner construction standards and testing program specifications, analyzing their economic aspects. The main studies on the subject have been compiled, and a bibliometric analysis was performed. Thus, this paper concludes by pointing out gaps in the research regarding alternative materials and structures within geoenvironmental investigations on liners, and signposts future scientific threads related to sustainable development. Full article

The modern construction of transmission networks for transporting energy resources (e.g., crude oil, gas, hydrogen) or electricity is increasingly being carried out using trenchless technologies. Trenchless methods significantly reduce the need for extensive earthworks; however, they consequently generate substantial amounts of drilling waste. This waste consists primarily of a mixture of spent drilling fluids and drill cuttings. Due to the volume and composition of the waste, along with the rapidly increasing costs of waste disposal, the trenchless technology industry faces significant economic and environmental challenges related to circular economy principles in waste management. This article presents an analysis of trenchless construction methods for underground transmission networks, with particular emphasis on the quantity and quality of the generated drilling waste. Furthermore, research is conducted to develop a cationic flocculant based on polyvinylamine, designed to eliminate the harmful coagulants in drilling waste treatment technology. Based on the conducted studies, we propose a closed-loop waste management system for trenchless technologies. The implementation of circular economy principles, along with the integration of drilling fluid treatment systems with photovoltaic panels and energy storage units, enhances the energy efficiency of drilling waste treatment processes and aligns with global trends in the adoption of renewable energy sources (RESs). Full article

Green construction evaluation systems can assist building stakeholders in scientifically evaluating the carbon emission performance of construction projects. However, most green construction evaluation tools and methods fail to explicitly incorporate construction carbon emission indicators, let alone a quantitative evaluation. Therefore, this study proposes a carbon emission evaluation system based on the entropy–TOPSIS and K-means methods for foundation construction projects. In this study, we innovatively divided the carbon emission of the foundation construction process into three phases, namely, transportation emission, excavation and earthwork emission, and pile work emission, considering their different emission characteristics and reduction difficulties by nature. Different from traditional carbon evaluation methods, the carbon emission of the three phases were evaluated separately against the baseline value obtained from local construction quota. After that, the emission performance of the three phases was weighted and evaluated based on the entropy–TOPSIS method, and then rated via the K-means method. Based on a case study of 19 residential buildings, the weights of the three construction phases were 27.66% (transportation), 42.34% (excavation and earthwork), and 29.99% (pile work). The carbon performance of the 19 cases were rated by the K-means method into four levels: six cases were rated “Excellent”, five were rated “Good”, five were rated “Fair”, and three were rated “Poor”. The proposed method was expected to objectively and scientifically evaluate and rate the carbon emission of the foundation construction process, and provided a theoretical basis for decision makers to identify emission hotspots and formulate specific carbon reduction measures. Full article

The modern construction industry is undergoing considerable changes driven by increased specialization, technological advancements, and growing complexity. The integration of smart construction technology is rapidly advancing as a solution to address the aging workforce in the sector. However, the uncertainty and risks associated with soil construction on job sites remain, leading to increased costs during project execution. Recently, construction sites have sought to enhance productivity by leveraging building information modeling (BIM) and smart construction devices. The adoption of smart equipment, such as machine control and machine guidance, is on the rise in both structural and earthwork projects, with ongoing efforts to mitigate uncertainties. This study proposes a practical approach to reduce the uncertainty in earthworks by optimizing soil sharing strategies and equipment allocation from the initial design phase. A BIM model was developed as a solid structure and then segmented using Dynamo. This model was utilized to create a construction plan using Primavera P6, while AnyLogic (8.9.2) was employed to assess the suitability of equipment combinations, ultimately demonstrating the cost-saving benefits of the proposed approach. Through repeated simulations, work efficiency was enhanced by approximately 6.2% compared to the original 2D planning approach. Full article

Accurate earthwork quantity estimation is essential for effective project planning and cost management in the Architecture, Engineering, and Construction (AEC) industry. Traditional methods for quantity takeoff are often time-consuming and susceptible to human error, particularly when working with unstructured datasets such as CAD drawings. This study introduces the Earthwork Network Architecture (ENA), a novel deep learning framework that incorporates Large Language Models (LLMs), Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM) networks, and Transformers to automate and enhance the accuracy of earthwork quantity estimation. We assume that if LLMs can be trained effectively using such unstructured construction dataset, the effects such as improved accuracy and the challenges of LLMs can be clearly examined. Among the architectures tested, the LLM-based ENA demonstrated superior performance, achieving faster convergence, greater loss reduction, and higher classification accuracy, with a Quantity Takeoff Classification accuracy of 97.17%. However, the LLMs required significantly more computational resources compared with other models. These findings suggest that LLMs, typically used in natural language processing, can be effectively adapted for complex AEC datasets. This study lays the groundwork for future AI-driven solutions in the AEC industry, underscoring the potential of LLMs and Transformers to automate the quantity takeoff process and manage multimodal data in construction projects. Full article

Earthwork operations are critical to construction projects, with their safety and efficiency influenced by factors such as operator skill and working hours. Pre-construction simulation of these operations is essential for optimizing outcomes, providing key training for operators and improving safety awareness and operational efficiency. This study introduces a hierarchical cumulative reward mechanism that decomposes complex operational behaviors into simple, fundamental actions. The mechanism prioritizes reward function design elements, including order, size, and form, thus simplifying excavator operation simulation using reinforcement learning (RL) and enhancing policy network reusability. A 3D model of a hydraulic excavator was constructed with six degrees of freedom—comprising the boom, arm, bucket, base, and left/right tracks. The Proximal Policy Optimization (PPO) algorithm was applied to train four basic behaviors: scraping, digging, throwing, and turning back. Motion simulation was successfully achieved using diggable terrain resources. Results demonstrate that the simulated excavator, powered by RL neural networks, can perform coordinated actions and maintain smooth operational performance. This research offers practical implications by rapidly illustrating the full operational process before construction, delivering immersive movies, and enhancing worker safety and operational efficiency. Full article