Search

Industry 4.0 has the potential to revolutionise design-to-fabrication processes in the Architecture, Engineering, and Construction (AEC) industry. However, early adoption of Industry 4.0 technology has led to challenges related to data consistency, interoperability, and collaboration among stakeholders. To address these challenges of interoperability and standardisation, this paper introduces a digital thread-based framework for integrating Industry 4.0 concepts into design-to-fabrication processes. At the framework's core are digital threads, which connect physical assets with their digital twin models, communication networks, and decision algorithms. More specifically, the framework comprises a modular and scalable fabrication data schema combined with a comprehensive services software architecture that leverages fabrication design, management, and control tools. The framework was evaluated through a large-scale case study, the livMats Biomimetic Shell. The case study results demonstrate an improvement in collaboration and communication among stakeholders, reduction of errors in the robotic fabrication process and increased efficiency throughout the design-to-fabrication process. By embracing and implementing the digital thread concept, this research showcases the benefits of data-driven decision-making within the construction sector. • A framework linking physical assets, digital models, communication networks, and decision algorithms through digital threads. • A task data schema is proposed to create a shared language between design and fabrication. • Evaluation of the framework through large-scale timer shell design-to-fabrication process. • Regression models are used to learn and predict future design-to-fabrication processes and inform stakeholders. [ABSTRACT FROM AUTHOR]

Scientific contributions to BIM-sustainability integration have gained momentum in recent years due to the influential role of BIM as a well-accepted approach for sustainable construction practices. In this regard, some systematic reviews and informatic analysis papers have addressed this topic. Although these papers have provided useful insights, we go deeper into the body of knowledge through a critical lens. In addition, in this paper, keyword combination is broadened as opposed to other reviews, and critical insight is applied to synergies between BIM and sustainability through gap-spotting. For this purpose, 98 journal articles are selected and grouped into four major categories, namely: (i) BIM-based Life-Cycle Sustainability Assessment (LCSA); (ii) BIM for green buildings; (iii) BIM-aided construction waste management; (iv) state-of-the-art topics. The work's novelty lies in giving a holistic understanding of previously dismissed issues and a critical area review. Finally, the research gaps and future opportunities are discussed and tabulated. [Display omitted] • 543 articles on BIM and sustainability are analysed, deploying critical review and gap-spotting techniques. • The application of BIM in all sustainability dimensions is critically discussed. • BIM-LCA and BIM-LCC have received the most attention in synergy between BIM and sustainability. • BIM-Sustainability integration is rarely implemented in infrastructure projects. • This paper can be expanded into open-BIM to address some of the data-interoperability difficulties. [ABSTRACT FROM AUTHOR]

Creation of road and railway routes in general and also design of vertical alignment in particular constitute an significant engineering problem. The vertical alignment of roads, and especially of railways, is of great importance for passenger comfort under high-speed driving conditions. This requires alignment smoothness to a greater extent. In practice, the dominant tendency is to consider vertical arcs as parabolic curves (quadratic or cubic). Other solutions have been also proposed and analyzed in the literature, thus providing an alternative approach to traditional methods. This paper describes a design method of vertical arcs using the so-called general transition curves. These curves describe the entire curvilinear transition between two straight lines using a single equation, and the curvature at the contact points with the straight lines is zero, which is of great practical significance in the light of vehicle motion dynamics. As a result, relevant research shows that general transition curves, compared to other curves, provide a more favorable distribution of lateral changes of acceleration. The paper deals not only with appropriate design procedures of a general nature, but also specific procedures of fitting vertical arcs to preset points. The methods for designing vertical arcs constitute a useful extension of available methods, and offer a valuable tool for engineers and designers of road and railway routes. • a new approach to the design of vertical arcs was presented • the proposed approach is based on the use of so-called general transition curves • these curves are the original design tool and describe the entire transition between two straight lines with one equation • the proposed approach is algorithmic and can be very useful in computer-aided design [ABSTRACT FROM AUTHOR]

The Architecture, Engineering, Construction and Owner-operated (AECO) industry faces an array of productivity challenges, in part stemming from limited interoperability and suboptimal management of building information across project lifecycles. This paper investigates the application of rule-based systems from the manufacturing industry, especially as used in the semiconductor manufacturing sector, to improve productivity in the AECO industry. A comparative methodology is employed, examining processes in both the manufacturing and AECO industries. The results indicate that methodologies from semiconductor mask manufacturing can be effectively adapted for use in the AECO industry, particularly in design for buildability and standardized rule application. This paper includes the implementation of a Proof-of-Concept (POC) for Manufacturing Rule Check (MRC) in the AECO industry, focusing on Prefabricated Bathroom Units (PBU) production. The MRC developed for the POC could be integrated into the Model Checker platform of Singapore's CORENET X regulatory approval system, as well as deployed as a specialized application in the cloud that facilitates ease of collaboration among the design to fabrication players in the construction process. • Conducted a comparative analysis between semiconductor and AECO processes • Implemented Manufacturing Rule Check system focused on prefabricated bathrooms • Enhanced BIM and IDD interoperability with rule-based checking on regulatory platforms • Demonstrated the significance of adopting IDD to streamline AECO workflows [ABSTRACT FROM AUTHOR]

Construction robotics has emerged as a leading technology in the construction industry. This paper conducts an innovative dual-track quantitative comprehensive method to analyze the current literature and assess future trends. First, a bibliometric review of 955 journal articles published between 1974 and 2023 was performed, exploring keywords, journals, countries, and clusters. Furthermore, a neural topic model based on BERTopic addresses topic modeling repetition issues. The study identifies building information modeling (BIM), human–robot collaboration (HRC), and deep reinforcement learning (DRL) as "three pillars" in the field. Additionally, we systematically reviewed the relevant literature and nested symbiotic relationships. The outcome of this study is twofold: first, the findings provide quantitative and qualitative scientific guidance for future research on trends; second, the innovative dual-track quantitative analysis research methodology simultaneously stimulates critical thinking about the modeling of other similarly trending topics characterized to avoid high degree of homogeneity and corpus overlap. [Display omitted] • Previous AEC research has lacked a comprehensive macrolevel methodology. • A dual-track analysis method based on neural and SNA modeling is proposed. • The analysis of 995 journal papers revealed three pillars of construction robotic trends. • BIM, the HRC, and DRL were identified as the three crucial pillars in the field. • The outcome offers quantitative and qualitative assessments guiding future research. [ABSTRACT FROM AUTHOR]

This paper analyzed how different visual environments (i.e., normal, glare, dark, and dusty environments) affect construction equipment operators' struck-by hazards. To achieve this objective, an experiment using eye-tracking technology was conducted in screen-based virtual environments to measure and statistically analyze three types of data affecting struck-by hazards: (i) hazard detection abilities; (ii) eye-tracking data; and (iii) psychological responses. The results revealed that visual environments significantly influenced all types of data, particularly environments characterized by low illuminance and low luminance contrast, which notably impaired hazard detection abilities. These results emphasize the importance of considering the visual environment to prevent struck-by hazards and suggest the feasibility of using physiological and psychological indicators as measures of hazard detection abilities. This paper is a steppingstone for future research into optimizing visual environments for enhanced safety in construction sites by preventing struck-by hazards. • Visual environments' impact on struck-by hazards was studied in virtual environments. • Hazard detection abilities were measured with eye-tracking and psychological data. • Three types of data were analyzed using the Friedman test and correlation analysis. • Dark environments with low luminance and contrast were most vulnerable to hazards. • Eye-tracking data can be used as a biomarker to indicate hazard detection abilities. [ABSTRACT FROM AUTHOR]

Optimizing construction labor productivity is a challenge due to the inherent uncertainties of construction projects. While increasing the workforce size is often perceived as a strategy to enhance productivity, it can lead to increased physical interactions and workspace interference. This paper presents a framework for assessing the construction productivity, taking into account spatial constraints, labor interactions, and the dynamic nature of the workspace. The proposed model effectively captures the influence of workforce dynamics on construction activity productivity by integrating two techniques: Discrete-Event Simulation (DES) and Social Force Modeling (SFM). DES replicates the workflow, while SFM simulates worker interactions and movements. A real-world case study validates the model's ability to simulate construction scenarios realistically. The model can effectively capture how productivity varies depending on the number of workers, workspace layout, and project progress. The model can empower engineers with valuable insights into labor productivity optimization, leading to more efficient construction projects. • This paper tries to introduce a platform that consists of Discrete Event Simulation (DES)- Social Force Modeling (SFM). • It is aimed to determine the optimum number of workers in a construction site by considering workspace limitation, interactions between labor, and dynamic construction environment. • A hybrid model that integrates DES and SFM is developed. DES is used to simulate the work process, and the SFM method is used to simulate workers' physical interactions and movement. [ABSTRACT FROM AUTHOR]

Despite ongoing research in Architectural, Engineering, Construction and Operations (AECO), little is understood about BIM's interaction with its adoption process. This paper conducts a comprehensive scoping review that utilises secondary data to systematically map the existing literature on the adoption of BIM within AECO organisations. A literature review identified 146 papers on BIM in AECO organisations, categorising them into 46 on pre-adoption, 85 on post-adoption, and 15 on both phases. Findings reveal a tendency towards a 'tunnel vision', isolating a single organisational aspect or adoption phase. However, the study finds that BIM significantly interacts with various organisational elements, such as environment, power dynamics, social structure, and culture, necessitating comprehensive changes and strategies both before and after adoption. Advocating for a holistic approach, the study emphasises integrating change management, continuous learning, and ongoing improvement in BIM implementation. This perspective is a significant contribution to understanding BIM's multifaceted impact in AECO organisations. [Display omitted] • Challenges in fully transitioning to BIM, result in untapped potential. • The organisational environment, power dynamics, social structure, and culture for BIM adoption are currently overlooked. • Reveals the intricate interaction of organisations and BIM throughout the transformative process. • Identifies knowledge gaps, provides a research agenda cube, offers valuable guidance for future studies. [ABSTRACT FROM AUTHOR]

This paper delves into the innovative realm of 3D wall printing, employing large-scale printers to construct walls layer by layer and aiming to revolutionize traditional house construction. The review comprehensively explores the properties of 3D printed walls in both fresh and hardened states, covering aspects like failure modes, quality control, mechanical and non-structural properties, seismic response, and reinforcement techniques. Taking a distinctive perspective, it draws parallels between 3D printing concrete and masonry structures, presenting them as a modernized version of traditional construction. Overlooking aspects like various wall cross-sections, connections to other structural elements (i.e., wall-to-wall, wall-to-roof, wall-to-foundation connections), non-structural wall intersections, and reinforcement techniques are addressed, crucial for successful integration into large-scale projects. The review serves as a cautionary guide to researchers, shedding light on less-explored areas in large-scale 3D wall printing and providing insights for future research directions and potential codes and standards drawing inspiration from masonry walls. [Display omitted] • This study explores 3D wall printing to gather insights into the implementing innovative technology in house construction. • This paper reviews the material's properties and structural integrity to enhance printed walls' efficiency and functionality. • This paper aims to evaluate the performance of 3D-printed walls according to standards for masonry structures. • This review focuses on three pivotal aspects: geometry, reinforcement needs, and essential connection details for walls. [ABSTRACT FROM AUTHOR]

The detection of fastener defects is crucial for ensuring the safety and reliability of high-speed train operations. This paper proposes an intelligent algorithm named YOLO-Fastener for detecting fastener defects in ballastless track systems. The proposed YOLO-Fastener incorporates efficient channel and spatial attention mechanisms, enhancing the extraction of crucial features related to fastener defects. Decision regions of the model in identifying fastener defects are visualized through heatmaps. The model is trained and tested on a limited dataset of high-resolution fastener images collected by a ballastless track detection vehicle equipped with 3-D laser devices. The results show that the precision and recall of the proposed model on the test set are 98.33% and 99.15%, which are 1.63% and 4.81% higher than those of the advanced Faster R-CNN model. In terms of fastener detection efficiency, the proposed model is the fastest with an inference time of 10.4 ms, which is an 18.75% improvement over the result of the advanced YOLOv7 model. • The paper proposes an intelligent algorithm named YOLO-Fastener for detecting fastener defects. • A high-resolution dataset of fastener defects is collected by a ballastless track detection vehicle. • The ECSA module has been developed to extract more crucial fastener defect features. • The GhostConv and RepConv modules are employed to reduce model parameters and increase inference speed. [ABSTRACT FROM AUTHOR]

Radio Frequency Identification (RFID) systems have remarkable potential to be used in the supply chain management systems of the construction industry. RFID's ability to identify, track and locate objects provides tremendous flexibility in planning and operation of the industry. Consequently, RFID systems can contribute to on-time project completion, cost savings, enhanced reputation, and avoidance of regulatory fines. Moreover, RFID enhances visibility into inventory, equipment, and workforce, ensuring real-time safety measures. This paper conducts an in-depth analysis of state-of-the-art RFID detection and localization techniques, identifying gaps specific to the construction sector. The paper proposes the integration of emerging technologies, with a particular focus on the Internet of Things (IoT) and security mechanisms. This integration aims to solve challenges in using RFID systems in the construction industry's supply chain. It promises to enhance efficiency, security, and effectiveness of RFID technology, leading to a more efficient and resilient supply chain management system. [Display omitted] • Provides an in-depth analysis of state-of-the-art RFID detection and localization techniques, uncovering gaps and limitations specific to construction, and proposing innovative solutions. • Discovers how RFID, combined with emerging technologies like IoT, enhances supply chain efficiency and resilience, addressing specific challenges unique to the construction sector. • Addresses security concerns related to RFID localization and proposes a practical solution tailored to the construction industry's needs. [ABSTRACT FROM AUTHOR]

The adoption of a BIM-based approach for the design and setup of a Structural Health Monitoring (SHM) system is an unexplored topic in the scientific literature. This paper presents a methodology designed to optimize the information management of the entire process using Building Information Modeling (BIM), defining the exchange information requirements (EIRs), Process Map, and Levels of Information Need (LoINs). Moreover, to verify the consistency of the information exchanged, this paper employs the information delivery specification (IDS) standard, developing a script that, using LoINs and the BIM model as input, verifies the desired requirements at each stage of the process. The proposed approach is applied to a viaduct on the Naples-Salerno highway, achieving a fully digital and interoperable platform for stakeholders involved in the processes. The results highlight the advantages of the proposed methodology over traditional approaches. • Improved coordination across disciplines in SHM system design. • Exploiting BIM to optimize collaboration and efficiency of traditional SHM workflows. • Achieve consistency and compliance with EIRs through Information Delivery Specifications (IDS). • Innovating SHM system design and setup through open-BIM for greater effectiveness. • Validating the performance of BIM-based workflows for the SHM system setup of highway viaducts. [ABSTRACT FROM AUTHOR]

In the realm of construction production control, effective communication across operational levels and the rapid influx of diverse data are essential. Yet, integrating this data faces challenges due to disparate systems and a lack of common terminology, resulting in data silos and hindered interoperability. An ontology-based solution emerges as promising for enhancing interoperability. This research paper introduces the development, implementation, and assessment of the cSite ontology, encompasses several crucial facets necessary for efficient production control such as location, activities, and documents. To evaluate its practicality, a real-case study was conducted, wherein the ontology was employed to answer competency questions through SPARQL queries. Furthermore, interactive dashboards, situated within the construction control rooms, were developed to present the information visually. This paper underscores the transformative potential of integrated and visualised production information in construction projects. Additionally, it illuminates how the cSite ontology can facilitate the development and implementation of construction digital twins. • Development of the cSite ontology for effective construction production and control. • Real-case study involving the utilisation of the ontology to answer competency questions through SPARQL queries. • The cSite ontology's capability to support the development and implementation of construction digital twins. [ABSTRACT FROM AUTHOR]

This paper developed a novel online optimization deep learning framework for accurate estimation and control of tunnel boring machine's (TBM) attitude and position. The proposed spatio-temporal deep learning model integrates graph convolutional network (GCN) and long short-term memorial (LSTM) neural network which can provide an accurate estimation of TBM's trajectory deviations. This model is later utilized as the meta-model and integrated with an online non-dominated sorting genetic algorithm II (NSGA-II) method to optimize and minimize the trajectory deviations in real-time. A tunnel project from Singapore is utilized as a case study for demonstration purposes. TBM's key operational parameters, articulation displacements, and TBM's trajectory deviations are processed and utilized for real-time prediction. The results indicate that (1) The developed deep learning models can predict TBM's trajectory deviations with high accuracy. (2) TBM's trajectory deviations can be effectively reduced by the proposed optimization method. (3) The proposed spatio-temporal deep learning methods outperform the state-of-the-art methods. (4) The proposed online optimization method is more practical and creates better overall improvement than the conventional multi-objective optimization (MOO) approach. The novelty of this paper includes (a) developing a hybrid framework for accurate trajectory deviation estimation and TBM operating optimization, and (b) investigating the influence of time and distance lag between the TBM operation and position control by considering an online optimization. • A novel online multi-objective optimization (MOO) method is proposed. • Deep learning model is established for reliable estimation on TBM's trajectory deviations. • The developed model is utilized as meta-models and hybrids with online NSGA-II method. • A tunnel project from Singapore is utilized as a case study • TBM's overall trajectory deviations can be reduced by 46.4% by the proposed method. [ABSTRACT FROM AUTHOR]

This paper proposes a trajectory planning and control method for heavy-duty manipulators based on inclination-displacement mapping. In this method, inclination sensors are employed to detect the excavator's orientation. By establishing a mapping relationship between joint inclination and cylinder displacement, the cylinder displacement is indirectly derived. Subsequently, considering the typical excavation operation process, the spatial trajectory of the excavator bucket is planned. The displacement of the driving cylinder is determined using kinematic inverse solutions and cubic polynomials. The cylinder displacement is then controlled using a position-velocity (PV) strategy. This method is tested on a 95-ton large excavator, and the results demonstrate several advantages, including easy installation, low maintenance requirements, smooth trajectory planning, and high tracking accuracy. These qualities make it suitable for the demands of intelligent operations in large excavators. Thus, this paper offers valuable insights for the intelligent transformation of heavy excavators. • The mapping relationship of joint inclination-cylinder displacement in larger robotic excavators is established. • The bucket spatial trajectories in a a typical work cycle are planned, and smooth planning trajectories are achieved. • Actual digging tests on a 95-ton robotic excavator are carried out, and accurate trajectory tracking are obtained. • The proposed trajectory planning and control method provides a new solution for automated excavation of large excavators. [ABSTRACT FROM AUTHOR]

New-generation intelligent construction places higher demands on digitisation and intelligence of tunnel. Digital twin (DT) effectively supports high-fidelity modelling, virtual-real mapping, and analysis-based decision-making but with research in the initial stage. To begin with, this paper delves into the complexity and uncertainty inherent in tunnel construction, highlighting DT as a promising solution compared to exisiting technologies such as Building Information Modelling. Then, a systematic literature survey is conducted, revealing growing focus on DT research topics. To provide comprehensive insights into DT-related technologies and their application in tunnel construction, this paper clusters literature from perspectives of sensor networks, Internet of Things (IoT), computer vision-based twin data acquisition, communication, natural language processing (NLP), automatic control-based connection, and geometric, semantic, analytical integrated twin modelling. These aspects shed light on potentials and limitations of existing researh in developing a functional DT. In response to the challenges of information richness, timeliness, and analytical capabilities, an improved conceptual framework tailored for tunnel is proposed to close the information and control loop. Finally, the paper discusses the prospects and gaps of DT in theory and practice to leverage DT implementation. • Digital Twin greatly enhances the development of intelligent tunnel construction. • A comprehensive literature analysis is conducted to assess status of Digital Twin technologies in tunnel construction. • A close-loop conceptual framework of Digital Twin is proposed. • Gaps and future prospects of Digital Twin for tunnel construction are discussed. [ABSTRACT FROM AUTHOR]

As civil structures age and deteriorate, it becomes crucial to conduct structural health monitoring (SHM) to ensure safety and timely maintenance. Surface defect detection plays a vital role in SHM by providing an initial assessment of structural conditions. Recent advancements in deep learning and automation techniques have led to extensive exploration of deep learning-based surface defect detection using images in the field of civil engineering. However, the performance of surface defect detectors heavily relies on the quality of data used for training, and data-related challenges can significantly impact the practicality of these detectors. These challenges encompass inherent and external negative characteristics of the raw data, including images and labels, which can significantly impact the performance of surface defect detectors. Unfortunately, there is a lack of systematic studies that review and discuss data-related challenges and their solutions in surface defect detection. To bridge this research gap, this study aims to review previous studies on deep learning-based surface defect detection using images, with a specific focus on the data perspective. A total of 237 journal papers were selected and critically analyzed in terms of deep learning tasks and application domains. The study summarizes the data-related challenges that affect the performance and applicability of surface defect detectors, along with the corresponding solutions proposed in the selected papers. While various methods have been proposed to address these challenges, limitations still exist and need to be addressed in future research. To guide future studies in addressing data-related issues, a data management framework is designed, encompassing fixed factors and variable factors derived from the selected papers. Furthermore, the study provides suggestions for future research opportunities to offer insights to researchers in the field of deep learning-based surface defect detection. [Display omitted] • A total of 237 journal papers are selected and critically investigated. • Data-related issues in surface defect detectors and the solutions are presented. • A data management framework including fixed and variable factors is designed. • Suggestions of future research opportunities for surface defect detections are provided. [ABSTRACT FROM AUTHOR]

This paper presents an approach for enhancing the path-following capability of concrete printing by integrating steel cables into the center of printed mortar strips during the print process, thus satisfying the synchronous and continuous requirements of 3D printing construction. To investigate the impact of steel cables on buildability of printed composites, the bonding strength between mortars and three types of steel cables with different diameters (0.5 mm, 1 mm, and 1.5 mm) was examined through pull-out tests. Moreover, four-point bending tests were conducted to examine the flexural performance of printed mortar beams reinforced with varying numbers and diameters of steel cables. Experimental results demonstrate that mortar filaments reinforced with 0.5 mm and 1 mm diameter steel cables can meet the buildability requirements within the designated open-time, while 1.5 mm diameter steel cables tend to rebound out of the fresh printed mortar due to their rebound force exceeding the grip strength of the mortar, rendering reinforced 3D printing unfeasible. Pull-out tests reveal that bonding strength between steel cables and 3D printed mortars is between 1.4 and 2.4 MPa. Due to steel cable's bundle structure and printing methods, this bonding strength is lower than that of traditional reinforced concrete. In addition, the flexural strength of printed beams reinforced with steel cables is increased by up to around 90%, and the ductile fracture mode trend was observed. This paper confirms the feasibility and effectiveness of this enhancement approach, providing a reference for other reinforcement methods in 3D printed building structures. • The flexibility of the steel cable can be adapted to the free design of the print path. • The transformation of the printer head can realize the synchronous delivery of multiple steel cables. • The buildability can be negatively impacted by the resilience of cable. • The bonding property between steel cable and 3DMP is weaker than that of traditional reinforced concrete. • 3D printed beams reinforced with steel cables show significant improvement in flexural properties. [ABSTRACT FROM AUTHOR]

Multi-objective optimization can enhance design quality through performance simulation. However, ease or efficiency of construction is also important, and optimization may lead to difficult-to-build designs. Early quantification of constructability would allow designers to balance performance and construction issues. While it is difficult to quantify all factors that influence constructability, robotic construction simulations offer rich datasets to compare potential outcomes. This paper integrates constructability knowledge into early-stage design and examines the impact on multi-objective optimization. It evaluates robotic material delivery systems in constructing a standalone classroom optimized for structural, daylighting, and energy goals. When considering robotic pick and place time, the optimized designs differ, offering the opportunity to change design directions based on construction knowledge. Broader implications also become observable, as incorporating robots with higher carrying capacities reduces the structural elements and embodied carbon of optimal designs. This paper thus demonstrates benefits of incorporating robotic constructability simulation into early design optimization. • A time-based robotic construction metric is demonstrated for early design. • Simplified robotic material delivery paths are used to assess potential designs. • Classroom is optimized for embodied carbon, constructability, daylight, and energy. • Optimal geometries depend on priorities but are influenced by construction metric. • Larger robots reduce embodied carbon, showing value of early construction evaluation. [ABSTRACT FROM AUTHOR]

Hydraulic excavators, widely employed in harsh environments, have garnered increased attention in recent years from manufacturers and researchers for automatic operation, particularly through vision-based manipulator pose measurement. This paper utilized a mixed review method to explore the vision-based measurements as well as other applications. A quantitative analysis of computer vision (CV) applications on excavators was performed through a literature search, leading to the classification of these applications into three categories based on keywords. Subsequently, a comprehensive literature review identified four key requirements and challenges for vision-based measurement in the context of automatic control, followed by a discussion on the future prospects of marker-based and deep learning-based manipulator pose measurement for automatic control. This paper offers an in-depth examination of CV applications in excavators, emphasizing the pertinent challenges and forthcoming trends in vision-based manipulator pose measurement for automatic control. • Investigate the applications of computer vision on excavators • Review the literature in 3 aspects: excavator detection and tracking; action recognition; manipulator pose estimation. • Propose requirements and challenges of vision-based measurement approaches from the perspective of automatic control. [ABSTRACT FROM AUTHOR]

An important aspect of automatic floor plan analysis is the extraction of textual information, as it is essential for a thorough understanding of the drawing. This paper presents a text extraction approach utilizing a deep learning-based object detection model and state-of-the-art Optical Character Recognition (OCR) methods. The paper contributes to the research community in three ways: First, it introduces additional annotations to existing data sets to encompass text elements. Second, it proposes a specialized data synthesis pipeline, allowing for generating training images that mimic important characteristics of real data. Finally, it documents a comparative study of deep learning-based object detection architectures (Tesseract, EAST, CRAFT, Faster R-CNN, YOLOv5, YOLOR, YOLOv7, and YOLOv8) and OCR tools (PARSEq, MATRN, EasyOCR, and Tesseract) for the task. Results indicate that YOLOv7 yields the best text detection performance (up to 97.5% wmAP) and PARSEq excels in character recognition (85.2% CER). The data sets are made available. • Data set established for text detection on floor plans with bounding box annotations. • Proposed customizable synthetic data generation method for text on floor plans. • Comparison of deep learning detection models enhanced with synthetic data. • Comparison of OCR tools on data set highlights need for improvement. • Modular text extraction pipeline for downstream task-specific adoption. [ABSTRACT FROM AUTHOR]

The Aerial Building Machine (ABM) is a complex construction equipment used in high-rise building construction, facing challenges due to environmental uncertainties. This paper introduces a multi-condition generative design framework to improve ABM's visualization, operability, and intelligence. It seamlessly integrates real-time data between geometric and physical models and employs an ensemble deep learning model for objective value prediction, using a snapshot strategy. Combining structural reliability concepts with Latin hypercube sampling-based stochastic optimization, an optimal design scheme is obtained for uncertain loads. An ABM case study in China illustrates the approach's feasibility, showing it meets reliability requirements across different conditions and achieves significant improvements (16.59% under normal conditions and 16.91% under extreme wind conditions). Additionally, ensemble deep learning outperforms existing methods for ABM structural reliability estimation. Identifying optimal designs and evaluation options, this paper contributes a multi-condition optimization approach for enhanced structural reliability and establishes an efficient generative design workflow and system for exploring a vast solution space. • A multi-condition generative design framework for ABM is proposed. • The ensemble deep learning approach is employed to predict the structural response precisely. • The load uncertainties are considered according to the developed LHS-based SO approach. • A real aerial building machine in China is taken as a case study for illustration. • The proposed approach shows great performance in the structural optimization design. [ABSTRACT FROM AUTHOR]

Regular patrol inspection of concrete dams can detect cracks at an early stage. However, conventional crack segmentation models based on deep learning (DL) are difficult to be deployed in resource-constrained mobile devices due to the large number of parameters. This paper describes a lightweight semantic segmentation model, termed as CrackTrNet, for images of concrete dam cracks. CrackTrNet is a hybrid U-shaped model based on convolutional neural network (CNN) and Vision Transformer. The CNN is adopted to extract low-level visual features and the Transformer focuses on learning the global contextual information. The results demonstrate that its segmentation accuracy can reach 97.60%, while the model size is only 34.86 MB, which is 66.12%–87.85% lower than that of current mainstream DL-based models. To make the model more practical, a crack inspection mobile application (APP) is developed using Android Studio. The integration of lightweight CrackTrNet and APP can effectively assist the intelligent inspection of dam cracks to ensure structural safety. • A lightweight hybrid network, CrackTrNet, is presented for semantic segmentation of dam cracks. • The integration of CNN and Transformer maximizes the preservation of global and local features. • Transfer learning and depthwise separable convolution are introduced to optimize the model size. • The mobile application is developed to assist patrol inspection of cracks in concrete dams. [ABSTRACT FROM AUTHOR]

To address the negative impacts of image degradation on vision measurement in hazy tunnel construction, this paper presents a unified enhancement method of color and grayscale images in tunnel haze environments. Firstly, a tunnel haze environment light scattering model is introduced utilizing geometric optics principles and the conventional atmospheric scattering model. Secondly, a model for perceiving image haze is established within the image feature space to estimate ambient light and transmission. The efficacy of the method is assessed by constructing a tunnel haze simulation chamber and a platform for measurement of tunnel boring machine (TBM) cutter wear. Comparative experiments demonstrate the method reduces the error in 3D point cloud reconstruction by 77% and improves the measurement precision of TBM cutter wear by 62%. The results demonstrate the potential application of this method in automated tunnel construction. However, further research is needed to enhance its efficacy in dense haze images. • Improved the atmospheric scattering model based on the tunnel environment and geometric optics. • Established a haze perception model based on image compression features. • Proposed a method for calculating atmospheric light and transmission. • Built a tunnel haze environment simulation chamber and a TBM cutter wear measurement platform. [ABSTRACT FROM AUTHOR]

Intelligent Compaction (IC) utilizes the Intelligent Compaction Measurement Value (ICMV) to assess compaction quality in real-time. However, current engineering practices rely on a fixed ICMV for evaluation, overlooking material variations and different compaction stages. The choice of ICMV is often dictated by the manufacturer, lacking rationality. This paper presents a multi-domain ICMV system to customize the appropriate ICMV for various construction scenarios. ICMVs are derived by processing the roller's vibrational response in the time, frequency, and dual time-frequency domains. Optimal filtering methods are recommended for each domain, and sixteen ICMVs are calculated. A criterion is proposed to select suitable ICMVs based on their relationships to rolling passes, statistical performance, and model accuracy. Consequently, six optimal ICMVs are suggested based on the criterion and validated in the field test, effectively enhancing the evaluation accuracy and robustness. This multi-domain ICMV system leads to rigorous and reliable IC evaluations, facilitating its widespread implementation. • A multi-domain ICMV system is proposed to assess the subgrade construction quality. • ICMVs are derived based on vibratory response in time, frequency, and dual time-frequency domains. • Optimal filtering methods are recommended for processing the roller's vibratory response. • A criterion is proposed to perform the adaptive analysis of ICMVs. • The rationality and reliability of intelligent compaction (IC) are improved with the proposed multi-ICMV system. [ABSTRACT FROM AUTHOR]

This paper addresses the limited research on the metaverse's application in the construction industry. It aims to investigate how the metaverse can empower construction, identify adoption barriers, and determine the most significant barriers. We propose a novel application framework of construction metaverse based on cyber-physical-social systems, identify 17 barriers using the political-economic-social-technological framework, and employ an expert survey and bi-objective optimization to rank the barriers. Results indicate that scalability, lack of policy incentives, and immature business models are the most critical barriers. The findings provide valuable insights for researchers, practitioners, and policymakers in the construction industry, helping to allocate resources effectively and drive metaverse development. The study's importance lies in its potential to guide successful metaverse integration in construction, leading to improved efficiency and innovation. This research inspires future work on specific metaverse applications in construction and interdisciplinary research to understand and overcome the identified barriers. • We propose a CPSS-based framework for construction metaverse. • We identify the barriers that hinder the construction metaverse application. • We evaluate critical levels of identified barriers. [ABSTRACT FROM AUTHOR]

Building Information Modeling (BIM) plays a pivotal role in the construction management of dam engineering projects, which face challenges in data interoperability due to the absence of standardized data formats. While Industry Foundation Classes (IFC) offer a standardized digital representation of the built environment, it lacks the capability to accurately model the semantics of roller-compacted concrete dams. Therefore, this paper presents an extended IFC-based information exchange for the construction management of roller-compacted concrete dams, incorporating the development and validation of a prototype through a case study. The results indicate a significant enhancement in standardized information exchange for construction management compared to traditional practices. The approach facilitates BIM-assisted information exchange automation among stakeholders involved in roller-compacted concrete dam construction projects. The findings of this study provide valuable insights into dam construction management system prototyping and cross-platform collaboration. [Display omitted] • Requirements for the exchange of construction management information are identified for roller-compacted concrete dam. • The IFC schema is extended to enhance data interoperability as an information exchange standard. • A prototype system is developed to demonstrate the possibility of exchanging construction information with IFC. • The feasibility of IFC-based information exchange is validated through a case study. [ABSTRACT FROM AUTHOR]

Driven by the rapid evolution of 3D printing technology, the construction industry is on the verge of a momentous revolutionary shift. The implementation of construction 3D printing (C3DP) or additive construction (AC) is rewriting the established conventions of traditional building methods. The efficiency and versatility demonstrated by C3DP have the potential not only to revolutionize construction techniques but also to address persistent industry challenges. This paper provides an updated and comprehensive review of AC, drawing on insights from industry reports and post-2016 academic research. Its primary aim is to bridge the gap between academia and industry, thereby offering researchers, professionals, and policymakers a complete review of the state-of-the-art of C3DP as well as the latest technological advancements. It delves into various aspects of 3DCP, including printing systems, materials, thermal performance, current limitations, and sustainability considerations, providing valuable insights and shaping a roadmap for future research endeavors. [Display omitted] • Comprehensive critical comparison of printing systems used in additive construction. • Explored typical and novel materials used in 3D printing for construction. • Discussion of the factors affecting thermal efficiency and the enhancement methods. • Environmental, economic, and social sustainability of the 3D printing construction. • Limitations in the 3D printing construction technology and areas of future research. [ABSTRACT FROM AUTHOR]

The transition to robotic construction requires advanced planning approaches to meet the specific requirements for successful robot deployment. Robots require precise information (e.g., position, velocity, force) to execute tasks reliably. Existing research focuses on robot-oriented construction processes but lacks real-time planning integration with building and construction information. To overcome these challenges, this paper proposes the Robot Construction Action Node (RCAN), serving as a middle layer system between BIM-based smart components and the Robot Operating System (ROS). RCAN breaks down construction planning into ordered activities for flexible adaptation and direct robot control. By assigning these construction activities to components, the macro construction process is linked to the micro construction methods. This procedure is tested and evaluated using a Linked Building Data (LBD) data modeling approach. The proposed solution is validated through three robot construction scenarios in an earlier built simulation environment. • An RCAN middle layer system is proposed for data linking and interaction between BIM and ROS. • A procedure converts IFC models and construction plannings into merged RDF graphs. • An RCAN-based framework allows interaction between smart components and robots. • A simulation presents execution of construction activities by a mobile manipulator using the RCAN system. [ABSTRACT FROM AUTHOR]

This work addresses the problem of automatic tunnel surface defect inspection using unmanned aerial vehicles (UAVs). The research aims at proposing a robust and efficient monitoring method for image data acquisition and processing in complex and dark tunnel environments. A method, called Proximity Move-Pause-Photo for Surface Defect Inspection (PMPP-SDI), is proposed by combining reactive flying control strategies with a grid scanning pattern to capture high-quality image data from multiple views and angles. The image data is then used to generate a 3D point cloud model of the tunnel surface for structural condition assessment. The method is tested in a field experiment in a railway tunnel in Ireland, and the results show that it can achieve stable navigation, high-resolution reconstruction, and accurate defect detection. The paper discusses the advantages and limitations of the method, and suggests improving the control/navigation intelligence, data quality, and defect analysis as the future research directions. • Reactive strategy for adaptative UAV navigation in tunnels. • UAV 3D close-range surface data acquisition. • Method validation and tunnel defect analysis. [ABSTRACT FROM AUTHOR]

A tunnel boring machine (TBM) generates rock chips during excavation, which are crucial for assessing surrounding rock integrity, enhancing excavation efficiency, and evaluating cutter wear. However, traditional methods struggle to identify small rock chips, chips submerged in soil or water, and chips in stacked states. This paper proposes a convolutional neural network (CNN)-based method for directly recognizing the particle size distribution from rock chip images. A dataset of 2520 rock chip images representing 84 particle-size distributions was collected in a laboratory environment. By comparing various CNN architectures and hyperparameters, an optimal model was obtained with a mean absolute error (MAE) of 1.66 × 10−2 and R 2 of 0.923 on the test set. The results demonstrate that the proposed method enables the real-time recognition of particle size distribution using rock chip images, which has the potential to significantly improve intelligent auxiliary excavation technology in TBMs. • A dataset of 2520 rock chip images representing 84 particle size distributions was collected. • A CNN-based method for directly recognizing particle size distribution from rock chip images is proposed. • An optimal model was obtained with a MAE of 1.66 × 10−2 and R 2 of 0.923 on the test set. [ABSTRACT FROM AUTHOR]

Today, engineers rely on conventional iterative (often manual) techniques for conceptual design. Emerging parametric models facilitate design space exploration based on quantifiable performance metrics, yet remain time-consuming and computationally expensive, leaving room for improvement. This paper provides a design exploration and explanation framework to augment the designer via a Conditional Variational Autoencoder (CVAE), which serves as a forward performance predictor as well as an inverse design generator conditioned on a set of performance requests. Hence, the CVAE overcomes the limitations of traditional iterative techniques by learning a differentiable mapping for a highly nonlinear design space, thus enabling sensitivity analysis. These methods allow for informing designers about (i) relations of the model between features and performances and (ii) structural improvements under user-defined objectives. The framework is tested on a case-study and proves its potential to serve as a future co-pilot for conceptual design studies of diverse civil structures and beyond. [Display omitted] • We propose a new generative design method employing (explainable) deep learning. • A novel autoencoder architecture for forward and inverse design is suggested. • Our novel method acts as a design co-pilot for enabling informed decision making. • A synthetic data pipeline for training the design co-pilot is developed. • Our method provides local sensitivity analysis with negligible computational overhead. [ABSTRACT FROM AUTHOR]

Accurate extraction of cracks is important yet challenging in bridge inspection, particularly that of tiny cracks captured from high-resolution (HR) images. This paper presents a crack-boundary refinement framework (CBRF) for meticulous segmentation of HR crack images. First, a triple-scale feature extraction module is designed to enhance the representation of miniscule-crack pixels. Then, a cascade operation involving global and local steps is adopted to conduct the refinement. In addition, an active boundary loss is introduced into the training process to solve the semantic inconsistency of crack boundary areas. The first HR crack image dataset is established to thoroughly evaluate the CBRF. Finally, an unmanned aerial vehicle (UAV)-based case study is conducted on the Yinpenling Bridge, which further confirms the practicality of the CBRF in improving the safety and efficiency of UAV-based bridge detection while ensuring the accuracy. • Cascade-based CBRF is proposed for crack extraction from high-resolution (HR) images. • The first HR image benchmark dataset for crack segmentation is established. • Triple-scale cascaded refinement operations are introduced to restore the tiny-crack pixels. • Active boundary loss is employed for the semantic consistency of crack boundary areas. • CBRF-UAV-based platform provides a safer and more efficient way for bridge inspection. [ABSTRACT FROM AUTHOR]

The correspondence between BIM and construction instances is crucial to construction management. However, spatial deviation and geometric heterogeneity between BIM and construction point clouds pose great challenges. This paper establishes high-dimensional point cloud feature tensor to devise a point cloud semantic segmentation network and an incremental point-to-point correspondence estimation strategy against spatial deviation and geometric heterogeneity. In the construction of the stadium for the 31st Summer World University Games, the method achieved semantic segmentation accuracy (OA) of 93.8% - 99.9% and reduced BIM-and-construction correspondence error from 16 cm to 3 cm, and automatically documented four-phase construction progresses of 38 317 instances with progress monitoring error of 1%. These results demonstrate the effectiveness and applicability of the proposed method in BIM-to-construction semantic transfer and BIM-and-construction instance correspondence for large complex buildings. Future research will design transfer learning networks to achieve fully BIM-driven semantic understanding and knowledge mining for intelligent construction. • A High-Dimension point cloud Feature Tensor (HDFT) is designed to describe heterogeneous point clouds. • HDFT embedded semantic segmentation network is particularly developed for cross-source point clouds. • Point-to-point correspondence strategy is devised based on HDFT to overcome geometric heterogeneity. • Point correspondences between BIM and construction are effective for construction progress monitoring. [ABSTRACT FROM AUTHOR]

Construction robots have been increasingly adopted in construction projects to improve productivity, reduce risk, and speed up work cycles. Visual Simultaneous Localization and Mapping (V-SLAM) technology is widely used in construction robots due to its lightweight weight, cost-effectiveness, and provision of semantic information. On real construction sites, lighting conditions are often challenging due to factors such as uneven lighting intensity, inadequate exposure, or robots in backlit positions (e.g. roughcast houses without artificial lighting, underground car parks), which cause images captured under these conditions to exhibit low signal-to-noise ratio, uneven lighting, color distortion, noise, and other problems. These challenges make the extraction and matching of feature points in V-SLAM difficult, resulting in significant positioning errors or the inability to generate positioning trajectories for construction robotics. Although existing methods for enhancing low-light images can certainly improve image brightness, they still cannot effectively address the localization challenges brought about by low-light construction scenes with uneven illumination and noise. To address the interference of uneven and changing lighting conditions on V-SLAM localization in construction sites, this paper proposes the Unsupervised Reflectance Retinex and Noise model (URRN-Net) to enhance low-light construction images. By using a CNN model based on the Retinex theory to decompose the illumination characteristics of images, we achieve effective brightness restoration of uneven low-light images by utilizing unsupervised loss functions. URRE-Net can reduce the root mean square localization error by >65% compared to low-light images in the ORB-SLAM3 method, and the maximum error is reduced by >71% in on-site experiments. The proposed URRE-Net can be integrated with existing V-SLAM algorithms to provide more robust localization services for low-light construction site applications such as building operations (e.g., interior wall spraying robotic) or construction management tasks (e.g., automatic tunnel inspection). • Uneven low-light conditions in construction sites pose challenges for V-SLAM robot localization. • URRN-Net is proposed to recover brightness and feature information in low-light images. • URRN-Net is trained using unsupervised learning without paired datasets. • Feature loss function is designed to selectively recover features for V-SLAM. • URRN-Net can effectively reduce positioning errors in on-site low-light construction conditions. [ABSTRACT FROM AUTHOR]

Risk management in construction projects requires effective construction supply chain risk management (CSCRM). To gain insights into CSCRM research, this paper conducts a systematic literature review and bibliometric analysis covering the period from 1999 to 2023. The findings of this comprehensive analysis shed light on various aspects, including risk management phases, classification of micro or macrolevel risks, traditional approaches, and the emergence of artificial intelligence (AI) applications. Through an extensive database search, relevant articles on CSCRM were identified for analysis. The review reveals that while traditional techniques such as surveys, case studies, and statistical tools remain prominent, there is an increasing adoption of AI methods. Initially focused on risk identification, assessment, and analysis; the CSCRM phases have expanded over time to include risk allocation, prioritization, and recovery. Analysis of publication trends shows a rise in the use of AI techniques since 2016 alongside persistent utilization of traditional approaches. Moreover, influential authors, journals, and collaborative networks are highlighted to provide valuable insights into the field's development. Overall visualization contributes to advancing both research and practice in CSCRM by presenting a holistic overview of theories, methods, and emerging technologies within the field along with critical risk management approaches and publication trends. [Display omitted] • Systematic analysis of CSCRM research from 1999 to 2023. • Insights on risk management phases and risk classifications. • Traditional vs. AI approaches in CSCRM. • Identification of influential authors, journals, and networks. • Evolving trends: Increased AI adoption in CSCRM research. [ABSTRACT FROM AUTHOR]

The width and buried depth of hidden cracks in tunnel lining are important indicators for measuring the development degree of crack propagation, and evaluating the risk of lining block falling caused by the coexisting defects with voids and cracks. This paper proposes a high-precision fitting method for the width and buried depth of hidden cracks in lining that does not rely on wave velocity. Time domain features, as well as the main frequency, 3 dB bandwidth, and 3 dB energy of the partial time energy spectrum, are used as the inputs of the back propagation (BP) neural network. The experimental results show that compared with models trained by time domain features, models trained by time domain and time-frequency domain features have better fitting accuracy and generalization ability, the estimation results of crack width and burial depth can be used for monitoring the development speed of the crack propagation in void lining. • A nonlinear model is established for estimating the width and buried depth of internal cracks in tunnel lining. • Using time-frequency domain features instead of frequency domain features to improve the fitting accuracy and generalization ability of the model. • Provide quantitative indicators for the development degree of the coexisting defects with voids and cracks in tunnel lining. [ABSTRACT FROM AUTHOR]

The paper presents a novel method for automatically creating semantic digital models for buildings in Manhattan environments from dense point cloud data. Unlike previous approaches, which rely solely on data-driven methods, our method integrates artificial intelligence with domain engineering knowledge to overcome challenges in indoor point cloud processing and geometry representation in complex layouts. A feature-based Decision Tree classifier extracts main building elements, utilized in a knowledge-based algorithm for 3D space parsing. On this basis, an optimization process generates parameterized floor plans, used to finally create volumetric digital models. The method was validated on datasets from the Technical University of Munich and Stanford University, achieving a mean accuracy of approximately 0.08 m for model placement and 0.06 m for estimating element parameters, which highlights its effectiveness for generating a building's semantic digital model. This approach underscores the potential of AI integration in digital twinning workflows for more automated solutions. [Display omitted] • Designing a hybrid bottom-up, top-down approach for automatic building digital model creation. • Align the capabilities of AI in scene understanding with domain knowledge to overcome challenges in indoor 3D reconstruction. • Developing a knowledge-based method for 3D space parsing in largescale indoor point cloud. • Reconstruction of the parametric building's floor plan using point cloud with low sensitivity to poor data quality. • Creation of dynamic parametric building digital models (LOD200) for flexible facility management and space analysis. [ABSTRACT FROM AUTHOR]

Collective robotic construction (CRC) is an emerging approach to construction automation based on the collaboration among teams of small mobile robots. This paper enhances an existing modular CRC system, showcasing its capability to assemble full-scale in-plane timber structures. Utilizing strategies of co-design, the robotic actuators were updated to accommodate material tolerance in the passive building material, timber struts, which they use for locomotion and assemble into structures. A custom effector was also developed to establish architecturally relevant, structural connections between struts. The enhancements address two major challenges in CRC system development: material tolerance and connections. To showcase these research findings and compare with other construction automation systems, a reinforced slab structure was assembled. With a building envelop of 0.485 m3, this is one of the largest structures assembled by a CRC system. As such, the work highlights the potential applicability of CRC in real-world architectural projects. • Present research on assembly of in-plane timber structure with a novel CRC system. • Introduce co-design methods and mechanisms for dealing with material machining tolerances. • Present the development of an effector for execution of screwed connections by mobile robots. • Evaluate and compare the assembly processes of the presented CRC system with other robotic systems. [ABSTRACT FROM AUTHOR]

Although contemporary architectural design education adopts the parametric design approach, which involves complex iterations between the arrangement of form components and building performance, this method limits students' exploration of the optimal matches between generated form and the behaviours of prospective users. Therefore, as a solution, this study hypothesises the effects of human behaviour simulation on students' exploration of user-centric values in the parametric design process. This paper compares the self-evaluation scores of 90 undergraduate students before and after simulation. Data were collected during an authentic digital design course that examined shopfront façade prototypes. Statistical analysis and interpretation indicate that simulation better facilitates students' search for matches between initially value-isolated forms, created using a parametric design tool, and useful user-centric values. However, simulation is not relevant for discovering unexpected forms. This study addresses the unknown affordances in simulation when assigning user-related value to form generation that lacks value. • The study investigates the impact of human behaviour simulation on enhancing user-centric values in parametric design. • In a digital design course, students engaged in shopfront façade design using a parametric tool and a simulation platform. • An empirical quasi-experiment was adopted to compare students' self-assessments with and without using the simulation. • The simulation promoted the search for usefulness and user-centric values, but not for original form and social interaction. • The simulation is interpreted to offer an iterative approach, error detection, and value speculation in parametric design. [ABSTRACT FROM AUTHOR]

Railway track health monitoring and maintenance are crucial stages in railway asset management, aiming to enhance the train operation quality and service life. For this aim, various inspection means (using diverse non-destructive testing techniques) have been applied, however, these means are mostly not able to monitor whole railway track network or track underlying layers (e.g., ballast and subgrade). The use of remote sensing techniques, such as Interferometric Synthetic Aperture Radar (InSAR), can expedite the defect diagnosis process for railway tracks, elevating the scope of health monitoring to a network-wide level. The Ground Penetrating Radar (GPR) has emerged as a particularly reliable method, especially for detecting structural deficiencies in underlying layers. As a result, combining the two distinct non-destructive testing techniques – GPR and InSAR – presents a promising strategy for efficient railway asset management. Recognizing the significance of embracing newer and more advanced monitoring strategies, this paper reviews the fusion of GPR and InSAR methodologies, and explores the potential integration of machine learning models to develop a predictive health monitoring and condition-based maintenance approach for railway tracks. • A review of InSAR/GPR with potential fusion for railway monitoring was discussed. • A general framework for fusion of InSAR/GPR data and machine learning integration was proposed. • Predictive strategy based on fusion of characterized techniques for railway health monitoring/maintenance plan was focused. • Future research directions are recommended based on the review of literature and discussion of technology. [ABSTRACT FROM AUTHOR]

Resource allocation has always been a critical challenge for construction project planning, and it affects the cost, duration, and quality of the projects. However, current methods mainly focus on a single project and lack integrated planning and optimization across a construction company's multiple projects. This paper describes a simulation of an Autonomous Resource Allocation (ARA) model using Deep Reinforcement Learning (DRL) agents and methods like Double Deep Q-Networks and combined experience replay to develop and test ARA algorithms based on data harvesting from the Internet of Things (IoT) devices. The results show that DRL can successfully perform ARA by capturing the complex interactions among resource allocation features, without needing retraining when situations change. It shows promising future possibilities for construction companies to improve resource utilization and project performance for larger and more complex construction projects. • Novel Approach for Simulation of Portfolio-Project information. • Unification of DRL and Portfolio-Project Simulation for Resource Allocation. • Novel Approach for Processing of Portfolio-Project information Simulation. • Using Data Harvesting and IoT for Gathering Construction Sites' Information. • Novel Reward Function to Assign Resources Efficiently in Different Scenarios. [ABSTRACT FROM AUTHOR]

The decision-making on green retrofitting of existing buildings relies on both explicit and implicit knowledge, and its efficiency and reliability need improvement. Intelligent approaches that can sufficiently utilize the text information of existing projects are required to provide more suitable strategies for green retrofitting. This paper describes a decision-making approach combining Case-Based Reasoning (CBR) and Random Forest (RF), which can identify similar cases from the database containing 109 green retrofit projects and revise outdated measures. A practical project case study shows that the revised retrofit measures can reduce Energy Use Intensity (EUI) by 37%. The proposed approach optimizes and standardizes CBR processes and provides guidance for coping with semi-structured green retrofit decision-making problems, thereby promoting sustainable development and intelligent management in the construction field. The system prototype will be developed and promoted after the case database is expanded. • A CBR-RF approach is designed to select more energy-efficient strategies for building green retrofit. • RF is proven to optimize the case revision stage of CBR to avoid outdated retrofit measures. • The information on existing green retrofit projects is standardized and cross-platform used. • This approach provides intelligent guidance for retrofit decision-making, improving efficiency and reliability. [ABSTRACT FROM AUTHOR]

This comprehensive study delves into scientific publications, distinguishing general literature from formwork-specific findings and giving an overview of research methods and formwork systems for concrete construction. A shift towards reusable materials and the widespread use of robotics, particularly in 3D printing is noticeable. Structural research maintains a balanced focus, with little attention set on beams. While automation is attracting interest, full integration into formwork-related publications is still evolving. The need for practical implementation, applicability to mass production and sustainability aspects requires further exploration. Concluding, a list of future challenges is presented, serving as a guidance for subsequent research and developments in research and the concrete industry. [Display omitted] • This paper reviews formwork technologies regarding automation, structure, material, fabrication and test setups. • Shuttering systems are developed further in regard to sustainability, yet waste prevention and reuse are seldomly addressed. • Implementations considering mass production are low, setting a clear target for future research and development approaches. [ABSTRACT FROM AUTHOR]

This paper introduces a computer-aided approach for evaluating the stability of rotary cranes. Utilizing the Motion add-in within the SolidWorks package, a comprehensive numerical stability analysis was carried out. The interaction dynamics between the crane's support system and the ground were modeled employing linear springs, while the rope system was characterized by a blend of linear spring and damper elements. The term "temporary loss of stability" was introduced to describe scenarios wherein one support loses contact with the ground. Furthermore, ramifications of overlapping control signals on crane operational safety were investigated. Validation of the numerical findings was accomplished through experimental tests conducted on an actual crane. This integrated methodology not only enhances the understanding of crane stability but also offers practical insights for optimizing crane operations in real-world settings. • Computer-aided method for assessing the stability loss of a crane has been proposed. • The concept of temporary loss of stability has been introduced. • Impact of overlapping control functions on safety during work cycle was analyzed. • The method was verified on a real object (laboratory rotary crane). [ABSTRACT FROM AUTHOR]

Crack detection in civil infrastructures has seen impressive accuracy achieved by Convolutional Neural Networks (CNNs) and Transformers. However, practical deployments demand models that are not only highly accurate and robust but also efficient. This paper presents PoolingCrack, a novel and efficient Transformer-based model that leverages a hierarchical structure to capture local and global information in visual data, enabling accurate recovery of crack maps in various conditions. The encoder incorporates an average pooling design that enhances computational efficiency compared to traditional self-attention modules in Transformers, whereas the decoder deploys feature alignment, which improves the feature fusion accuracy. Asphalt, concrete, and masonry crack segmentation results show that the proposed model can reach 0.4% to 6.8% higher mDS than the representative models despite requiring 36–62% fewer parameters and achieving more robustness and effectiveness, with up to 52% higher mDS against noises and other artifacts. • An efficient Transformer-based model is proposed for robust crack segmentation. • Convolutional embedding and pooling blocks are leveraged for an efficient design. • Feature alignment module is employed to fix feature fusion deviation. • The designed model achieves higher accuracy and robustness than the representative large models. • The developed model reduces 36% to 62% parameters. [ABSTRACT FROM AUTHOR]

The harsh actual working environment and heavy weight of the electric shovel pose a great challenge to its trajectory tracking performance. Taking into account the strong robustness and anti-interference performance of the sliding mode control method and the global stability of the inversion control method, a Lyapunov-based inversion sliding mode trajectory tracking method is proposed in this paper, and its effectiveness is verified through numerical simulation based on the electromechanical coupling dynamic model of the electric shovel and the actual electric shovel tracking experiment. The results show that the trajectory tracking method can effectively realize the trajectory tracking of the electric shovel accompanied by tracking deviation within 0.3 m. The existence of the track slip phenomenon makes the electric shovel shake when steering, which also makes the actual operating velocity of the electric shovel fluctuate greatly. Meanwhile, the steering process of the electric shovel is accompanied by a regenerative braking steering mode. [Display omitted] • A electric shovel inversion sliding mode trajectory tracking method is proposed. • The electromechanical coupling dynamic model of electric shovel is established. • The trajectory tracking system based on RTK positioning technology is constructed. • The effect of electromechanical characteristics on path tracking is considered. [ABSTRACT FROM AUTHOR]

Cracks are an essential indicator of infrastructure degradation, and achieving high-precision, pixel-level crack segmentation is a common goal for artificial intelligence (AI)-enabled data processing. This study examines the inherent characteristics of cracks to introduce boundary features of cracks into crack identification and then builds a boundary guidance crack segmentation model (BGCrack), which includes four stages: backbone, boundary feature modeling, global feature modeling, and optimization of joint features. Some lightweight but effective modules are specifically designed and embedded in BGCrack to help achieve this goal. In particular, a high-frequency information enhancement (HFIE) module is designed for the edge modeling stage to better extract boundary features of cracks. A global information perception (GIP) module that combines frequency domain modeling and a Transformer unit (time domain modeling) is developed to help model global contexts and long-term dependencies. The ablation studies prove the validity of the model designs including the gradient loss function and, in particular, the boundary feature modeling, as intended in this study. In the experiments, among different models, BGCrack uses the fewest parameters and relatively low computation powers, but it has the best performance in all assessment measures. Furthermore, this paper also open-sources the code and the steel crack dataset, aiming to promote unified and impartial benchmarking. • Edge features are introduced into crack identification to improve predictions. • A boundary guidance crack segmentation model, BGCrack, is proposed. • A dataset, Steelcrack, is provided to promote research on the crack segmentation. • BGCrack outperforms many existing models in all assessment measures. [ABSTRACT FROM AUTHOR]

With the increasing affordability of robot technologies and the reduction in size and weight of autonomous systems, the deployment of autonomous robotic systems on construction sites has gained significant attention. One major challenge faced by these systems is the accurate mapping and localization within an environment that constantly evolves on a daily basis. This computational problem, known as simultaneous localization and mapping (SLAM), has garnered substantial interest, leading to the proposal of various algorithms in recent years. This paper aims to provide a comprehensive overview of the SLAM algorithms by presenting the necessary background information, discussing the challenges involved in general, examining common approaches, and highlighting recent developments. Furthermore, the specific considerations related to deploying SLAM in construction environments are addressed. In order to provide practical insights into the advantages and use cases of state-of-the-art SLAM algorithms, a rigorous evaluation is conducted within a construction environment • Review of SLAM background, limitations, and approaches • Discussion of special considerations for localization of mobile robots in construction • Evaluation of three state-of-the-art LiDAR SLAM algorithms on a construction dataset • Experiments highlight challenges and the need for better LiDAR SLAM algorithms [ABSTRACT FROM AUTHOR]

Gridshell roofing constructions are favored in modern engineering and architecture for their capacity to produce expansive, lightweight roofs using slender main structural elements, yet their complex and costly fabrication limits broader adoption. The Multi-body Rope Approach (MRA) is effective in computing structurally efficient geometries in gridshells, emphasizing the need to optimize design configurations for minimal internal stresses. This paper presents two strategies, Multiple Order MRA (MO-MRA) and Repulsive Nodes MRA (RN-MRA), to improve the MRA and streamline gridshell construction by reducing the necessary types of structural components. These approaches are combined in an improved MRA (i-MRA), reducing manufacturing costs and increasing efficiency in construction management. The i-MRA was implemented in Matlab and tested on four case studies of increasing complexity, demonstrating its effectiveness. • Developed Improved Multibody Rope Approach for free-form gridshell structures. • Simultaneously optimized funicular shape and minimum structural element types. • Produced structurally effective geometries easy to handle during construction. • Demonstrated method effectiveness on four complex case studies. • Valuable tool for architects and engineers to optimize gridshell design. [ABSTRACT FROM AUTHOR]