Emerging remote inspection technologies are addressing the challenges of conventional building work inspections by reducing time, cost, and safety risks for inspectors, while also improving overall effectiveness. These technologies involve data collection, information extraction, and compliance checks, highlighting the need for a comprehensive understanding to enable the adoption of more efficient

An efficient convolutional neural network (CNN), called EfficientNetV2, was recently developed. The early blocks of EfficientNetV2 have structural characteristics that lead to higher training speeds than state-of-the-art CNNs. Inspired by EfficientNetV2, extended research was conducted in this study to determine whether the early, middle, and late blocks of CNNs should have respective structural characteristics

In spite of recent advances, a significant disparity between automatically reconstructed building information models (BIMs) and real scenes persists, particularly within complex indoor environments. With this objective in mind, a knowledge-driven as-built BIM reconstruction method is proposed, which employs laser scanning point clouds and panorama images. Initiation of the method involves the segmentation

This paper presents the continuous monitoring of a full-scale Movable Scaffolding System (MSS) under normal operation, addressing the challenges faced during the monitoring period and the advantages of such a system. The monitoring system was implemented in an MSS used to build in-situ prestressed concrete decks with spans up to 70 m, in Lužný Bridge access viaducts between April 2019 and March 2020

Drones are increasingly being used in construction for various applications. However, this integration has increased interactions between drones and workers, posing significant safety challenges for workers. This paper assessed the physical risks of drones on construction sites using VR-based 4D simulations. Roofs, ladders, and scaffolds were identified as the top high-risk environments where workers

Regular inspection of bridge bearings plays a critical role in ensuring bridge safety. Traditional manual visual inspection is labor-intensive, time-consuming, and subjective. In light of these limitations, this study aims to achieve efficient detection of bridge bearings by leveraging advanced deep learning techniques. Two deep learning models, BearDet and BearCla, were proposed to detect bearings

The use of BIM is becoming increasingly important in the AEC industry because the included dataset enables the automation of many processes. One emerging application of BIM is the automation of building code checking by building authorities. Building code checking is a time-consuming process, particularly for escape routes. Therefore, its automation promises considerable optimisation potential. This

The developments of mobile-concrete pumps steadily increase the complexity of their operation. At the same time, increasing computational power and sensor performance give rise to new smart assistance systems for the operator. This paper presents an optimization-based trajectory planning and motion control concept for a mobile concrete pump that can ensure secure support and obstacle avoidance during

Single-objective optimal trajectory cannot adapt to the complex requirements of excavator construction. A comprehensive optimal trajectory planning method is proposed to optimize the working time, energy consumption, and operational impact of robotic excavators. Without fusing any performance indexes, a normalized multi-objective function and an improved particle swarm optimization algorithm are established

The authors present the first on-site investigation of artificial intelligence (AI)-integrated three-dimensionally movable kinetic façade (KF). Despite continued architectural interest on the KF to improve indoor visual comfort, its in-situ operational strategy has been little addressed. To examine our primary hypothesis that the adaptive KF controlled by AI models improves indoor daylight probability

This paper proposes a framework to automatically determine the productivity and operational effectiveness of an excavator. The method estimates the excavator's actual, theoretical, and relative cycle times in the loading operation. Firstly, a supervised learning algorithm is proposed to recognize excavator activities using motion data obtained from four inertial measurement units (IMUs) installed on

PERT (Program Evaluation and Review Technique) is suitable for evaluating schedule optimization of DBB (Design-Bid-Build) projects based on serial execution of design and construction. However, it is not suitable for evaluating the multi-objective joint optimization of DB (Design-Build) projects based on concurrent execution of design and construction. Therefore, focusing on the unique construction

Deep learning-based computer vision (DLBCV) techniques have played an important role in intelligent construction. Image datasets are essential for developing DLBCV algorithms. However, a large-scale construction-specific dataset of major construction elements, such as precast components (PCs), PC delivery trucks, and workers not wearing safety helmets, remains absent. This paper presents the Construction

The limited amount of high-quality training data available in indoor understanding with deep learning is a major problem. A possible solution to this problem is to use synthetic data to improve network training. In this study, a fully automatic method to generate synthetic noisy point clouds from as-built building information modeling (BIM) models is presented and it assesses the potential of these

The implementation of emerging technologies generates new possibility for the Architectural Engineering and Construction sector. Specifically, the study focuses on the applications of Digital Twins in the heritage construction sector, an area characterized by significant potentials and challenges in various research fields (e.g., energy, digital technology, citizen engagement, cultural aspects, management

Robots are expected to play an important role in future construction work. However, they are not yet widely adopted by the industry because it is difficult and expensive to program robots to conduct a variety of construction tasks. This paper presents a method for intuitively and flexibly teaching robots to perform various construction tasks through demonstrations. Robots are first programmed with

Construction projects require long working hours where workers are subjected to intensive tasks such as hard manual labor, heavy weightlifting, and compulsive working postures. Among the physiological metrics, Heart Rate (HR) is reported to be a good indicator of physical stress and workload. HR forecasting models have been used in various areas including cardiopathy research, heart attack warning

Geometric information modelling from point cloud data (PCD) is a fundamental step of the digital twinning process for rail infrastructure. Currently, this onerous procedure outweighs the anticipated benefits of the resulting model and expends 74% of the modellers' effort on converting PCD to a model. The cost of the resulting geometric information models (GIM) can be reduced by automating the modelling

Efficient information search from building information models (BIMs) requires deep BIM knowledge or extensive engineering efforts for building natural language (NL)-based interfaces. To address this challenge, this paper introduces a dynamic prompt-based virtual assistant framework dubbed “BIMS-GPT” that integrates generative pre-trained transformer (GPT) technologies, supporting NL-based BIM search

The design process in construction projects is iterative and multi-disciplinary in nature. In today’s industry practice, several discipline experts concurrently author multiple versions and design variants of BIM models and share them at frequent intervals. Applying a sound version control methodology can significantly enhance automation, enabling the coordination and combination of these model versions

The popularity of precast concrete in construction is rising due to its capacity for improving building efficiency and quality in comparison to cast-in-situ concrete. While researchers have focused on enhancing constructability factors like logistics and sequencing, the need for developing standardization in this area remains evident. This paper describes a framework for studying the relationship between

Object detection studies aim to solve safety problems at industrial sites; however, improving object detection performance and ensuring real-time capabilities simultaneously remains challenging in multi-complex industrial environments. This paper proposes an unconditionally protected detector to address this problem. The detector's backbone network uses a residual block with a bottleneck structure

The potential of blockchain is being widely explored within the construction industry, particularly for transparent communication and information sharing. However, only limited research has focused on implementing blockchain to address the challenge of aligning conflicting interests among independent agents, specifically, supply chain coordination. This paper develops a blockchain-enabled supply chain

Computer vision (CV)-based safety monitoring has been widely applied at construction sites. However, this method requires large, diverse, and accurately labeled training data, which is difficult or expensive to collect from real-world environments. To address this concern, this paper introduces a synthetic data generation methodology driven by game engines, facilitating the simulation of diverse construction

A discernible correlation emerged between global bridge disasters and bridge deterioration in recent years. To assist bridge inspectors in conducting deterioration identification, this paper presents a Pilgrimage Walk Optimization (PWO) algorithm inspired by Taiwan's unique Matsu bobee custom. The search behavior of the PWO algorithm simulates the gathering of devotees following Matsu's palanquin and

Automated construction quality assessments often face challenges due to noise and occlusions in on-site data when independently comparing elements in as-designed building information models (ad-BIMs) with registered 3D point clouds. This paper proposes BIM-Graph Neural Network (BIM-GNN), a learning-based approach that leverages semantics in ad-BIM to enhance element-wise quality assessments. BIM-GNN

The building tilt rate (BTR) prediction problem is of great importance for safety management in metro tunnel construction. To improve the BTR prediction accuracy, it is pertinent to accurately identify and properly handle less-reliable data which refers to data with an inconsistent input-output relation. A modified boosting and bagging approach is thus proposed, i.e., BooBag. Specifically, modified

Efficiently generating appealing and realistic architectural space configurations has been a significant challenge for designers. This paper presents a deep-learning approach, providing architects with increased control over the final design outcomes. Employing deep learning algorithms to analyze the graph structure of input bubble diagrams facilitates the generation of node-based space layouts confined

Managing, protecting, and the evolutionary development of historical landscapes require robust frameworks and processes for forming datasets and advanced decision support tools. Despite the great potential, using pattern language, machine learning, and regenerative and generative design tools has yet to be adopted in historic landscape research due to the need for suitable training datasets. To address

Reasonable alignment control can simplify the bridge construction process, reduce the complexity and cost of construction, and improve construction efficiency. The prefabricated assembling construction method brings challenges to alignment control. This study proposes a method for predicting the alignment of concrete cable-stayed bridge assemblies in unstressed conditions to accelerate the construction

The evaluation of process improvements measures in offsite construction shop floors often relies on experts' opinion, with limited use of empirical data gathered by sensors in real-time. To address this issue, there is a need for methods that integrate expert's tacit knowledge with robust data analysis techniques. This paper describes the application of exploratory data analysis techniques to evaluate

This paper presents methods for evaluating layout alternatives based on occupants' interactions for workplace design during the early design phase. The research proposes a modelling framework to simulate domain-specific patterns of occupancy and social interactions, as well as the process of design evaluation. The paper introduces a framework for an agent-based model using the Unity gaming engine to

Concrete cracks are one of the most harmful flaws on the road, threatening traffic safety. In this paper, an effective crack segmentation network MOACA-CrackNet that strives to boost both the model generalization rate and segmentation accuracy of crack segmentation is proposed to segment various types of cracks rapidly and accurately in a variety of acquisition conditions. First, a multi-frequency

The inspection of bridges is increasingly dependent on advanced equipment and algorithms like digital cameras and SfM (Structure from Motion). However, many existing SfM-based bridge inspection methods lack efficiency due to lengthy 3D reconstruction computation times, and digital image resolution often falls short in detecting fine cracks and calculating their widths, mainly influenced by the acquisition

Efficient management of construction progress requires regular progress tracking, but monitoring progress on a daily basis can be both time-consuming and labor-intensive since the meticulous manual data processing is involved. Soil-foundation construction entails multiple uncertain underground safety risks, the elimination of which requires significant time and effort, thereby increasing the likelihood

Widely reported anisotropy in 3D printed cementitious structures has been a primary concern to structural integrity, especially for fiber-reinforced cementitious material, e.g., engineered cementitious composites (ECC). To alleviate the anisotropy present in 3D printed ECC (3DP-ECC), two innovative printing patterns, “knitting” and “tilting” filaments, were proposed, mimicking the natural crossed-lamellar

Quality Assurance and Quality Control (QA/QC) play a crucial role in the building project life cycle, especially during construction, as discrepancies between as-built structures and as-designed models can lead to cost overruns and schedule delays. Ensuring building quality is of utmost importance, but traditional manual inspections suffer from errors, consume time, and incur significant expenses.

During the construction of prefabricated structures, manufacturing deviations and assembly deviations will accumulate. By detecting dimensional deviations of precast concrete (PC) components, rework can be avoided. This paper presents a Scan-vs-BIM (Building Information Modeling) method based on point clouds to identify PC components and evaluate manufacturing deviations. Based on Extended Orthogonal

Traditional wall-building robots regard brick masonry as a simple assembly process, ignoring the viscoelastic effect of cement mortar, which leads to poor masonry quality. Therefore, this paper proposes a many-objective trajectory optimization method based on response surface methodology (RSM) and non-dominated sorting genetic algorithm III (NSGA-III). Firstly, a substitution model between the objective

The planning of lift paths is a critical task in crane operations. Traditionally, crane operators and assistants perform operation tasks based on their observation and experience, this is a tedious and error-prone process. Previous studies mainly focus on the optimization of path length or planning time, but seldom consider the accessibility of information for planning and the execution ability of

Operator Support Systems (OSSs) that support operators during highly time-critical asphalt compaction operations provide them with real-time sensory data. Nonetheless, the conventional asphalt compaction OSSs tend to cognitively overload operators with information that requires much human interpretation on the fly. To address the problem of OSSs' infobesity, the transition to a higher level of system

Insufficient buildability during printing can result in structural instability of three-dimensional (3D) printed concrete. A damage-rheology model was developed to predict such structural failure by simulating the early-age behavior of 3D printed concrete. The model captures essential characteristics of early-age concrete, including structural build-up, softening damage, irreversible deformation, and

The integration of the shotcrete system with Ultra-High Performance Concrete (UHPC) to reinforce deficient concrete structures has been recognized as having significant potential. However, the execution of manual spraying operations within confined spaces or hazardous environments presents considerable risks, thereby highlighting the pressing necessity for implementing robotic solutions. This research

Massing studies during the early stages of architectural design play an essential role in determining the final building’s performance across design objectives. This paper aims to answer the question: How can early-stage architectural design workflows be translated into a generative design process to create valuable massing solutions? In response, a new application of the Non-Dominated Sorting Genetic

Effective resource scheduling and machine maintenance are two important interactive factors to improve prefabricated component productions. However, previous studies focused on machine maintenance without simultaneously considering stochastic resource scheduling, or studied job scheduling but neglected the resource constraint and machine availability. This paper explores the interaction between resource

Current digital design-to-build workflows are limited to distinct tasks and pre-programmed machine operations, and the lack of system adaptability makes it difficult to accommodate non-linear construction processes and unexpected incidents. This work questions how to address humanization in post-digital architectural practices in order to increase workflow flexibility. Taking a lightweight timber structure

Building information modeling (BIM) design validation is primarily aimed at responding quickly to serious design errors. A prompt response to BIM request for information (RFI) can significantly enhance the BIM return on investment (ROI). Although prior research has identified additional factors to consider while assessing the benefits of BIM coordination, it was not possible to conduct an economic

Designing architectural layouts is a complex task that has garnered significant attention in the research community. While automated site layout design and flat layout design have been extensively studied, automated building layout design has been relatively overlooked. This paper describes an approach for generating automated building layouts using deep learning and graph algorithms. A unique building

A well-designed visualized dashboard could provide intuitive information to construction project managers for effective decision-making. However, the impact of information load of dashboards on cognitive load has rarely been investigated. The roles of user cognitive styles were also ignored. This study examined the effect of dashboard information load and user cognitive style on cognitive load when

The project schedule delay problem has received considerable attention for its significance in impeding project performance. Compared to conventional projects, prefabricated construction projects could suffer more from schedule delay problems. A possible solution to such problems is to provide countermeasures by referring to valuable experience of historical cases. This paper proposes a case-based

Despite the availability of 3D digital models, 2D floor plans remain extensively used for quality inspection and maintenance as they offer firsthand information. While laser scanners enable efficient capture and reconstruction of real-world scenes, challenges arise in accurately extracting building geometry from laser scanning data due to the loss of geometric features. This paper describes a method