Automation in Construction最新文献

Extrusion based 3D Concrete Printing (E-3DCP) is a rapidly growing method of construction due to its ability to manufacture bespoke architectural and structural elements without incurring the additional time and costs typically associated with the manufacturing of the formwork of these components. However, Complex geometries such as overhangs, bridges, and cantilevers pose significant challenges to E-3DCP, increasing the risk of premature failure during 3D printing and complicating the integration of longitudinal reinforcement. In response to these challenges, researchers have developed various techniques and strategies to mitigate these complexities and failures. This paper provides a comprehensive review of these methods, evaluating their advantages and disadvantages, and identifying research gaps in the current literature.

Traditional bridge inspection methods have limitations, driving the need for advanced techniques. The primary objective of this paper is to explore and evaluate the potential of combining Mixed Reality (MR) technologies with Building Information Modeling (BIM) and damage information to overcome these challenges. The paper aims to improve communication, collaboration, and the accuracy of structural damage identification during inspections. Parametric objects were developed to accurately represent and locate damage within the BIM model of the Coimbra I Viaduct in Brazil, using detailed geometric parameters. On-site inspections leveraged MR technologies, enabling real-time integration of damage information into the BIM. This approach allowed full-scale interaction with the model in augmented reality (AR), facilitating direct comparison with actual structural features and improving the accuracy and efficiency of inspections. The findings demonstrate the feasibility of a simplified MR-based inspection process, offering a complementary method within a multi-platform Bridge Management System, thereby enhancing bridge maintenance.

The Architecture, Engineering, and Construction (AEC) industry has experienced an unprecedented surge in data growth, primarily propelled by the widespread adoption of digitalization technologies, including Digital Twins (DTs). This surge poses challenges in terms of data control and ownership. To address this, this paper presents a decentralized platform using blockchain-enabled dynamic Non-Fungible Tokens (NFTs) to securely represent DTs. The framework, implemented as a decentralized application (dApp), utilizes a Decentralized Oracle Network (DON) and interconnected smart contracts to convert DT data into dynamic NFTs for a public marketplace. Demonstrated through a synthetic case study, the framework offers transparency, traceability, and immutability. It introduces sustainability-related implications, such as a building carbon credit market, and financial implications, like trading AEC knowledge and a proposed project financing method. This model ensures DT ownership in AEC but also builds trust for knowledge exchange, potentially serving as a foundational model for applications beyond the AEC industry.

Steam generators (SGs) are essential in nuclear power facilities and require regular inspection to maintain their safety and operational effectiveness. This paper presents a quadruped robot designed to inspect SG heat-transfer tubes. The point-to-point crawling-motion planning problem of the robot is addressed by integrating an improved A* algorithm with an offline motion-posture library established for the tube-sheet environment. The planner can provide the global path, the step size for each crawling cycle, and the strategic placement of footholds. The proposed method can facilitate the robot in navigating obstacles on a tube sheet, seamlessly adapt to various postures and step lengths, and eliminate the necessity for turning or superfluous posture adjustments, thereby ensuring crawling efficiency. The efficacy of the proposed planner is validated rigorously through simulations and experimental trials using an actual SG tube sheet.

Cables are critical and vulnerable components of long-span cable-supported bridges, providing essential support and integrity to ensure bridge safety. Bridge cables are susceptible to damage over time due to environmental factors and external loads, and nondestructive evaluation (NDE) and structural health monitoring (SHM) technologies are usually employed for early detection and continuous monitoring of these potential issues, enabling scientific management and safe operation of bridges. This review presents a comprehensive understanding and recent advances on the inspection, monitoring, and assessment of bridge cables, including common types of cable damages, various detection technologies for both surface and internal damage, as well as methods for cable force measurement and condition assessment. The challenges and future research are also presented. This review could present vital insights for bridge engineers, researchers, and stakeholders, providing a foundation for future research and innovation in the inspection, maintenance, and management of bridge cables.

Building code compliance checking is considered a bottleneck in construction projects, which calls for a novel approach to building code query and information retrieval. To address this research gap, the paper presents a question and answering framework comprising: (1) a ‘retriever’ for efficient context retrieval from building codes in response to an inquiry, and (2) a ‘reader’ for precise context interpretation and answer generation. The ‘retriever’, based on the BM25 algorithm, achieved a top-1 precision, recall, and F1-score of 0.95, 0.95, and 0.95, and a top-5 precision, recall, and F1-score of 0.97, 1.00, and 0.99, respectively. The ‘reader’, utilizing the transformer-based “xlm-roberta-base-squad2-distilled” model, achieved a top-4 accuracy of 0.95 and a top-1 F1-score of 0.84. A fine-tuning and model distillation process was used and shown to provide high performance on limited amount of training data, overcoming a common barrier in the development of domain-specific (e.g., construction) deep learning models.

The current measurement of the main cable shape of large-span suspension bridges relies on the total station, which is time-consuming and labor-intensive. Therefore, this paper proposes an automatic measurement method for the cable shape of suspension bridges: (1) For obtaining target during the construction process, inertial navigation and differential Global Positioning System fusion and route planning method are adopted in combination with airborne laser scanning to get fine point clouds. (2) Addressing the challenge of large-scale point clouds segmentation, SCF-Bridge-Net is proposed based on Spatial Contextual Features Net (SCF-Net) and suspension bridges point clouds simplification method, enabling spatial positioning of the cable clamp and rapid automated calculation of geometric information. The proposed method is successfully applied to the Xianxin Road Bridge in China. The results show that the average error of the main cable shape is 1.1 cm, and the angle error of the cable clamp is approximately 0.21°, validating the efficiency and reliability.

Automation in Unmanned Aerial Systems (UAS)-based structural inspections has gained significant traction given the scale and complexity of infrastructure. A core problem in UAS-based inspection is electing an optimal flight path to achieve the mission objectives while minimizing flight time. This paper presents an effective two-stage method that guarantees coverage as a constraint to ensure damage detectability, while minimizing path length as an objective. A genetic algorithm first determines viewpoint positions, and a greedy algorithm calculates the camera poses, as opposed to directly optimizing all degrees of freedom (DOF) simultaneously. A sensitivity analysis demonstrates the range of applicability and superiority of this formulation over direct 5-DOF optimization by at least 30 % shorter path length. Applied examples, including focused and partial space inspections, are also presented, demonstrating the flexibility of the proposed method to meet real-world requirements. The results highlight the feasibility of the approach and contribute to incorporating automation into UAS-based structural inspections.

Deep learning (DL) on point clouds holds significant potential in the construction industry, yet no comprehensive review has thoroughly summarized its applications and shortcomings. This paper presents a detailed review of the current applications of DL on point clouds in the construction industry, highlighting existing challenges, limitations, and future research directions. A two-stage literature search was conducted, resulting in the collection of 55 research papers published since 2020. The review provides an overview of DL algorithms and examines the datasets used for DL on point clouds, including both real-world and synthetic datasets. Furthermore, it summarizes the various applications of DL on point clouds within the construction sector. Following this analysis, the paper discusses current deficiencies and potential improvements in model performance and data-related issues. Finally, several recommendations are provided to advance the development of DL-based point cloud applications in the construction industry.

Powered back-support exoskeletons (BSEs) are emerging as ergonomic interventions in construction to reduce musculoskeletal injuries by actively enhancing user strength. However, their adoption remains slow due to limited understanding of potential physiological impacts, including muscle fatigue, metabolic cost, joint hyperextension, and fall risk. This paper empirically investigates the potential physiological risk associated with the powered BSEs during construction tasks. A user-centered experiment assessed the impact of powered BSEs on muscle fatigue, metabolic cost, ergonomic posture, and stability during common construction activities. The results indicated that the powered BSEs significantly decreased muscle activity for back and abdominal muscle groups by an average of 60 %, reduced metabolic costs by 17 %, and lowered ergonomic risks by 50 % without impacting stability. This study contributes to the understanding of the physiological impacts of powered BSEs in construction, providing empirical evidence of their effectiveness in reducing muscle fatigue, metabolic costs, and enhancing ergonomic safety.