Search

Evacuation navigation in emergencies such as fires is one of the most important operational considerations for a building. The large and complicated interior spaces, as well as the intensive popula...

Detailed planning, sequencing, and scheduling for the installation of multiple pipe systems are greatly needed to efficiently complete a piping project with both reduced cost and duration. ...

Semantic segmentation of closed‐circuit television (CCTV) images can facilitate automatic severity assessment of sewer pipe defects by assigning defect labels to each pixel on the image, f...

Accurate estimation of object edge lines is the key for accurate dimension estimations. However, due to the limited spatial resolution of terrestrial laser scanning and the existence of mixed pixels along object edges, edge line estimation is always imperfect. Most of the existing edge line estimation algorithms simply remove mixed pixels before edge line estimation without utilizing mixed pixel data. This study developed high-accuracy edge line estimation algorithms for flat surfaces using 3D terrestrial laser scanning. In this study, four different edge line estimation algorithms are proposed and compared, and two of them leverage information from mixed pixels to improve the edge line estimation accuracy. The effects of scan data parameters on the performance of the edge line estimation algorithms are investigated using numerical simulations and validation experiments. Based on the simulation results, recommendations of edge line estimation algorithm and scanning settings are provided, which are further validated through experiments.

Maintenance workers on offshore platforms are usually exposed to a high level of noise from the working environment as most of the daily operations of oil and gas process machines generate noise over 85 dBA, causing substantial health and safety issues. Avoiding exposure of workers to the modules that generate high sound power during maintenance activities can significantly mitigate the noise impact on human health and safety. Noise simulation and noise mapping methodologies can be used to evaluate and quantify the noise impact on offshore platforms. However, limited digital information of offshore platforms makes noise simulation setup challenging as modules on topsides have a high level of details. In addition, current noise mapping studies are usually conducted in a 3D static manner, which only reflects noise impact at a certain time. Building information modeling (BIM) provides detailed physical and functional characteristics of a facility that can be applied to support the noise simulation on offshore platforms. In this study, attempts have been made to develop a BIM-supported 4D acoustics simulation approach to mitigating the noise impact on maintenance workers of offshore platforms. BIM is utilized to automatically provide required information to facilitate noise simulation setup. 4D acoustics simulation approach is used to obtain the spatio-temporary sound pressure level (SPL) distribution of the noise generated by the functional modules on offshore platforms. Acoustic diffusion equation (ADE) is selected as noise SPL prediction model. To evaluate noise impact on maintenance workers, an equation based on daily noise dose is then newly derived to quantify the noise impact. Optimization algorithm is used to determine the maintenance schedule with the minimum daily noise dose. Finally, optimized maintenance schedule that has considered noise impact is used to update the daily maintenance plan on offshore platforms. An example of a fixed offshore platform with maintenance daily activity information is used to illustrate the proposed BIM-supported 4D acoustics simulation approach. The results show that the developed approach can well mitigate noise impact on maintenance workers on offshore platforms, resulting in health and safety management improvement.

Augmented reality/virtual reality (AR/VR) has been increasingly adopted to enhance the visualization of building information modeling (BIM) models. However, there is a lack of mechanisms fo...

Sanitary sewer systems are designed to collect and transport sanitary wastewater and stormwater. Pipe inspection is important in identifying both the type and location of pipe defects to maintain the normal sewer operations. Closed-circuit television (CCTV) has been commonly utilized for sewer pipe inspection. Currently, interpretation of the CCTV images is mostly conducted manually to identify the defect type and location, which is time-consuming, labor-intensive and inaccurate. Conventional computer vision techniques are explored for automated interpretation of CCTV images, but such process requires large amount of image pre-processing and the design of complex feature extractor for certain cases. In this study, an automated approach is developed for detecting sewer pipe defects based on a deep learning technique namely faster region-based convolutional neural network (faster R-CNN). The detection model is trained using 3000 images collected from CCTV inspection videos of sewer pipes. After training, the model is evaluated in terms of detection accuracy and computation cost using mean average precision (mAP), missing rate, detection speed and training time. The proposed approach is demonstrated to be applicable for detecting sewer pipe defects accurately with high accuracy and fast speed. In addition, a new model is constructed and several hyper-parameters are adjusted to study the influential factors of the proposed approach. The experiment results demonstrate that dataset size, initialization network type and training mode, and network hyper-parameters have influence on model performance. Specifically, the increase of dataset size and convolutional layers can improve the model accuracy. The adjustment of hyper-parameters such as filter dimensions or stride values contributes to higher detection accuracy, achieving an mAP of 83%. The study lays the foundation for applying deep learning techniques in sewer pipe defect detection as well as addressing similar issues for construction and facility management.

As the coming decades will witness a big trend in the decommissioning of offshore platforms, simultaneously disassembling topsides of multiple offshore platforms is getting increasingly common. Considering high risk and cost of offshore operations, module lift planning among multiple offshore platforms with transport vessels is required to be carefully conducted. The lift planning usually contains two main parts: module layout on vessels planning and vessel transport schedules arrangement. In contrast to the current experience-driven module lift planning, this paper formulates the lift planning optimization problem and develops a web system integrating building information modeling (BIM) and geographical information system (GIS) to efficiently disassemble topsides for multiple offshore platforms. BIM provides detailed information required for planning module layout on vessels and GIS contains the management and analysis of geospatial information for the vessel transport schedule arrangement. As for module layout optimization, three heuristic algorithms, namely genetic algorithm (GA), particle swarm optimization (PSO), and firefly algorithm (FA) are implemented and compared to obtain the module layout with the minimum total lift time. While for vessel transport schedule, graph search technique is integrated with a developed schedule clash detection function to obtain the transport schedule with the minimum sailing time. The proposed optimization algorithms and techniques are integrated into a developed BIM/GIS-based web system. An example of three offshore platforms with eighteen modules in total is used to illustrate the developed system. Results show that the developed system can significantly improve the efficiency of lift planning in multiple topsides disassembly. The developed BIM/GIS-based web system is also effective and practical in the resource allocation and task assignment among multiple locations, such as construction sites, buildings, and even cities.

Although more than 65% of the total cost in facility management (FM) comes from facility maintenance management (FMM), there is a lack of efficient maintenance strategies and right decision making approaches to reduce FMM costs. Building information modeling (BIM) has been developed as a potential technology for FMM in buildings. This study proposes an FMM framework based on BIM and facility management systems (FMSs), which can provide automatic scheduling of maintenance work orders (MWOs) to enhance good decision making in FMM. In this framework, data are mapped between BIM and FMSs according to the Industry Foundation Classes (IFC) extension of maintenance tasks and MWO information in order to achieve data integration. After bi-directional data transmission between the BIM models and FMSs, work order information is visualized in BIM via API to identify components that have failed. Second, geometric and semantic information of the failure components is extracted from the BIM models to calculate the sub-optimal maintenance path in the BIM environment. Third, the MWO schedule is automatically generated using a modified Dijkstra algorithm that considers four factors, namely, problem type, emergency level, distance among components, and location. Illustrative examples are given in the paper to validate the feasibility and effectiveness of the proposed framework in indoor and outdoor 3D environments.

Design of steel reinforcement is an important and necessary task for designing reinforced concrete (RC) building structures. Currently, steel reinforcement design is performed manually or semi-automatically using computer software such as ETABS, with reference to building codes. These approaches are time consuming and sometimes error-prone. Recent advances in building information modeling (BIM) technology allow digital 3D BIM models to be leveraged for supporting different types of engineering analyses such as structural engineering design. With the aid of BIM technology, steel reinforcement design could be automated for fast, economical and error-free procedures. This paper presents a BIM-based framework using the developed three-stage hybrid genetic algorithm (GA) for automated optimization of steel reinforcement in RC frames. The methodology framework determines the selection and alignment of steel reinforcement bars in an RC building frame for the minimum steel reinforcement area, considering longitudinal tensile, longitudinal compressive and shear steel reinforcement. The first two stages optimize the longitudinal tensile and longitudinal compressive steel reinforcement while the third stage optimizes the shear steel reinforcement. International design code (BS8110) and buildability constraints are considered in the developed optimization framework. A BIM model in Industry Foundation Classes (IFC) is then automatically created to visualize the optimized steel reinforcement design results in 3D thereby facilitating design communication and generation of construction detailing drawings. A three-storey RC building frame is analyzed to check the applicability of the developed framework and its improvement over current design approaches. The results show that the developed methodology framework can minimize the steel reinforcement area quickly and accurately.

Document management systems in AEC projects manage important project documents such as schedules, RFIs, and change orders. Hence, security concerns in document management systems especially involving data integrity of documents and records may have a severe effect on a project in terms of money and the reputations of project participants. Therefore, in this research blockchain technology is leveraged to facilitate data integrity in document management for construction applications through - (1) irreversible and irrevocable approval workflow logic via smart contract technology, (2) irreversible recording of document changes via blockchain ledger technology, and (3) document version history integrity via a blockchain-based data structure. A prototype of the proposed smart contract framework was developed using Hyperledger fabric and evaluated. The scalability of the proposed framework to support document version integrity was also evaluated and discussed. A formulation based on existing literature is developed to evaluate the cost viability of the proposed framework.

Mechanical, electrical and plumbing (MEP) system provides various services and creates comfortable environments to residents in cities. To enhance the management efficiency of the highly complex MEP system, as-built building information modeling (BIM) is increasingly adopted in the world. Currently, as-built BIMs are mostly drawn manually by modelers in BIM modeling software referring to point clouds or on-site photos, which is time consuming and labor intensive. This study presents a novel fused BIM reconstruction approach for MEP scenes. The proposed approach makes the best of the rich semantic information provided by images and accurate geometry information provided by 3D LiDAR point clouds. Firstly, a state-of-the-art deep learning model focusing on semantic segmentation is fine-tuned for the MEP dataset, and then RGB images collected with depth camera are segmented with the well-trained model. Secondly, taking the segmented images and the corresponding depth images as input, a semantic-rich 3D map is generated. Thirdly, an instance-aware component extraction algorithm in LiDAR point clouds given approximate object distribution in 3D space is developed. In the component extraction algorithm, a label transfer technique is proposed to firstly determine the rough locations of targeting objects in LiDAR point clouds. Then, accurate component locations are determined for three types of components including irregular shaped components, regular shaped components, and secondary components attached to walls. Finally, the BIM model is reconstructed based on component extraction results. To validate the proposed technique, experiments were conducted in four MEP rooms in a water treatment plant in Hong Kong. It is demonstrated that the proposed technique is more accurate and more efficient with wider range of applications compared to previous BIM reconstruction methods.

Steel reinforcement (also referred to as rebar) design plays an important role in reinforced concrete (RC) structures in terms of strength requirements, cost and buildability. Currently, rebar design is performed at the individual member level with few considerations of the interference between different intersecting members, leading to potential clashes and buildability issues. Design for Manufacture and Assembly (DfMA) is a cutting-edge technology concept that improves the design for higher buildability by incorporating knowledge from downstream manufacture and assembly activities into the early design phase. This paper presents an innovative DfMA-oriented approach for rebar design optimization with Building Information Modeling (BIM) and a hybrid metaheuristic algorithm. Firstly, activities related to the manufacture and assembly of rebar are identified to apply DfMA principles, followed by the proposed BIM-based optimization framework. Secondly, multi-objective cost design formulation including both the material cost and the installation cost is proposed, incorporating the design code requirements and DfMA considerations. Following this, key modules for implementation are presented including the rebar layout searching, the hybrid genetic algorithm incorporated with Hooke and Jeeves’s method for optimization and rebar clash avoidance. The illustrative example shows that the proposed approach can generate a series of practical rebar layouts, and a trade-off between the material cost and installation cost is found, which means excessive emphasis on minimizing one of them will lead to the rise of the other.

Existing platforms for collaborative BIM design have a centralized system architecture, which suffers cybersecurity risks of design data manipulation and denial of access, leading to a loss of data traceability, a decline in design productivity, and project delays. Blockchain is a promising technology to solve such risks by providing decentralized and immutable data storage. However, integrating blockchain with BIM faces a problem that blockchain is inherently unsuitable for storing large-sized design files like BIM models, hindering blockchain from protecting BIM data integrity. Therefore, this paper proposes a distributed common data environment (DCDE) framework for BIM-based design leveraging two distributed technologies: blockchain and Interplanetary File System (IPFS). The DCDE framework guarantees irreversible design changes storage using blockchain while secures design file storage using IPFS. A blockchain transaction data model and a smart contract are also developed within the framework to support DCDE functionalities. Lastly, framework applicability and performance are tested in an illustrative design example. Results show that: (1) DCDE is a feasible solution for secure design collaboration, and (2) DCDE latency (in millisecond-level), TPS (60 transactions per second), and storage cost (12.5 KB per day) are within an acceptable range.

Currently, as-built building information modeling (BIM) models from point clouds show great potential in managing building information. The automatic creation of as-built BIM models from point clouds is important yet challenging due to the inefficiency of semantic segmentation. To overcome this challenge, this paper proposes a novel deep learning-based approach, ResPointNet++, by integrating deep residual learning with conventional PointNet++ network. To unleash the power of deep learning methods, this study firstly builds an expert-labeled high-quality industrial LiDAR dataset containing 80 million data points collected from four different industrial scenes covering nearly 4000 m2. Our dataset consists of five typical semantic categories of plumbing and structural components (i.e., pipes, pumps, tanks, I-shape and rectangular beams). Second, we introduce two effective neural modules including local aggregation operator and residual bottleneck modules to learn complex local structures from neighborhood regions and build up deeper point cloud networks with residual settings. Based on these two neural modules, we construct our proposed network, ResPointNet++, with a U-Net style encoder-decoder structure. To validate the proposed method, comprehensive experiments are conducted to compare the robustness and efficiency of our ResPointNet++ with two representative baseline methods (PointNet and PointNet++) on our benchmark dataset. The experimental results demonstrate that ResPointNet++ outperforms two baselines with a remarkable overall segmentation accuracy of 94% and mIoU of 87%, which is 23% and 42% higher than that of conventional PointNet++, respectively. Finally, ablation studies are performed to evaluate the influence of design choices of the local aggregation operator module including input feature type and aggregation function type. This study contributes to automated 3D scene interpretation of industrial point clouds as well as the as-built BIM creation for industrial components such as pipes and beams.

Precast concrete elements are widely adopted and the performance of precast structures is relying on the quality of connections between adjacent elements. For reinforced precast concrete elements, rebar positions are important for the overall structural performance, however, they are usually manually inspected. This study develops a technique for automated position estimation of rebars on reinforced precast concrete elements using colored laser scan data. A novel mixed pixel filter is developed to remove mixed pixels from the raw scan data based on both distance and color difference. A one-class classifier is used for extracting rebars from all the data based on both geometric and color features of points. Furthermore, a novel rebar recognition algorithm is developed to recognize individual rebars based on two newly defined metrics. Experiments on two reinforced precast concrete bridge deck panels were conducted and showed that the proposed technique can accurately and efficiently estimate rebar positions.

The amount of waste generated in construction and demolition (C&D) processes is enormous. Therefore, many studies on efficient C&D waste minimization and management have been conducted. However, 21 process-related and 8 technology-related limitations in C&D waste management and minimization have not yet been resolved. Building information modeling (BIM) helps project participants improve the processes and technologies in the planning, design, construction, and demolition phases, thereby managing and minimizing C&D waste efficiently. Therefore, this paper identifies the potential opportunities of BIM for efficient C&D waste management and minimization, such as design review, 3D coordination, quantity take-off, phase planning, site utilization planning, construction system design, digital fabrication, and 3D control and planning. The BIM-based approaches can support C&D waste management and minimization processes and technologies by addressing existing limitations through in-depth literature review. The roles of project participants and information required for each BIM-based approach in C&D waste management and minimization are discussed with illustrative process maps.

Offshore oil and gas platforms (OOGPs) usually have a lifetime of 30–40 years. An increasing number of OOGPs across the world will be retired and decommissioned in the coming decade. Therefore, a safe and efficient approach in planning the disassembly of the topsides of OOGPs is required. One commonly applied disassembly method is reverse installation, which moves the OOGP modules from the platform deck to a heavy lift vessel (HLV) in reverse order of their installation. Considering the high risk and cost of working offshore, shortening the lift time is crucial. In contrast to the traditional experience-driven lift operations, this paper describes minimizing the lift path for each OOGP module during disassembly, leveraging building information modeling (BIM) technology and an improved A* algorithm. BIM models provide accurate component-based geometric and semantic information that can be used for planning and optimization. However, there has been no previous study on the use of BIM for offshore disassembly. Industry Foundation Classes (IFC), which is a neutral data model of BIM, is used in this study to represent OOGP models. In particular, the IfcBuildingElementProxy entity is used to represent the OOGP components, and the information in IfcBuildingElementProxy is automatically extracted to obtain the location and dimension information of each OOGP module. Then, for a given layout of modules on the removal vessel, the lift path and removal sequence of different modules, with the shortest lift path distance, are obtained. The lift path distance is calculated using the A* algorithm, which has been widely applied in 2D environments and is modified in this study to suit the 3D environment. Finally, the genetic algorithm (GA) technique is applied to optimize the layout plan on the removal vessel by minimizing the total lift path distance. The developed BIM-based framework is illustrated and evaluated through an illustrative example. The results show that the proposed framework can generate and visualize the shortest lift path for each OOGP module directly and automatically, and significantly improve the efficiency of OOGP disassembly.

Augmented reality (AR), which requires a spatial registration technique, has proved to greatly improve the efficiency of facility maintenance management (FMM) activities. Being one of the most promising techniques for indoor localization, Wi-Fi fingerprinting has been widely used for AR spatial registration. However, localization accuracy of Wi-Fi fingerprinting decreases over time due to dynamics of environmental factors. Readings from different mobile devices can also affect the accuracy negatively. In this paper, a transfer learning technique named transferable CNN-LSTM is proposed for improving the robustness of Wi-Fi fingerprinting while implementing AR in FMM activities. Convolutional neural network (CNN), embedded with long short term memory (LSTM) networks, is utilized to predict the location of unlabeled fingerprints. Multiple kernel variant of maximum mean discrepancy (MK-MMD) is adopted to reduce the distribution difference between the source domain and the target domain, so that the location of the newly collected unlabeled fingerprints can be predicted accurately. As shown in the experimental validation, the transferable CNN-LSTM can achieve an accuracy of 97.1% in short-term (without significant environmental changes) spatial registration, 87.8% in long-term (with significant environmental changes) spatial registration, and around 90% in multi-device spatial registration, indicating a higher accuracy and better robustness over other conventional approaches.

Automated interpretation of closed-circuit television (CCTV) inspection videos could improve the speed and consistency of sewer condition assessment. Previous approaches focus on defect cla...

Construction supply chain management (CSCM) requires the tracking of material logistics and construction activities, an integrated platform, and certain coordination mechanisms among CSCM p...

Security of information in collaborative BIM platforms is crucial particularly for critical projects such as that of government buildings, prisons, and power plants. Inappropriate distribution and loss of sensitive information may potentially lead to physical security threats, financial loss, and loss of trust and reputation. Therefore, this paper identifies the information security requirements of collaborative BIM platforms considering the characteristics related to data security of collaborative BIM platforms through a literature review and as a result, identifies seven components of BIM security, based on which defines three levels of BIM security. Existing cybersecurity facilitating technologies such as encryption protocols, distributed database technology, and blockchain technology are reviewed to assess applicability to BIM security. This review shows that although the technologies to support BIM security are available in research and on market, they are not customized in existing collaborative BIM platforms to support BIM security. Therefore, two conceptual frameworks are proposed – (1) an encryption strategy-based framework to facilitate secure storage and distribution of BIM and (2) a blockchain-based framework to record BIM changes in a tamper-proof ledger for the non-trusting environment of construction projects. Discussions on cost and functionality are provided, which will be further extended in the future.

Steel reinforcement design in practices is performed at individual member level with little considerations of member-member intersections, which results in reinforcement overlaps and congestion. This paper presents a new approach based on building information modeling (BIM) and two-stage genetic algorithms (GA) to automatically optimize the clash-free steel reinforcement design. The approach considers reinforcement overlaps and congestion in beam-column joints and extracts 3D spatial information from design BIM models to underpin the automated clash-free optimization. The beam-column intersections are classified into appropriate categories such as T and cross joints, following by the generation of a clash-free reinforcement layout using the first-stage GA. Given the clash-free layout, the second-stage optimization is conducted using a hybrid GA and Hooke & Jeeves algorithm to calculate the optimal diameter combination of steel reinforcements (with minimum provided steel reinforcement area). An example is provided to illustrate the proposed BIM and two-stage GA based optimization method.

Processing steel reinforcement is an on-site activity that includes cutting and bending, which are time-consuming and uneconomical. When moving toward the construction automation, off-site prefabrication is important with the aid of Building Information Modeling (BIM) and Industry Foundation Classes (IFC) which are utilized as a collaborative approach to facilitate the fabrication workflow and data interoperability. This paper presents the integration of BIM and steel fabrication machine codes (BVBS) with openBIM standards to interoperate the computerized design and prefabrication automation of steel reinforcement. The integration begins with the reference of Information Delivery Manual (IDM) which involves the identification of information requirement in the process map for identifying the necessary data exchange within the prefabrication process. Definition of IFC model views is conducted to ensure that the exchange of data meets the end user's needs and is implementable for software applications. Next, the process information model of steel reinforcement fabrication is established by connecting the IFC entities with relationships among the specific tasks. A new approach is developed to extend the IFC data schema with prefab-related entities. The proposed BIM-BVBS integration is demonstrated utilizing IFC viewers and visual programming tools (Dynamo) in illustrative examples, the results of which reveal that prefab-related entities and attributes in IFC-based BIM models can be extracted efficiently to cater to the BVBS data transformation toward automatic prefabrication.

Due to the decentralisation and complexity of knowledge in the architecture, engineering and construction (AEC) industry, the research on knowledge graphs (KGs) is still insufficient, and most of the research focuses on text-based KG structuring or updating. Entity extraction, a sub-task of knowledge extraction, is critical in general KG update approaches. While the mainstream approach for this task generally uses textual data, visual data is more readily available, more accurate and has a shorter update cycle than textual data. Therefore, this paper integrates zero-shot learning techniques with general KGs to present a novel framework called “video2entities” that can extract entities from videos to update the AEC KG. The framework combines the perceptual capabilities of computer vision with the cognitive capabilities of KG to improve the accuracy and timeliness of KG updates. Experimental results demonstrate that the framework can extract “new entities” from architectural decoration videos for AEC KG updates.

As-built building information modeling (BIM) has gained much attention in mechanical, electrical and plumbing (MEP) systems for better facility management. To create as-built BIMs, laser scanning technology is widely used to collect raw data due to its high measurement speed and accuracy. Currently, as-built models are mostly drawn by experienced personnel in BIM modeling software with point cloud data as reference, which is labor intensive and time consuming. This study presents a fully automated approach to converting terrestrial laser scanning data to well-connected as-built BIMs for MEP scenes. According to the geometry complexity, MEP components are divided into regular shaped components and irregular shaped components. A 2D to 3D analysis framework is developed to detect objects and extract accurate geometry information for the two categories of MEP components. Firstly, the MEP scene is divided into slices on which rough geometry information of components' cross sections is extracted. Then, the extracted information on different slices is integrated and analyzed in 3D space to verify the existence of MEP components and obtain refined geometry information used for modeling. Following the detection stage, an MEP network construction approach is developed for MEP components connection and position fine-tuning. Finally, the extracted geometry information and connection relationships are imported into Dynamo to automatically generate the parametric BIM model. To validate the feasibility of the proposed technique, experiments were conducted with point clouds acquired from three scenes in Hong Kong. A comprehensive assessment is presented to evaluate the as-built model quality with three indices: retrieval rate, geometry parameter accuracy and deviation from point clouds to as-built model. The experiment results show that the proposed technique could successfully transform laser scanning data of MEP scenes to as-built BIMs with sufficient accuracy for facility management purpose.

This study presents a quality inspection technique for full-scale precast concrete elements using laser scanning and building information modeling (BIM). In today's construction industry, there is an increasing demand for modularization of prefabricated components and control of their dimensional quality during the fabrication and assembly stages. To meet these needs, this study develops a non-contact dimensional quality assurance (DQA) technique that automatically and precisely assesses the key quality criteria of full-scale precast concrete elements. First, a new coordinate transformation algorithm is developed taking into account the scales and complexities of real precast slabs so that the DQA technique can be fully automated. Second, a geometry matching method based on the Principal Component Analysis (PCA), which relates the as-built model constructed from the point cloud data to the corresponding as-designed BIM model, is utilized for precise dimension estimations of the actual precast slab. Third, an edge and corner extraction algorithm is advanced to tackle issues encountered in unexpected conditions, i.e. large incident angles and external steel bars being located near the edge of precast concrete elements. Lastly, a BIM-assisted storage and delivery approach for the obtained DQA data is proposed so that all relevant project stakeholders can share and update DQA data through the manufacture and assembly stages of the project. The applicability of the proposed DQA technique is validated through field tests on two full-scale precast slabs, and the associated implementation issues are discussed. Field test results reveal that the proposed DQA technique can achieve a measurement accuracy of around 3.0 mm for dimension and position estimations.

Purpose Literature on organizational analysis identified that project participants have a certain impact on the project outcome. However, there is no study that identifies the impact of project teams and individual project participants on a green building project. The purpose of this paper is to analyze the impact of green building project teams on green building certification. Design/methodology/approach Project information, project team information, and green building certification grade were collected using the Canadian green building database. Project team data were analyzed and organizations were ranked based on their green building project experience and collaborations with experienced green building organizations. The page rank algorithm is used to calculate the rank of organizations in order to identify the impact of organizational rank on the final green building certification grade of a project. Findings The results show a positive relationship between the green building certification grade and the number of organizations with more green building experience in a project team. The results also show that not having experienced key organizations such as owners, designers, and contractors will likely lead to a lower green building certification grade. Originality/value Impact of project teams on green building projects has not been studied before. This study used an innovative method to analyze green building project teams and to investigate the importance of green building project experience. The findings of this study provided evidence to support the influence of project team compositions in green building projects. The results presented in this paper can help project owners and managers during project team formation for successful execution of green building projects.

Precast concrete elements are popularly used and it is important to ensure that the dimensions of individual elements conforms to design codes. However, the current quality assessment of precast concrete elements is inaccurate and time-consuming. To address the problems, this study presents an automated quality assessment technique which estimates the dimensions of precast concrete elements with geometry irregularities using terrestrial laser scanners (TLS). While the scan data obtained from TLS represent the as-built condition of an element, a Building Information Modeling (BIM) model stores the as-design condition of the element. Taking the BIM model as a reference, the scan data are processed to estimate the as-built dimensions of the element. Experiments on a specimen demonstrated that the proposed technique can estimate the dimensions of elements effectively and accurately. Furthermore, a mirror-aided scanning approach, which aims to achieve reduced incident angles in real scanning environments, is proposed and validated by experiments.

Developed by the U.S. Green Building Council, Leadership in Energy and Environmental Design (LEED) certifies green buildings into different grades according to the number of credit points each building has achieved. LEED managers often attempt to achieve as many credits as possible with limited budgets and resources. However, referring to the credit requirements alone does not help evaluate the difficulty in achieving those credits. Data on how LEED credits were achieved in previous projects may offer some insights, yet no research has quantitatively analyzed the previous records. This study aims to analyze LEED credit achievements in previous projects using data driven techniques and provide LEED managers with a better understanding on the achievements of individual credits and related credits. 1000 projects certified by LEED-NC v3 were collected as the case base. A measurement called the percentage of average score (PAS) was proposed to analyze how individual credits were attained in the past. Credits like MRc6 and MRc3 were discovered to have stringent requirements and were rarely achieved. In addition, relationships among credits were analyzed using association rule mining. Thresholds for support and confidence were identified by implementing a classification algorithm namely CMAR. Among 224 pairs of related credits that are suggested by USGBC, 50 pairs were identified as strongly related. In addition, 13 new pairs of related credits that have not been suggested by USGBC were discovered.

The variation of construction machine poses is one of the main causes for interactive on-site safety issues such as struck-by hazards. With the aim to reduce such hazards, we propose a framework for predicting construction machine poses based on historical motion data and activity attributes. After building a machine motion dataset, we develop a keypoint-based method for recognizing machine activities considering working patterns and interaction characteristics. The recognized activity information is then incorporated with historical pose data to predict future machine poses through a type of recurrent neural network (RNN), named Gated Recurrent Unit (GRU). In experiments of using excavators as the objects, our framework achieves decent performance for machine pose prediction, which is further improved by incorporating activity information, reaching an average percentage of correct keypoints (PCK) of 90.22%. The results indicate the high potential of our framework in predicting construction machine poses and improving on-site safety.

Computer vision techniques are widely studied for automating the interpretation of sewer pipe inspection videos, yet previous studies mainly focus on defect detection and segmentation of individual images, which cannot identify if the defect is the same one across consecutive video frames (i.e. track the defect). Nevertheless, the number of unique defects in the video is required for evaluating the pipe condition. This paper proposes a framework for tracking multiple sewer defects in CCTV videos based on defect detection and metric learning. First, a deep learning -based defect detection model and a metric learning model is developed and trained respectively using with our sewer datasets. Then, using the detections and their features from the trained models as inputs, the tracking module predicts tracks by Kalman filter and associates tracks based on defect motion, appearance features, and defect types. Our experiments demonstrate the framework is able to track sewer defects in CCTV videos with a decent IDF1 score of 57.4%. We notice that tracking performance can be influenced by the detection accuracy and configurations of the metric learning module. By analyzing the tracking results based on different weights of the distance metrics, we find that assigning larger weights to appearance and defect class distance metrics tends to increase IDF1 score, while larger motion distance weight may degrade tracking accuracy. The proposed framework contributes by tracking multiple sewer defects, which can assist with counting unique defects in inspection videos.

Indoor positioning complements the mature outdoor positioning technology, Global Navigation Satellite System (GNSS), by achieving real-time positioning in any environment under a blockage of GNSS signals. In the construction management field, this paper demonstrates that indoor positioning enables five significant applications that considerably enhance work efficiency and safety on construction sites. Without a perfect indoor positioning system and under complicated site environment, developing a suitable on-site indoor positioning system is challenging and essentially user-oriented and environment-specific. This paper analyses the challenges to implement on-site indoor positioning systems, and proposes indoor positioning performance metrics, namely APP-CAT, for evaluating indoor positioning systems. The fundamental indoor positioning principles are first discussed and evaluated. Subsequently, the top 10 indoor positioning technologies, selected by their performance in APP-CAT and their popularity, are thoroughly compared. The promising trends of indoor positioning development, e.g., indoor positioning hybridization, game theory positioning, and integration with BIM models, are highlighted.

Interim payment provisions in construction projects are susceptible to unfair practices. In construction project participants with varying financial capacities belonging to different organizations are bound by contractual relationships. Due to this type of project organizational structure, project participants do not completely trust each other which prevents the adoption of existing centralized automated frameworks for interim payment. Therefore, this paper presents a distributed blockchain-based framework that does not require to be trusted for automatically enforcing the terms and conditions related to interim payments and sharing payment records at project-level transparently and securely. A logic to automatically initiate, validate, and disburse interim payments according to general contract conditions for interim payments is formalized in this paper. A blockchain-based data model that enables selective-transparency in payment records is proposed. This data model facilitates the sharing of sensitive financial information privately between two contracting parties and non-sensitive payment-related information publicly among all project participants. The proposed blockchain-based framework is supported by a key management strategy to facilitate different security properties such as confidentiality and authenticity of data and users. Considering the non-technical nature of construction project participants, the proposed key management strategy is designed to dynamically generate cryptographic keys from publicly sharable parameters so that storage and management overheads are reduced. Security properties such as immutability, data confidentiality, user integrity, performance, and cost of deployment of the proposed blockchain framework are validated and recommendations for executing the proposed framework with a high level of security are discussed in this paper.

To better support the prevention of air pollutions for sustainable cities, researchers have studied different methods to forecast air pollutant concentrations. Existing methods have gone through the development from deterministic methods, statistical methods, to machine learning and deep learning methods. The latest direction lies in Long Short-Term Memory (LSTM) based methods. They are a special kind of deep learning network, and can not only well model non-linear real-world problems, but also consider the impact of long-historical values. These methods have achieved state-of-the-art performance in air quality predictions, but some gaps have not been well addressed, especially the overlook on the multi-sequential-variants, and the lack of efficient parameter optimization in the deep learning models. To this end, this study proposes a Lag-FLSTM (Lag layer-LSTM-Fully Connected network) model based on Bayesian Optimization (BO) for multivariant air quality prediction. A case study in the U.S. is conducted to test the method. The results showed that Lag-FLSTM has at least 23.86 % lower RMSE than other methods. The contributions of this study are that we not only developed a deep learning method that can automatically optimize the model parameters but also studied how different metrological features and other pollutants affect the prediction of PM2.5 concentrations.

Improving the energy efficiency of the buildings is a worldwide hot topic nowadays. To assist comprehensive analysis and smart management, high-quality historical data records of the energy consumption is one of the key bases. However, the energy data records in the real world always contain different kinds of problems. The most common problem is missing data. It is also one of the most frequently reported data quality problems in big data/machine learning/deep learning related literature in energy management. However, limited studied have been conducted to comprehensively discuss different kinds of missing data situations, including random missing, continuous missing, and large proportionally missing. Also, the methods used in previous literature often rely on linear statistical methods or traditional machine learning methods. Limited study has explored the feasibility of advanced deep learning and transfer learning techniques in this problem. To this end, this study proposed a methodology, namely the hybrid Long Short Term Memory model with Bi-directional Imputation and Transfer Learning (LSTM-BIT). It integrates the powerful modeling ability of deep learning networks and flexible transferability of transfer learning. A case study on the electric consumption data of a campus lab building was utilized to test the method. Results show that LSTM-BIT outperforms other methods with 4.24% to 47.15% lower RMSE under different missing rates.

As-built building information models (BIMs) are increasingly needed for construction project handover and facility management. To create as-built BIMs, laser scanning technology has gained popularity in the recent decades due to its high measurement accuracy and high measurement speed. However, most existing methods for creating as-built BIMs from laser scanning data involve plenty of manual work, thus becoming labor intensive and time consuming. To address the problems, this study presents a semi-automated approach that can obtain required parameters to create as-built BIMs for steel structures with complex connections from terrestrial laser scanning data. An algorithm based on principal component analysis (PCA) and cross-section fitting techniques is developed to retrieve the position and direction of each circular structural component from scanning data. An image-assisted edge point extraction algorithm is developed to effectively extract the boundaries of planar structural components. Normal-based region growing algorithm and random sample consensus (RANSAC) algorithm are adopted to model the connections between structural components. The proposed approach was validated on a bridge-like steel structure with four different types of structural components. The extracted as-built geometry was compared with the as-designed geometry to validate the accuracy of the proposed approach. The results showed that the proposed approach could efficiently and accurately extract the geometry information and generate parametric BIMs of steel structures.

To better control and manage harbor water quality is an important mission for coastal cities such as New York City (NYC). To achieve this, managers and governors need keep track of key quality indicators, such as temperature, pH, and dissolved oxygen. Among these, the Biochemical Oxygen Demand (BOD) over five days is a critical indicator that requires much time and effort to detect, causing great inconvenience in both academia and industry. Existing experimental and statistical methods cannot effectively solve the detection time problem or provide limited accuracy. Also, due to various human-made mistakes or facility issues, the data used for BOD detection and prediction contain many missing values, resulting in a sparse matrix. Few studies have addressed the sparse matrix problem while developing statistical detection methods. To address these gaps, we propose a deep learning based model that combines Deep Matrix Factorization (DMF) and Deep Neural Network (DNN). The model was able to solve the sparse matrix problem more intelligently and predict the BOD value more accurately. To test its effectiveness, we conducted a case study on the NYC harbor water, based on 32,323 water samples. The results showed that the proposed method achieved 11.54%-17.23% lower RMSE than conventional matrix completion methods, and 19.20%-25.16% lower RMSE than traditional machine learning algorithms.

Construction sites are among the most hazardous places with various safety issues. The high rate of hazards on construction sites can be attributed to the dynamic and complex characteristics of construction-related entities, such as the movement of construction equipment and workers as well as the interactions among them. Tracking construction equipment and workers can help avoid potential collisions and other accidents to achieve safer on-site conditions. As construction equipment (e.g. excavators, trucks, cranes, and bulldozers) plays a significant role in construction projects, it is important to track the location, pose and movement of construction equipment. Currently, with the wide installation of surveillance cameras on construction sites, computer vision techniques are explored to process the captured surveillance videos and images, such as to monitor the site conditions and prevent potential hazards. Previous studies have attempted to identify and locate different types of construction equipment on construction sites based on surveillance videos using computer vision techniques. However, there are limited studies that automatically estimate the full body pose and movement of on-site construction equipment, which can greatly influence the safety condition of construction sites and the utilization of the equipment itself. In this study, a methodology framework is developed for automatically estimating the poses of different construction equipment in videos captured on construction sites using computer vision and deep learning techniques. Firstly, keypoints of equipment are defined, based on which the images collected from the surveillance cameras are annotated to generate the ground truth labels. 70%, 10%, and 20% of the annotated image dataset are used for training, validation and testing, respectively. Then, the architectures of three types of deep learning networks i.e. Stacked Hourglass Network (HG), Cascaded Pyramid Network (CPN), and an ensemble model (HG-CPN) integrating Stacked Hourglass and Cascaded Pyramid Network are constructed and trained in the same training environment. After training, the three models are evaluated on the testing dataset in terms of normalized errors (NE), percentage of correct keypoints (PCK), area under the curve (AUC), detection speed, and training time. The experiment results demonstrate the promising performance of our proposed methodology framework for automatically estimating different full body poses of construction equipment with high accuracy and fast speed. It is indicated by experiments that both HG and CPN can achieve relative high accuracy, with a PCK value of 91.19% and 91.78% respectively for estimating the equipment full body poses. In addition, the ensemble model with online data augmentation can further improve the accuracy, achieving a NE of 14.57 × 10−3, a PCK of 93.43%, and an AUC of 39.72 × 10−3 at the detection speed of 125 millisecond (ms) per image. This study lays the foundation for applying computer vision and deep learning techniques in the full body pose estimation of construction equipment, which can contribute to the real-time safety monitoring on construction sites.

Precast concrete bridge deck panels are commonly used for bridge constructions because they enable faster construction and have less impact on traffic flow. The quality of connections betwe...

Traffic noise is a major health concern for people living in urban environments. Noise mapping can help evaluating the noise level for certain areas in a city. Traditionally, noise mapping is performed in 2D geographic information system (GIS). The use of 3D GIS is also emerging in noise mapping in recent years. However, the current noise-mapping platforms can only conduct noise evaluation for the outdoor environment and the indoor environment separately. In addition, related information about absorption coefficient and transmission loss (TL) in noise calculation is not properly retrieved and is often replaced with a single value. In this research, building information modelling (BIM) and 3D GIS are integrated in order to combine traffic noise evaluation in both outdoor environments and indoor environments in a single platform. In our developed BIM–GIS integration platform, the built environment is represented in a 3D GIS model that contains information at a high level of detail from BIM. With the...

Site layout planning is often performed on construction sites to find the best arrangement of temporary facilities so that transportation distances of on-site personnel and equipment are minimized. It could be achieved by creating dynamic layout models, which capture the changing requirements of construction sites. However, formulating such models is extremely tedious because it requires much manual data input and changes to design and construction plans are manually updated by layout planners. This study presents an automated framework of creating dynamic site layout models by utilizing information from BIM. The A* algorithm is used in conjunction with genetic algorithms to develop an optimization framework that considers the actual travel paths of on-site personnel and equipment. To address the space limitation on site, our model optimizes the dimensions of facilities and also considers interior storage within buildings under construction. A case example is demonstrated to validate this framework and shows a 13.5% reduction in total travel distance compared with conventional methods.

Leadership in Energy and Environmental Design (LEED) is a widely used international green building certification program developed by the U.S. Green Building Council (USGBC). Although the need for LEED certification has grown significantly, LEED managers still face challenges in target credit selection and green building technology design. They frequently meet new types of projects with different project characteristics and requirements. Therefore, it would be helpful if LEED managers could refer to other similar certified green building cases when planning and designing LEED projects. However, this is not supported in current studies and research. This paper proposes a case-based reasoning (CBR) approach to provide case studies of similar certified green building projects and suggestions on target LEED credits. Currently, linear formation of Local-Global method is commonly used in the retrieval step of CBR. This paper presents a non-linear formation of Local-Global retrieval based on Artificial Neural Network (ANN), which can provide a higher accuracy. LEED for New Construction (LEED-NC) is the focus of this paper, and 1000 LEED-NC v2009 certified cases were collected for the case base. Pairwise comparison was conducted to generate the local distance (attribute similarity) and the target for training the ANN model. The proposed non-linear CBR approach was tested and evaluated using 20 recently certified projects, and the results showed a prediction accuracy of 80.75% on the LEED credit selection. The results were also compared with those calculated by commonly used linear CBR approaches: Multiple Regression Analysis, Correlation Analysis, and the k-NN approach. The accuracy achieved by these methods was between 71.23% and 77.54%, which was lower than the proposed approach.

Purpose – The purpose of this paper is to present a framework for integrating construction supply chain in order to resolve the data heterogeneity and data sharing problems in the construction industry. Design/methodology/approach – Standardized web service technology is used in the proposed framework for data specification, transfer, and integration. Open standard SAWSDL is used to annotate web service descriptions with pointers to concepts defined in ontologies. NoSQL database Cassandra is used for distributed data storage among construction supply chain stakeholders. Findings – Ontology can be used to support heterogeneous data transfer and integration through web services. Distributed data storage facilitates data sharing and enhances data control. Practical implications – This paper presents examples of two ontologies for expressing construction supply chain information – ontology for material and ontology for purchase order. An example scenario is presented to demonstrate the proposed web service framework for material procurement process involving three parties, namely, project manager, contractor, and material supplier. Originality/value – The use of web services is not new to construction supply chains (CSCs). However, it still faces problems in channelizing information along CSCs due to data heterogeneity. Trust issue is also a barrier to information sharing for integrating supply chains in a centralized collaboration system. In this paper, the authors present a web service framework, which facilitates storage and sharing of information on a distributed manner mediated through ontology-based web services. Security is enhanced with access control. A data model for the distributed databases is also presented for data storage and retrieval.

Developed by the USGBC, LEED is currently the most widely adopted credit-based green building rating program worldwide. Buildings can be graded as Platinum, Gold, Silver, or Certified depending on the number of LEED credit points achieved. Selection of LEED credits is an important step in LEED certification planning and application. The relationships between LEED credit achievement and project factors like budget and schedule have already been studied. Apart from these, climate factors such as temperature and precipitation can also affect the selection of green building technologies and therefore the LEED credits achieved. However, study on the relationships between LEED credit achievement and the climate of the building location is lacking. This paper investigates the relationship between climate factors and LEED credits using data mining techniques. The LEED credits achieved and the local climate conditions of 912 LEED certified existing building projects were collected and analyzed. By setting the climate factors as variables and the credit achievements as the targets, 26 classification models were built using the Random Forests classification algorithm. The variable importance for each credit was then calculated based on the contribution to the classification performance. For the models with high AUC performance, high importance climate factors were identified and discussed. The results show that some climate factors, such as diurnal temperature range, have a notable correlation with the achievement of certain LEED credits. Implications and contributions of the results are also discussed.

This study presents a systematic and practical approach for dimensional and surface quality assessment of precast concrete elements using building information modeling (BIM) and 3D laser scanning technology. As precast concrete based rapid construction is becoming commonplace and standardized in the construction industry, checking the conformity of dimensional and surface qualities of precast concrete elements to the specified tolerances has become ever more important in order to prevent failure during construction. Moreover, as BIM gains popularity due to significant developments in information technology, an autonomous and intelligent quality assessment system that is interoperable with BIM is needed. The current methods for dimensional and surface quality assessment of precast concrete elements, however, rely largely on manual inspection and contact-type measurement devices, which are time demanding and costly. In addition, systematic data storage and delivery systems for dimensional and surface quality assessment are currently lacking. To overcome the limitations of the current methods for dimensional and surface quality assessment of precast concrete elements, this study aims to establish an end-to-end framework for dimensional and surface quality assessment of precast concrete elements based on BIM and 3D laser scanning. The proposed framework is composed of four parts: (1) the inspection checklists; (2) the inspection procedure; (3) the selection of an optimal scanner and scan parameters; and (4) the inspection data storage and delivery method. In order to investigate the feasibility of the proposed framework, case studies assessing the dimensional and surface qualities of actual precast concretes are conducted. The results of the case studies demonstrate that the proposed approach using BIM and 3D laser scanning has the potential to produce an automated and reliable dimensional and surface quality assessment for precast concrete elements.

This study aims to improve the underground utility management efficiency from the perspective of utility component and urban utility network, as well as to facilitate the decision-making for utility maintenance work. The main reasons for the inefficient information sharing, poor utility management and reactive decision-making are investigated, after which potential solutions are explored. An integrated utility management framework is proposed based on the integration of Building Information Modeling (BIM) and Geographic Information System (GIS), for which a common utility data model representing utility information in five aspects is developed to facilitate the mapping of Industry Foundation Classes (IFC) and City Geography Markup Language (CityGML). The verification of the proposed framework indicates that the developed data model can represent utility information comprehensively, based on which functions of the integrated BIM-GIS platform are developed to support underground utility management in terms of individual utility components and the utility spatial networks. With the proposed utility management framework, the information sharing process, utility management efficiency and decision-making can be improved and facilitated. In the future, more functions of the framework will be developed according to practical requirements and more maintenance data will be utilized to validate and enhance the framework.

The benefits of integrating and coordinating supply chain partners have been well recognized in many industries. In the construction industry, supply chain integration is technically challenging due to the high fragmentation of the industry. Information, applications, and services are loosely distributed among participants with a wide range of hardware and software capabilities. In addition, participants are often unwilling to share information because the temporary nature of construction projects often impedes the establishment of trust. A secure, modular, and flexible system that can aggregate scattered information and share that information across applications is, therefore, highly desirable. We have prototyped a service oriented, web-based system that can provide both these capabilities. Called the SC Collaborator, this system facilitates the flexible coordination of construction supply chains by leveraging web services, web portal, and open source technologies. These technologies enable the SC Collaborator system to provide an economical and customizable tool for integrating supply chain partners with a wide range of computing capabilities. This paper describes the overall architecture and the features of the system. Two example scenarios are included to demonstrate the potential of SC Collaborator in integrating and managing information from project partners. The first scenario is an e-Procurement example whereas the second is a rescheduling scenario based on the data from a completed project in Sweden. (C) 2009 Elsevier B.V. All rights reserved.