資源
分享此頁:
列印
列印
香港專上院校所提供之論文/研究刊物
| 院校 | 題目 | 類型 | 日期 | 作者 | 摘要 | 網頁 |
|---|---|---|---|---|---|---|
| HKUST | Development of BIM-assisted Access Point Placement Optimization and Deep Learning based Multi-floor Identification Algorithms for Enhancing Indoor Positioning to Support Construction Applications | Thesis | 08/2019 | Kenneth Chun Ting LI | Over the past decades, indoor positioning has been drawing wide attention in different fields of engineering. Indoor positioning technologies are complementary to the mature outdoor positioning technology such that the indoor positioning technologies can provide a real-time positioning service in any environment where there is a blockage of GNSS signals. In the fields of construction and facility management, indoor positioning technologies enable promising applications that can considerably enhance the productivity, efficiency and safety on construction sites, supporting five major applications, which are (1) construction safety management, (2) construction process monitoring and control, (3) inspection of construction structures and materials, (4) construction automation with robotics, and (5) the use of building information modelling (BIM) technology for construction progress management. Currently, there is no single perfect indoor positioning system that can perform optimally under any circumstances. In addition, due to the large variety of indoor positioning technologies and principles, as well as the complex and dynamic environment on construction sites, developing suitable indoor positioning systems on construction sites is a challenging task. Applying indoor positioning systems is essentially user-oriented and environment-specific. This thesis thus analyses the challenges to apply indoor positioning systems on construction sites, and then proposes six indoor positioning performance metrics, namely APP-CAT, for evaluating suitable on-site indoor positioning systems. Subsequently, the top 10 indoor positioning technologies, which are selected according to their evaluation results using APP-CAT and their popularity amongst the indoor positioning literature studies, are thoroughly discussed and compared. The promising recent trends of developing on-site indoor positioning systems, such as infrastructure-free positioning, collaborative positioning, game theory positioning, and device-free positioning, as well as integration of indoor positioning technologies with BIM models, are also highlighted. In this research work, the comprehensive discussion of current development in indoor positioning from different aspects is intended to help academics, researchers, and industry practitioners develop high-performing and suitable on-site indoor positioning systems for supporting various engineering and construction applications. Among various positioning technologies, Wi-Fi fingerprinting has emerged as a popular technique due to the wide coverage of Wi-Fi signals and its high compatibility with smartphones. Wi-Fi fingerprinting utilizes the patterns of the Wi-Fi signal strengths, which are measured by the Received Signal Strength Index (RSSI), for position estimation. Normally, Wi-Fi access points are placed arbitrarily, which causes a poor positioning accuracy. In fact, positioning accuracy can be considerably enhanced by optimizing the access point (AP) placement strategy. In light of the high popularity of Wi-Fi fingerprinting and the liberty to design AP placemnent strategies on construction sites, this thesis aims to conduct AP placement optimization is by finding the optimal AP placement strategy that maximizes the distinctiveness between individual Wi-Fi fingerprints in a 3D virtual environment. The use of BIM technology provides 3D geometric and semantic information to accurately reproduce the virtual environment for realistic simulation of Wi-Fi signal propagation. Wi-Fi signal propagation is usually modelled by a modified indoor radio wave path loss model, but such models cannot easily consider the multipath effect in an indoor environment. Therefore, in this thesis, an accurate Deep Belief Network (DBN) based path loss model, which considers the multipath effect emulated by the ray-tracing method using particle swarm optimization (PSO), is proposed and implemented to predict the indoor Wi-Fi signal strengths. Based on the results of the simulation, the optimal AP placement strategy as well as the geometrically-constrained optimal AP placement strategy can be obtained by using the genetic algorithm (GA). The test results in a university library have shown that the developed AP placement optimization algorithm could consistently enhance the accuracy of 3D indoor positioning under the circumstances of different numbers of APs and the presence of geometric constraints. Facility management is often performed in a multi-floor indoor environment such as shopping malls and airports. However, one of the major challenges facing the received signal strength indicator (RSSI) based fingerprinting is the inability to perform accurate indoor positioning in a multi-floor environment, despite their popularity. The multi-floor environment poses a large challenge to RSSI fingerprint-based indoor positioning because the uniqueness of RSSI fingerprints is largely lost in a multi-floor environment, especially when ring structure exists in the building. Such a ring structure is commonly found in large airports and shopping malls. In this thesis, in light of the analogy between visual images and a radio map, a novel twofold multi-floor localization algorithm based on convolutional neural network (CNN) is developed to perform robust and accurate multi-floor localization. To support the twofold CNN model and to improve the localization accuracy, the similar selective search algorithm and data augmentation algorithm are proposed. Lastly, with the support of inertial measuring units (IMUs), the snapping algorithm is proposed to convert a random trajectory to a grid shape for the purpose of localization. Per the validation results, the proposed multi-floor localization algorithm is capable of identifying on which floor the user is located such that the “floor jumping” problem is mitigated, and thus the overall indoor positioning accuracy on RSSI fingerprint-based indoor positioning is substantially improved during indoor navigation. To summarise, this thesis provides a comprehsive review of the top 10 indoor positioning technologies for their usage on construction sites, and aims to develop a BIM-assisted access point placement optimization and deep learning based multi-floor identification algorithms for enhancing indoor positioning to support construction applications for both construction management and facility managment. |
N.A. |
| HKUST | Evaluation and Development of Automated Detailing Design Optimization Framework for RC Slabs Using BIM and Metaheuristics | Thesis | 08/2019 | Muhammad AFZAL | Reinforced concrete (RC) structural design optimization has been undertaken for several decades and plays an important role in maximizing the reliability, cost efficiency, and environmental sustainability of RC structures. However, optimization of RC structural design is challenging and requires advanced strategies during different life cycle phases of RC structures. Over the past few decades, substantial fundamental research efforts in RC structural design optimization have been undertaken, but there is a lack of a comprehensive review of these efforts that can provide academic and industry practitioners with sufficient detailed insights. Therefore, this research introduces a critical evaluation of previous research related to the optimization of RC structures for minimizing the amount of construction materials, the material cost, and the environmental effects, with more emphasis on detailing design (such as steel reinforcement), aiming to identify the common research themes and highlight the future directions. Based on the critical evaluation, the portfolio of 348 available research articles presents the identified research gaps and potential future research directions. For example, the adoption of clash-free rebar design optimization, detailing design optimization of complex and irregular RC components, and the concentration of design for manufacture and assembly (DfMA) aspects, are seldom conducted and studied. Moreover, steel reinforcement detailing design of RC structures is one of the common and important tasks in building construction. Currently, despite having introduced advanced computing technologies in the architecture, engineering, and construction (AEC) industry, the rebar detailing design process is still predominantly performed by manual or at least semi-manual approaches, with the aid of computer software packages following the regional design codes. Manual or semi-manual perspectives often result in conservative, uncertain, and sometimes unacceptable outcomes. Additionally, the simple design of RC structural elements can potentially face constructability issues such as congestion, collision, and complexity which may cause complications during the procurement of rebars and other elements all along the construction phase. These issues also hinder concrete pouring and as a result, generate improper compounding of concrete with the rebars which disturb the integrity of the RC structure. All these concerns substantially increase the construction cost, time and quality and thus are uneconomical for AEC industry stakeholders. Although a few previous studies have conducted detailing design optimization of RC structures, very little attention has been given to the above-mentioned issues. Therefore, this research also aims to develop a holistic BIM-based framework utilizing the different meta-heuristic algorithms (such as SGA, SGA-SQP, and PSO-SQP, etc.) for the optimal detailing design of RC solid slabs, considering the minimization of overall construction cost. The main objective function determines the overall minimized construction cost of the RC solid slab, including the cost of steel reinforcement bars in all reinforcing layers, the cost of concrete, and the cost of labor for installing the steel reinforcement bars and pouring the concrete in the RC solid slab. The optimization process is handled in such a way that the first stage optimizes the steel reinforcement present in all four reinforcing layers (two layers each at the bottom and top of solid slab), while the second stage optimizes the solid slab thickness based on the characteristic concrete strength. For the optimum design to be directly constructible without any further alterations, aspects such as available standard rebar diameters, spacing requirements of the rebars, relevant regional design provisions (i.e. British Standards), and the above-mentioned constructability (more specifically clash-avoidance) concerns, are also incorporated into the development of optimization model. In this research, a case study of a typical RC solid slab containing one-way and two-way spanning slab panels is analyzed to investigate the capabilities of the proposed framework. The results demonstrate the potential of the developed model in producing optimum and realistic design solutions. The developed model can be utilized as a design tool to retrieve economical design solutions at the early-stage structural detailing design. |
N.A. |
| HKUST | Application of Mixed Reality Technology for Operations and Maintenance of Building Facilities | Thesis | 08/2019 | Keyu CHEN | The architecture, engineering, construction and operation (AECO) industry has been widely regarded as a highly resource consuming industry. Among different stages of the AECO industry, the operations and maintenance (O&M) lasts the longest in the lifecycle of a building and incurs more than 85% of the total costs, indicating the importance of optimizing management and improving efficiency during O&M. However, it was indicated that two-thirds of the estimated cost of facility management is lost due to inefficiencies during the O&M stage. With current approaches for O&M activities, it is difficult for people to directly visualize and update information of building facilities and many¬ facilities are hidden (e.g. ventilation ducts above ceilings and water pipes under floors). Therefore, this research aims to apply innovations to improve efficiency during the O&M stage. In recent years, professionals begin to realize the practical value of mixed reality (MR) technology, which can aid in various tasks during O&M. Through integrating virtual information with the real world, MR makes the information of users surrounding facilities readable and manipulable. However, there are two major limitations while implementing MR in O&M: (1) All existing methods for MR spatial registration have their own limitations in either accuracy or practicality. (2) There is a lack of efficient methods for data transfer from BIM to MR, which limits the functionality and complexity of MR applications. To tackle these limitations, this research develops an MR engine that can achieve accurate and robust MR spatial registration and efficient data transfer from BIM to MR. For the development of the MR engine, an indoor localization approach is proposed for MR spatial registration. A transfer learning technique named transferable CNN-LSTM is proposed for improving the accuracy of localization and reducing Wi-Fi fingerprinting’s vulnerability to environmental dynamics. A deep learning approach that combines convolutional neural network (CNN) with long short term memory (LSTM) networks is first proposed to predict the locations of unlabeled fingerprints based on labeled fingerprints. Then the transferable CNN-LSTM model is derived from the CNN-LSTM networks based on transfer learning to improve the robustness against time and devices. The proposed transferable CNN-LSTM model is tested and compared with some conventional approaches and even some transfer learning approaches. Another part of the engine focuses on efficient mechanisms for BIM-to-MR data transfer. An ontology-based approach is proposed for transfer of semantic data. For geometric models, building components are classified into four types according to their different features and different model simplification algorithms are proposed accordingly. The algorithms were first tested with single components, and then a whole building was used to evaluate the overall performance of the developed mechanisms. As illustrated in the tests, the developed mechanisms can efficiently transfer both semantic information and geometric information of BIM models into MR applications, thus reducing the time for model transfer and improving the fluency of corresponding MR applications. The developed MR engine is then applied to facility maintenance management (FMM) and emergency evacuation. To improve the efficiency of FMM, a BIM-based location aware MR collaborative framework is developed, with BIM as the data source, MR for interaction between users and facilities, and Wi-Fi fingerprinting for providing real-time location information. An experiment is designed to evaluate the effectiveness of the developed system framework. For emergency evacuation, a graph-based network is formed by integrating medial axis transform (MAT) with visibility graph (VG), with the addition of buffer zones. Closed-circuit television (CCTV) processing techniques are also developed to monitor the flow of people so that evacuees can avoid congested areas. An Internet of things (IoT) sensor network is established as well to detect the presence of hazardous areas. With the constructed graph-based network, congestion analysis and environment index of each area, an optimal evacuation path can be obtained and augmented with MR devices. This research develops an MR engine that can improve the accuracy and robustness of conventional Wi-Fi fingerprinting based MR spatial registration and efficiency of BIM-to-MR data transfer. The developed MR engine has been implemented in FMM and emergency evacuation, illustrating the potential of the proposed approaches in improving the efficiency of O&M activities. |
N.A. |
| HKUST | A BIM-based location aware AR collaborative framework for facility maintenance management | Journal | 07/2019 | Chen, K., Chen, W., Li, C.T., and Cheng, J.C.P. | Facility maintenance management (FMM) accounts for a large amount of the total cost of facilities’ lifecycle, illustrating the importance of improving FMM efficiency. Many mechanical facilities, like ventilation ducts above ceilings, are normally hidden, indicating the necessity of applying certain technology that can enable users to visualize and update the information of hidden facilities. Real-time location information is also needed so that users can be aware of their current location and the surrounding facility can be displayed accordingly. Therefore, this paper aims to develop location aware augmented reality (AR) framework for FMM, with building information modeling (BIM) as the data source, AR for the interaction between users and facilities, and Wi-Fi fingerprinting for providing real-time location information. The developed framework has the following features: (1) a proposed softmax-based weighted K nearest neighbour (S-WKNN) algorithm is used for Wi-Fi fingerprinting to obtain the current location of users; (2) a room identification method, based on BIM, the obtained location, and ray casting algorithm, is proposed to identify which room the user is currently in; (3) according to the obtained location and the identified room, users can visualize and interact with their surrounding facilities through the AR devices; and (4) users in a remote location can visualize site situation and interact with site facilities in real time through video streaming and the shared database. At the end of the paper, an experiment was designed to evaluate the effectiveness of the developed system. As shown by the experiment, the developed AR collaborative system can reduce the completion time of the designed task by around 65% compared with traditional 2D drawing-based method, and can provide a localization accuracy of around 1m |
連結 |
| HKUST | Automatic generation of fabrication drawings for facade mullions and transoms through BIM models | Journal | 07/2019 | Deng, M., Gan, V.J.L., Singh, J., Joneja, A., and Cheng, J.C.P. | Fabrication drawings are essential for manufacturing, design evaluation and inspection of building components, especially for building façade structural components. In order to clearly represent the physical characteristics of the façade structural components, a large number of section views need to be produced, which is very time-consuming and labor intensive. Therefore, automatic generation of fabrication drawings for building façade components (such as mullions and transoms) is of paramount importance. In this paper, attempts have been made to develop an efficient framework in order to automatically generate fabrication drawings for building façade structural components, including mullions and transoms. To represent the complex physical characteristics (such as holes and notches) on mullions and transoms using minimum number of drawing views, a computational algorithm based on graph theory is developed to eliminate duplicated section views. Another methodology regarding the generation of breaks for top views is also proposed to further improve the quality of drawing layouts. The obtained drawing views are then automatically arranged using a developed approach. In addition, primary dimensions of the drawing views focusing on the physical features are also generated. Furthermore, in order to maintain the consistency of drawing formats across multiple drawings, a methodology is proposed to determine the scaling factors of the drawings by using clustering technique. In an illustrative example, the proposed framework is used to generate the fabrication drawings for a typical BIM model containing façade structural components, and saving in time is observed. | 連結 |
| HKUST | Parametric modeling and evolutionary optimization for cost-optimal and low-carbon design of high-rise reinforced concrete buildings | Journal | 07/2019 | Gan, V.J.L., Wong, C.L., Tse, K.T., Cheng, J.C.P., Lo, I.M.C., and Chan, C.M. | Design optimization of reinforced concrete structures helps reducing the global carbon emissions and the construction cost in buildings. Previous studies mainly targeted at the optimization of individual structural elements in low-rise buildings. High-rise reinforced concrete buildings have complicated structural designs and consume tremendous amounts of resources, but the corresponding optimization techniques were not fully explored in literature. Furthermore, the relationship between the optimization of individual structural elements and the topological arrangement of the entire structure is highly interactive, which calls for new optimization methods. Therefore, this study aims to develop a novel optimization approach for cost-optimal and low-carbon design of high-rise reinforced concrete structures, considering both the structural topology and individual element optimizations. Parametric modelling is applied to define the relationship between individual structural members and the behavior of the entire building structure. A novel evolutionary optimization technique using the genetic algorithm is proposed to optimize concrete building structures, by first establishing the optimal structural topology and then optimizing individual member sizes. In an illustrative example, a high-rise reinforced concrete building is used to examine the proposed optimization approach, which can systematically explore alternative structural designs and identify the optimal solution. It is shown that the carbon emissions and material cost are both reduced by 18–24% after performing optimization. The proposed approach can be extended to optimize other types of buildings (such as steel framework) with a similar problem nature, thereby improving the cost efficiency and environmental sustainability of the built environment. | 連結 |