FYPs/Thesis/Journal from Higher Education Institutions in Hong Kong


Below Information is provided by the Higher Insitutions signed MoU with CIC.



Date: From


Institution Title Type Date Author(s) Abstract Link
HKUST Semi-automated generation of parametric BIM for steel structures based on terrestrial laser scanning data Journal 01/2020 Yang, L., Cheng, J.C.P., and Wang, Q. 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. Link
HKUST Data-driven predictive maintenance planning framework for MEP components based on BIM and IoT using machine learning algorithms Journal 01/2020 Cheng, J.C.P., Chen, W., Chen, K., and Wang, Q. Facility managers usually conduct reactive maintenance or preventive maintenance strategies in building maintenance management. However, there are some limitations that reactive maintenance cannot prevent failure, and preventive maintenance cannot predict the future condition of MEP components and repair in advance to extend the lifetime of facilities. Therefore, this study aims to apply a predictive maintenance strategy with advanced technologies to overcome these limitations. Building information modeling (BIM) and Internet of Things (IoT) have the potential to improve the efficiency of facility maintenance management (FMM). Despite the significant efforts that have been made to apply BIM and IoT to the architecture, engineering, construction, and facility management (AEC/FM) industry, BIM and IoT integration for FMM is still at an initial stage. In order to provide a better maintenance strategy for building facilities, a data-driven predictive maintenance planning framework based on BIM and IoT technologies for FMM was developed, consisting of an information layer and an application layer. Data collection and data integration among the BIM models, FM system, and IoT network are undertaken in the information layer, while the application layer contains four modules to achieve predictive maintenance, namely: (1) condition monitoring and fault alarming module, (2) condition assessment module, (3) condition prediction module, and (4) maintenance planning module. Machine learning algorithms, ANN and SVM, are used to predict the future condition of MEP components. Furthermore, the developed framework was applied in an illustrative example to validate the feasibility of the approach. The results show that the constantly updated data obtained from the information layer together with the machine learning algorithms in the application layer can efficiently predict the future condition of MEP components for maintenance planning. Link
HKUST Transfer learning enhanced AR spatial registration for facility maintenance management Journal 02/2020 Chen, K., Yang, J., Cheng, J.C.P., Chen, W., and Li, C.T. 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. Link
HKUST Developing efficient mechanisms for BIM-to-AR/VR data transfer Journal 06/2020 Chen, K., Chen, W., Wang, Q., and Cheng, J.C.P. Augmented reality/virtual reality (AR/VR) has been increasingly adopted to enhance visualization of building information modeling (BIM) models. However, there is a lack of mechanisms for efficient data transfer from BIM to AR/VR. On one hand, most semantic information is lost while importing BIM models into AR/VR engines. On the other hand, huge and complicated BIM models can increase the time for model transfer, increase the computation work load while rendering, and reduce the fluency when using AR/VR applications. Therefore, this paper aims to develop efficient mechanisms for BIM-to-AR/VR data transfer to better utilize the information of BIM. In this paper, an ontology-based approach is proposed to transfer semantic information of BIM. Building components in geometric models are classified according to their features and simplified with different polygon reduction methods. As shown in the experimental validation, the proposed mechanisms have the capability to efficiently transfer semantic information of BIM to AR/VR, greatly reduce the number of triangles for geometric models while maximizing the consistency of the overall shape, and improve the framerate in corresponding AR/VR applications. N.A.
HKUST Analysis of Urban Walkability Using BIM and 3D GIS Models FYP 06/2020 LAI, Chi Ching
POON, Kwok Ho
Walkability, which is defined as the friendliness of a city or district towards walking, has been evaluated in the current Urban Design Report released by the Planning Department. The ultimate target of urban planning is not only being walkable but also provides comfortable walkways for pedestrians to travel through the city. Surveying and walking audit are the two common methods to measure the walkability of a district. However, the two methods are subjected to personal views and labor-intensive in data collection. This study tries to integrate Building Information Modeling (BIM), medial axis transform (MAT) network, and pedestrian flow simulation to analyze the walkability of Kwun Tong District. This approach digitizes the study region with rich geometric and semantic information for comprehensive analysis, which could present high similarity to the real environment. The BIM model of this study is a 3D model of the Kwun Tong District binding with information of the walking facilities such as the opening hours and slope of the walkway. The 3D pedestrian network, which indicates the walkable paths in the 3D model with walkway information, is built on the BIM model in order to calculate the time cost using a self-defined utility function. Pathfinder is used for pedestrian flow simulation to capture videos of pedestrians walking in the specific route in the BIM model, which gives realistic and clear illustrations in the walking environment. This study covers the area along Ngau Tau Kok Station to Kwun Tong Station, including residential area and commercial area, which is able to simulate various pedestrian walking behaviors in different districts. Three phases of simulations are carried out in the study region in this project, trying to demonstrate the working principle of the study method by analyzing the walkability of a specific region, sorting out the problems, and trying to improve the walkability with alteration in the BIM model. The ultimate target of the study is to provide a platform for walkability analysis so that the effectiveness of the urban planning policies can be simulated before adoption. N.A.
HKUST Creating a Connected Digital Twin of HKUST Campus for Smart Campus Facility Management FYP 06/2020 FONG, Tsz Yan
KONG, Yu Hin
Experts in engineering defines BIM as a representation of a digital twin which is a virtual replica of a physical system (Marr 2017). A digital twin provides rich semantic and geometric information for facilitating construction and FM processes. Through Facility Management Systems (FMSs) and Building Management Systems (BMSs) linked with sensors, information can be garnered to support building FM. FMS or BMS is a computer-based system installed in offices or buildings ensuring that all buildings are structurally sound and serviceable.

In this research, we initially plan to incorporate two common FM software, namely ArchiBUS and Maximo with the HKUST FM system for the sake of maximizing the FM effectiveness and facilitating FM process. However, we did not get either one of the licenses of both software, so it turns out that we have to use other machine learning set of tools to do predictions for our library. The specific goals were (1) to build a machine learning model to perform temperature forecasting; (2) to make suggestion on the operative temperature of AC in library to ensure thermal comfort; (3) to provide common campus FM capabilities by setting up and demonstrating tailor-made user interfaces by using Power BI.