| Author: | Chan, Lap Pong |
| Title: | Application of artificial intelligence technology in the Hong Kong construction industry : current status, benefits, challenges, and future prospects |
| Advisors: | Chan, W. M. Daniel (BRE) |
| Degree: | DIREC |
| Year: | 2025 |
| Department: | Department of Building and Real Estate |
| Pages: | xvii, 200 pages : color illustrations |
| Language: | English |
| Abstract: | The construction industry in Hong Kong is currently undergoing a significant digital transformation, referred to as ‘Construction 2.0’, driven by the integration of advanced technologies such as building information modelling, electronic contract awards, and extensive digitalisation of construction processes. Central to this evolution is the role of artificial intelligence (AI) technology, which enhances and expands the capabilities of existing digital tools, potentially revolutionising the prevailing industry practices across various levels and impacting various stakeholders profoundly. This thesis investigates the pivotal concepts and primary applications of AI technology within the construction industry, focusing on how AI tools can transform different construction activities ranging from project management to facilities maintenance. It explores the use of diverse AI technologies like machine learning techniques, natural language processing, computer vision, and robotics, and their applications in critical key areas such as project design, site planning, risk assessment, and on-site safety and facilities maintenance. The research aimed to provide a comprehensive road map for the future digital transformation of the construction industry in Hong Kong, underlining that intelligent systems are not merely theoretical but are rapidly becoming a practical reality with significant implications for the industry's evolution. This study first examined how AI technology can be effectively integrated into various construction processes and then assessed the associated benefits and challenges of AI technology adoption among professionals at different working levels from site management to on-site workers. This study employed a comprehensive approach to gathering information and data on AI applications in the Hong Kong construction industry, utilising a systematic literature review, in-depth interviews, and an industry-wide questionnaire survey. The literature review involved analysing the published research papers and global industry reports related to AI applications in construction, providing a fundamental understanding of current trends, benefits, and challenges. Self-administered survey forms were distributed to managers, engineers, and workforce experts to gather quantitative opinion-based data on AI technology implementation based on their hands-on site management experience. These questionnaires captured a range of perspectives on current practices and attitudes including the perceived benefits and challenges within the construction industry. In-depth expert interviews with senior industry professionals from mainland China, Hong Kong, the UK, and the USA provided qualitative insights into AI’s current and potential uses in construction, enriching the study with expert opinions. For data analysis, smart partial least squares structural equation modelling (PLS-SEM) and SPSS for confirmatory factor analysis (CB-SEM) were applied to ensure robust data diagnostics. Besides these methods, mean scores for statistical analysis were also adopted to further interpret and compare the data collected. This multifaceted approach ensured a comprehensive understanding of AI’s role in the construction industry, supported by rigorous data analysis techniques. The objectives of this research study were as follows: 1. To evaluate the applicability of AI technology across different construction processes in Hong Kong, such as project planning, site management, risk assessment, workplace safety, and facilities maintenance. 2. To analyse how foundational AI technologies, including machine learning, natural language processing, computer vision, and robotics, are suited to the development needs of the Hong Kong construction sector. 3. To explore the perceived benefits and potential challenges of implementing AI technology in the construction sector, mainly focusing on enhancing knowledge understanding and practical adoption among construction professionals of varying ages and job levels. 4. To recommend some effective pragmatic strategies or measures for promoting a wider use of AI technology in the construction industry of Hong Kong and overseas. By addressing these research questions, the thesis seeks to provide a deep understanding of AI’s potential role in the Hong Kong construction industry and offer practical recommendations for educating construction professionals about AI’s perceived benefits and challenges. This endeavour aims to support the industry’s ongoing digital transition and promote broader acceptance and implementation of AI technologies. Objective #1 was achieved through a comprehensive literature review, expert interviews, and an industry-wide questionnaire survey with a series of Likert-type questions geared towards the different stakeholders working in the construction and related fields, by investigating how AI technology can be applied in the construction industry. The survey questions were compiled, elaborated, and supported by different types of literature reviews. Most of the respondents applied AI technology in project management, risk assessment, safety enhancements, and facilities maintenance and operation. Objective #2 was consolidated into different AI technology literature reviews and expert interviews. It aimed to determine how foundational AI technologies, including machine learning, natural language processing, computer vision, and robotics, are suited to the development needs of the Hong Kong construction sector. Through the AI literature review summary, the growing trend of the perceived benefits and challenges of applying AI technology in construction can be identified and analysed. Most of the respondents were using computer vision, image recognition via convolutional neural networks, Gaussian splatting, and segment. Objective #3 was achieved through a comprehensive literature review, expert interviews, and an industry-wide questionnaire survey with a series of Likert-type questions geared towards the different stakeholders working in the construction and related fields, by exploring the perceived benefits and potential challenges of implementing AI technology in the construction sector, particularly focusing on the enhancement of knowledge understanding and practical adoption among construction professionals of varying ages and job levels. The survey results were collated and analysed using mean scores, a statistical program (SPSS for Windows), and the PLS-SEM technique. Additionally, a site case study using Openspace.ai was adopted to cross-check and validate the results of the survey with a real-life site case project. Most respondents identified key advantages such as improved site safety and reliability, as well as reduced construction costs. However, a significant disadvantage noted was full reliance on technology and potential AI bugs or malfunctions. Objective #4 was achieved by analysing and consolidating the literature interview findings and expert interview opinion data and hence offering some recommendations for improvement. This objective will assist construction project stakeholders to apply the academic knowledge learnt from this thesis and broaden their hands-on experience in the implementation of various AI technologies in the construction field both locally and internationally. The recommendations mainly included effective strategies or measures for overcoming the identified challenges and emphasising the perceived benefits of the adoption of diverse AI technologies in the construction industry. The integration of algorithms and digitalisation optimises processes, while enhanced computational capabilities significantly improve efficiency and outcomes. Finally, AI technology adoption in construction would increase the operational efficiency of construction sites in various respects. Moreover, construction project stakeholders prefer using hybrid AI tools to perform tedious data analysis for facilitating faster and more accurate human-made decisions. |
| Rights: | All rights reserved |
| Access: | restricted access |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| 8428.pdf | For All Users (off-campus access for PolyU Staff & Students only) | 4.27 MB | Adobe PDF | View/Open |
Copyright Undertaking
As a bona fide Library user, I declare that:
- I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
- I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
- I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.
Please use this identifier to cite or link to this item:
https://theses.lib.polyu.edu.hk/handle/200/13952