簡易檢索 / 詳目顯示

研究生: 陳仁幹
Lorenzo, Raffael
論文名稱: 應用生成式 AI 強化建築資訊模型法規檢核流程-以 HVAC 系統為例
Enhancing BIM Code Compliance Checking Process With Generative AI – A Case Study of HVAC System
指導教授: 馮重偉
Feng, Chung-Wei
學位類別: 碩士
Master
系所名稱: 工學院 - 土木工程學系
Department of Civil Engineering
論文出版年: 2025
畢業學年度: 113
語文別: 英文
論文頁數: 112
中文關鍵詞: BIM建築法規檢核生成式人工智慧大型語言模型
外文關鍵詞: BIM, Building Code Compliance, Generative AI, Large Language Model
相關次數: 點閱:21下載:2
分享至:
查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報
  • 機電(MEP)系統結構複雜,且經常與其他建築構件發生衝突,容易產生問題。這些衝突不僅影響施工效率,還可能導致不符合法規規定,進而直接影響建築性能與居住者安全。在目前的實務操作中,針對機械法規條文的解讀與合規檢查仍屬人工作業,需投入大量時間與專業知識。雖然已有研究探索大型語言模型(LLMs)在建築領域的應用,但針對如法規解讀與合規檢查等專業任務進行客製化開發的研究仍屬少數。本研究針對特定領域配置一套專用的大型語言模型,以提升建築法規檢核流程的效率與一致性。研究提出一種新方法,結合生成式人工智慧進行法規條文解釋,以及以 BIM 為基礎的自動化規則執行流程。此方法特別針對暖通空調(HVAC)系統中常見的空間衝突問題進行探討,因其管線複雜且尺寸龐大,最容易違反設計規範。選擇 HVAC 設計作為研究焦點,係因其合規性對於建築安全與運作功能至關重要。透過結合生成式 AI 與 BIM 工作流程,本研究旨在降低法規解讀所需的人工投入,並提供一套實用的方法,於設計階段即進行自動化合規檢查。

    Mechanical, Electrical, and Plumbing (MEP) systems are complex and prone to issues since they often face clashes with other building elements. These clashes not only affect construction efficiency but can also lead to non-compliance with building codes, which directly impacts building performance and occupant safety. In current practice, interpreting mechanical code clauses and performing compliance checks remain manual tasks, requiring significant time and expert effort. While the use of Large Language Models (LLMs) has been explored in various construction-related studies, few have focused on developing tailored or customized LLMs for domain-specific tasks such as regulation interpretation and compliance checking. In this research, a domain-specific LLM was configured to improve the efficiency and consistency of the building code compliance checking process. The study proposes a new approach that integrates generative AI for interpreting building clauses with BIM-based automation for rule execution. The study explores how generative AI can assist in interpreting building code clauses, particularly those related to HVAC systems, which are often involved in spatial conflicts due to their complex routing and size. HVAC design is chosen as the focus because code compliance in these systems is critical to ensuring safe and functional building operation. By combining generative AI with BIM workflows, this research aims to reduce the manual effort in regulatory interpretation and offer a practical method for automating compliance checks during the design phase.

    ABSTRACT (中文) i ABSTRACT ii TABLE OF CONTENTS iii LIST OF TABLES vi LIST OF FIGURES vii CHAPTER 1 INTRODUCTION 1 1.1 Background and Motivation 1 1.2 Research Objectives 2 1.3 Research Scope and Limitations 3 1.4 Research Procedure 3 1.5 Thesis Organization 5 CHAPTER 2 LITERATURE REVIEW 6 2.1 Problem Statement 6 2.2 Literature Review 8 2.2.1 Overview of Compliance Checking in Construction 8 2.2.2 BIM Applications in Building Compliance Checking 10 2.2.3 AI Applications in Building Compliance Checking 12 2.3 Summary 13 CHAPTER 3 RESEARCH METHODOLOGY 15 3.1 Tools and Software 17 3.1.1 Building Information Modeling Tool 17 3.1.2 Scripting Tool and Environment 18 3.1.3 Artificial Intelligence Tool 19 3.2 Building Code Interpretation 20 3.2.1 Building Code Selection 20 3.2.2 Clause Categorization 21 3.2.3 Manual Clause Interpretation 23 3.3 Prompt Engineering Strategy 25 3.3.1 Prompt Engineering Methods 25 3.3.2 Prompt Engineering Combinations 28 3.4 Custom GPT Configuration 39 3.4.1 Custom GPT Knowledge 40 3.4.2 Custom GPT Instructions 42 3.4.3 Structured Output Configuration 43 3.4.4 Custom GPT Configuration Validation 45 3.5 Translating Code Requirements into BIM Parameters 47 3.5.1 Building Code Parameters Identification 47 3.5.2 Map Building Code Parameter Into BIM Parameter 48 3.6 Compliance Check Script Generation 50 3.6.1 Compliance Check Script Environment 51 3.6.2 Compliance Check Script Generation 51 3.6.3 Compliance Check Script Execution 57 3.6.4 Compliance Check Script Generation Training 59 CHAPTER 4 CASE STUDY 69 4.1 Case Study 69 4.1.1 Building Code Interpretation 69 4.1.2 Compliance Check Script Generation 77 4.1.3 Compliance Check Study Case 80 4.2 Key Findings 91 4.2.1 Clause Interpretation and Parameter Mapping 91 4.2.2 Compliance Check Script Generation and Execution 92 4.2.3 Limitations 93 CHAPTER 5 CONCLUSIONS 95 5.1 Conclusions 95 5.2 Future Development 96 REFERENCES 98

    Akhmetzhanova, B., Nadeem, A., Hossain, A., & Kim, J. R. (2022). Clash Detection Using Building Information Modeling (BIM) Technology in the Republic of Kazakhstan. https://doi.org/10.3390/buildings
    Amor, R., & Dimyadi, J. (2021). The promise of automated compliance checking. Developments in the Built Environment, 5. https://doi.org/10.1016/j.dibe.2020.100039
    Bitaraf, I., Salimpour, A., Elmi, P., & Shirzadi Javid, A. A. (2024). Improved Building Information Modeling Based Method for Prioritizing Clash Detection in the Building Construction Design Phase. Buildings, 14(11). https://doi.org/10.3390/buildings14113611
    Chen, J., Wu, L.-I., Chen, M., Qian, X., Zhu, H., Zhang, Q., & Li, G. (2024). ARCEAK: An Automated Rule Checking Framework Enhanced with Architectural Knowledge. http://arxiv.org/abs/2501.14735
    Cheng, F. (2013). Using Building Codes and Standards to Improve the Construction Quality and Safety.
    Dimyadi J.; Amor R. (2013). Automated Building Code Compliance Checking - Where is it at?
    Dimyadi, J., Clifton, C., Spearpoint, M., & Amor, R. (2016). Computerizing Regulatory Knowledge for Building Engineering Design. Journal of Computing in Civil Engineering, 30(5). https://doi.org/10.1061/(asce)cp.1943-5487.0000572
    Eastman, C., Lee, J. min, Jeong, Y. suk, & Lee, J. kook. (2009). Automatic rule-based checking of building designs. In Automation in Construction (Vol. 18, Issue 8, pp. 1011–1033). https://doi.org/10.1016/j.autcon.2009.07.002
    Fuchs, S., Fauth, J., Boden, M., & Amor, R. (2025). THE CHALLENGE OF AUTOMATED COMPLIANCE CHECKING: A REGULATORY VIEW. https://bimpermit.digital/en/
    Fuchs, S., Witbrock, M., & Amor, R. (2024). Using Large Language Models for the Interpretation of Building Regulations. https://chat.openai.com/
    Greenwood, D., Lockley, S., Malsane, S., & Matthews, J. (2010). Automated compliance checking using building information models. http://www.buildingsmart.com/
    International Code Council. (2021). International Mechanical Code. International Code Council.
    Ismail, A. S., Ali, K. N., & Iahad, N. A. (2017). A Review on BIM-Based Automated Code Compliance Checking System. IEEE.
    Ismail, A. S., Ali, K. N., Iahad, N. A., Kassem, M. A., & Al-Ashwal, N. T. (2023). BIM-Based Automated Code Compliance Checking System in Malaysian Fire Safety Regulations: A User-Friendly Approach. Buildings, 13(6). https://doi.org/10.3390/buildings13061404
    Jiang, L., Shi, J., & Wang, C. (2022). Multi-ontology fusion and rule development to facilitate automated code compliance checking using BIM and rule-based reasoning. Advanced Engineering Informatics, 51. https://doi.org/10.1016/j.aei.2021.101449
    Kojima, T., Gu, S. S., Reid, M., Matsuo, Y., & Iwasawa, Y. (2023). Large Language Models are Zero-Shot Reasoners. http://arxiv.org/abs/2205.11916
    Lee, J. K., Cho, K., Choi, H., Choi, S., Kim, S., & Cha, S. H. (2023). High-level implementable methods for automated building code compliance checking. Developments in the Built Environment, 15. https://doi.org/10.1016/j.dibe.2023.100174
    Luo, H., & Gong, P. (2015). A BIM-based Code Compliance Checking Process of Deep Foundation Construction Plans. Journal of Intelligent and Robotic Systems: Theory and Applications, 79(3–4), 549–576. https://doi.org/10.1007/s10846-014-0120-z
    Madireddy, S., Gao, L., Din, Z. U., Kim, K., Senouci, A., Han, Z., & Zhang, Y. (2025). Large Language Model-Driven Code Compliance Checking in Building Information Modeling. Electronics (Switzerland), 14(11). https://doi.org/10.3390/electronics14112146
    Mehrbod, S., Staub-French, S., Mahyar, N., Fellow, P., & Tory, M. (2019). BEYOND THE CLASH: INVESTIGATING BIM-BASED BUILDING DESIGN COORDINATION ISSUE REPRESENTATION AND RESOLUTION. In Journal of Information Technology in Construction (ITcon) (Vol. 24). http://www.itcon.org/2019/3
    Moundas, M., White, J., & Schmidt, D. C. (2024). Prompt Patterns for Structured Data Extraction from Unstructured Text. In PLoP (Vol. 2024).
    Nguyen, T.-H., & Kim, J.-L. (2011). BUILDING CODE COMPLIANCE CHECKING USING BIM TECHNOLOGY. IEEE.
    Peng, J., & Liu, X. (2023). Automated code compliance checking research based on BIM and knowledge graph. Scientific Reports, 13(1). https://doi.org/10.1038/s41598-023-34342-1
    Preidel, C., & Borrmann, A. (2018). BIM-based code compliance checking. In Building Information Modeling: Technology Foundations and Industry Practice (pp. 367–381). Springer International Publishing. https://doi.org/10.1007/978-3-319-92862-3_22
    Shehadeh, A., Alshboul, O., Taamneh, M. M., Jaradat, A. Q., & Alomari, A. H. (2024). Enhanced clash detection in building information modeling: Leveraging modified extreme gradient boosting for predictive analytics. Results in Engineering, 24. https://doi.org/10.1016/j.rineng.2024.103439
    Solihin, W., & Eastman, C. (2015). Classification of rules for automated BIM rule checking development. Automation in Construction, 53, 69–82. https://doi.org/10.1016/j.autcon.2015.03.003
    Soliman-Junior, J., Tzortzopoulos, P., & Kagioglou, M. (2022). Designers’ perspective on the use of automation to support regulatory compliance in healthcare building projects. Construction Management and Economics, 40(2), 123–141. https://doi.org/10.1080/01446193.2021.2022176
    Teo, Y. H., Yap, J. H., An, H., Yu, S. C. M., Zhang, L., Chang, J., & Cheong, K. H. (2022). Enhancing the MEP Coordination Process with BIM Technology and Management Strategies. In Sensors (Vol. 22, Issue 13). MDPI. https://doi.org/10.3390/s22134936
    Vergara-Perucich, J. F. (2025). AI-Driven Deconstruction of Urban Regulatory Frameworks: Unveiling Social Sustainability Gaps in Santiago’s Communal Zoning. Urban Science, 9(6), 186. https://doi.org/10.3390/urbansci9060186
    Wan, H., Zhang, J., Chen, Y., Xu, W., & Feng, F. (2024). Generative AI Application for Building Industry.
    White, J., Fu, Q., Hays, S., Sandborn, M., Olea, C., Gilbert, H., Elnashar, A., Spencer-Smith, J., & Schmidt, D. C. (2023). A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT. http://arxiv.org/abs/2302.11382
    Wu, Q., Chen, L., Shi, P., Wang, W., & Xu, S. (2022). Identifying Impact Factors of MEP Installation Productivity: An Empirical Study. Buildings, 12(5). https://doi.org/10.3390/buildings12050565
    Xie, X., Zhou, J., Fu, X., Zhang, R., Zhu, H., & Bao, Q. (2022). Automated Rule Checking for MEP Systems Based on BIM and KBMS. Buildings, 12(7). https://doi.org/10.3390/buildings12070934
    Xue, X., & Zhang, J. (2022). Regulatory information transformation ruleset expansion to support automated building code compliance checking. Automation in Construction, 138. https://doi.org/10.1016/j.autcon.2022.104230
    Zhang, Z., Ma, L., & Broyd, T. (2022). TOWARDS FULLY-AUTOMATED CODE COMPLIANCE CHECKING OF BUILDING REGULATIONS: CHALLENGES FOR RULE INTERPRETATION AND REPRESENTATION.
    Zhao, Q., Wang, H., Wang, R., & Cao, H. (2025). Deriving insights from enhanced accuracy: Leveraging prompt engineering in custom GPT for assessing Chinese Nursing Licensing Exam. Nurse Education in Practice, 84. https://doi.org/10.1016/j.nepr.2025.104284
    Zheng, Z., Chen, K.-Y., Cao, X.-Y., Lu, X.-Z., & Lin, J.-R. (2023). LLM-FuncMapper: Function Identification for Interpreting Complex Clauses in Building Codes via LLM.

    下載圖示 校內:立即公開
    校外:立即公開
    QR CODE