Full Text Available
Note: Clicking the button above will open the full text document at the original institutional repository in a new window.
An LLM Approach for Automating the Analysis of BIM (IFC) Data
This thesis introduces a novel methodology for automating the analysis of Building Information Modeling (BIM) data using LangGraph, an advanced extension of the LangChain framework, and integrating Google’s Gemini Large Language Model (LLM) with IfcOpenShell. BIM, and specifically Industry Foundatio...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Published: |
AUC Knowledge Fountain
2025
|
| Subjects: | |
| Tags: |
No Tags, Be the first to tag this record!
|
| Summary: | This thesis introduces a novel methodology for automating the analysis of Building Information Modeling (BIM) data using LangGraph, an advanced extension of the LangChain framework, and integrating Google’s Gemini Large Language Model (LLM) with IfcOpenShell. BIM, and specifically Industry Foundation Class (IFC) files, are widely used in the construction industry for representing and managing building data. However, analyzing this data effectively remains a significant challenge due to its volume and complexity. Additionally, analyzing BIM data typically requires knowledge of different BIM software depending on the application. This research addresses this challenge by creating a workflow that utilizes LangGraph’s ability to develop different AI agents designed to handle tasks like extracting element data, analyzing spatial relationships, and categorizing risks based on predefined criteria, without the need for any BIM software at all. The integration of Gemini LLM provides advanced language-based reasoning and decision-making capabilities that allow the system to process complex queries, in human language, and provide valuable insights from the BIM data. As a proof-of-concept, four applications of the LangGraph methodology were created, providing significant insights regarding the strengths and limitations of this framework. The models were validated through hypothetical case studies and real-world applications, and responses were evaluated based on their accuracy, validity, and completeness, demonstrating the framework’s effectiveness in analyzing BIM data in construction projects. However, the results also revealed limitations that can affect the system’s performance in large-scale real-world applications. These findings suggest that while the proposed system shows great potential, further optimization is needed to enhance its usability and reliability in more complex and large-scale scenarios. |
|---|