Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

AHMsys: An Automated HVAC Modeling System for BIM Project

Long Hoang Dang, Duy-Hung Nguyen, Thai Quang Le, Thinh Truong Nguyen, Clark Mei, Vu Hoang

TL;DR

AHMsys tackles the labor-intensive HVAC modeling phase in BIM by converting 2D CAD drawings into accurate 3D HVAC models using a lightweight, data-efficient pipeline. It relies on 2D drawing preprocessing, contour-based object detection with minimal labeled data, and a parametric 3D generation stage driven by automation scripts. On Akila's BIM dataset, it achieves near-perfect type accuracy (≈98–99%) for ducts and related components and delivers about a 20% reduction in BIM project work hours, demonstrating practical productivity gains for mid-sized firms. The approach reduces reliance on large annotated datasets and heavyweight DL models, making automated HVAC modeling more accessible in industry.

Abstract

This paper presents a novel system, named AHMsys, designed to automate the process of generating 3D Heating, Ventilation, and Air Conditioning (HVAC) models from 2D Computer-Aided Design (CAD) drawings, a key component of Building Information Modeling (BIM). By automatically preprocessing and extracting essential HVAC object information then creating detailed 3D models, our proposed AHMsys significantly reduced the 20 percent work schedule of the BIM process in Akila. This advancement highlights the essential impact of integrating AI technologies in managing the lifecycle of a digital representation of the building.

AHMsys: An Automated HVAC Modeling System for BIM Project

TL;DR

AHMsys tackles the labor-intensive HVAC modeling phase in BIM by converting 2D CAD drawings into accurate 3D HVAC models using a lightweight, data-efficient pipeline. It relies on 2D drawing preprocessing, contour-based object detection with minimal labeled data, and a parametric 3D generation stage driven by automation scripts. On Akila's BIM dataset, it achieves near-perfect type accuracy (≈98–99%) for ducts and related components and delivers about a 20% reduction in BIM project work hours, demonstrating practical productivity gains for mid-sized firms. The approach reduces reliance on large annotated datasets and heavyweight DL models, making automated HVAC modeling more accessible in industry.

Abstract

This paper presents a novel system, named AHMsys, designed to automate the process of generating 3D Heating, Ventilation, and Air Conditioning (HVAC) models from 2D Computer-Aided Design (CAD) drawings, a key component of Building Information Modeling (BIM). By automatically preprocessing and extracting essential HVAC object information then creating detailed 3D models, our proposed AHMsys significantly reduced the 20 percent work schedule of the BIM process in Akila. This advancement highlights the essential impact of integrating AI technologies in managing the lifecycle of a digital representation of the building.
Paper Structure (8 sections, 3 figures, 3 tables)

This paper contains 8 sections, 3 figures, 3 tables.

Table of Contents

  1. System Framework
  2. 2D Drawing Preprocessing
  3. 2D HVAC Drawing Extraction
  4. HVAC Object Detection
  5. HVAC Object Dimension Estimation
  6. 3D Model Generation
  7. Results
  8. Conclusion

Figures (3)

  • Figure 1: The 3D HVAC model generated by our proposed AHMsys based on the 2D CAD drawing.
  • Figure 2: Our proposed AHMsys contains three key steps: 1) 2D Drawing Preprocessing, 2) 2D HVAC Drawing Extraction, and 3) 3D Model Generation. Given a 2D CAD drawing and a list of potential object types within the drawing as inputs, this framework will create integrated 3D HVAC model as output.
  • Figure 3: The workload for the BIM project at Akila Company in 2022 was mainly focused on HVAC modeling, which accounted for 65% of the total. The remainder was distributed among other disciplines, including architecture and structure design.