EUVIMEDEUVIMED entdecken
Open Access · CC BY-SA 4.0

Automasi Deteksi Konflik Struktur Arsitektural Menggunakan Algoritma Kecerdasan Buatan Berbasis Cloud

Evanard Putranata, Mirelle Adisty

Jurnal Rekayasa Sipil dan Arsitektur · 2026

DOI: 10.51903/zx5gw766 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Jurnal Rekayasa Sipil dan Arsitektur, 2026. Verfasst von Evanard Putranata und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The increasing complexity of modern construction projects has intensified coordination challenges among architectural, structural, and Mechanical-Electrical-Plumbing (MEP) disciplines. Conventional Building Information Modeling (BIM)-based clash detection methods are capable of identifying spatial conflicts but often generate high false-positive rates and require time-consuming manual verification. This study aims to develop an automated conflict detection framework by integrating Graph Neural Networks (GNN) and cloud computing within an OpenBIM Industry Foundation Classes (IFC) environment. A quantitative experimental approach was employed using a coordinated BIM model containing 44,800 three-dimensional objects from architectural, structural, and MEP disciplines. Spatial relationships among building elements were represented as graphs and analyzed using a GNN-PointNet++ architecture deployed on a cloud-based GPU environment. The results demonstrate that the proposed system successfully classified hard clash, soft clash, 4D time clash, and regulatory clash conflicts, achieving a precision of 98.67%, recall of 99.15%, and F1-Score of 98.91%. Furthermore, the framework reduced total design coordination time from 11.50 hours to 0.35 hours, corresponding to a computational efficiency of 96.95%, while maintaining 100% IFC interoperability and a false alarm rate of 1.32%. The novelty of this research lies in the integration of GNN-based spatial graph learning and cloud computing for automatic multi-type conflict classification in OpenBIM IFC models. The proposed framework improves both the accuracy and efficiency of BIM-based design coordination for digital construction environments.

Zitieren

APA

Putranata, E., & Adisty, M. (2026). Automasi Deteksi Konflik Struktur Arsitektural Menggunakan Algoritma Kecerdasan Buatan Berbasis Cloud. Jurnal Rekayasa Sipil dan Arsitektur. https://doi.org/10.51903/zx5gw766

Vancouver

Putranata E, Adisty M. Automasi Deteksi Konflik Struktur Arsitektural Menggunakan Algoritma Kecerdasan Buatan Berbasis Cloud. Jurnal Rekayasa Sipil dan Arsitektur. 2026. doi:10.51903/zx5gw766

BibTeX
@article{Putranata2026,
  author = {Putranata, Evanard and Adisty, Mirelle},
  title = {Automasi Deteksi Konflik Struktur Arsitektural Menggunakan Algoritma Kecerdasan Buatan Berbasis Cloud},
  journal = {Jurnal Rekayasa Sipil dan Arsitektur},
  year = {2026},
  doi = {10.51903/zx5gw766}
}
Kostenlos starten →