Logo image
Back
Graph-based unsupervised domain adaptation for fault diagnosis of HVAC systems Author links open overlay panel
Journal article   Open access   Peer reviewed

Graph-based unsupervised domain adaptation for fault diagnosis of HVAC systems Author links open overlay panel

Naghmeh Ghalamsiah, Jin Wen, Teresa Wu, Kasim Selcuk Candan and Zheng O’Neill
Building and environment, v 289, 114055
Feb 2026
DOI: https://doi.org/10.1016/j.buildenv.2025.114055
Featured in Collection :   Research Supported by Drexel Libraries' OA Programs
url
https://doi.org/10.1016/j.buildenv.2025.114055View
Published, Version of Record (VoR)Open Access via Drexel Libraries Read and Publish Program 2025CC BY-NC-ND V4.0,  Restricted

Abstract

Unsupervised domain adaptation HVAC fault diagnosis Graph convolutional network Transfer learning Temporal causal discovery framework
While data-driven methods have shown strong potential for fault diagnosis in heating, ventilation, and air conditioning (HVAC) systems, their effectiveness is often limited by the scarcity of well-labeled data in real buildings. Unsupervised domain adaptation (UDA) mitigates this challenge by transferring knowledge from labeled source domains to diagnose faults in unlabeled target domains. Most existing UDA approaches for HVAC fault diagnosis employ convolutional neural networks (CNNs), which overlook the underlying system topology. Graph neural networks (GNNs) offer a powerful alternative for capturing complex interactions among system components. However, their potential for UDA remains unexplored due to the absence of predefined graph structures for HVAC systems. To address this gap, this study proposes a GNN-based UDA framework that transforms HVAC tabular data into fault-specific causal graph representations. The proposed method achieves over 74.5% accuracy across multiple scenarios, demonstrating its effectiveness and superior performance compared to benchmark models.

Metrics

22 Record Views

Details

UN Sustainable Development Goals (SDGs)

This publication has contributed to the advancement of the following goals:

#13 Climate Action
#11 Sustainable Cities and Communities
#7 Affordable and Clean Energy

InCites Highlights

Data related to this publication, from InCites Benchmarking & Analytics tool:

Collaboration types
Domestic collaboration
Web of Science research areas
Construction & Building Technology
Engineering, Civil
Engineering, Environmental
Logo image