{"title":"Unsupervised domain adaptation for HVAC fault diagnosis using contrastive adaptation network","authors":"Naghmeh Ghalamsiah , Jin Wen , K.Selcuk Candan , Teresa Wu , Zheng O’Neill , Asra Aghaei","doi":"10.1016/j.enbuild.2025.115659","DOIUrl":null,"url":null,"abstract":"<div><div>Data-driven methods have shown great promise for heating, ventilation, and air conditioning (HVAC) systems’ fault diagnosis, but their reliance on well-labeled datasets poses challenges in real-world applications where such data may not be readily available. Meanwhile, well-labeled data might exist from virtual testbeds or laboratory systems. Domain adaptation could provide a solution to utilize labeled data from a source domain (such as a virtual or laboratory testbed) to diagnose faults in an unlabeled target domain, such as faults in a real building system. This paper utilizes the contrastive adaptation network (CAN) algorithm, originally successful in image classification, to overcome the specific challenges faced by current domain adaptation algorithms in HVAC systems. Furthermore, temporal causal discovery framework (TCDF), a causality-based framework for discovering causal relationships in time series data, is implemented in the data processing step to meet the requirements of convolutional networks, where spatially closer features are more likely to be correlated. The results on air handling unit (AHU) datasets demonstrate that the CAN algorithm effectively facilitates domain adaptation in the absence of target labels and that the feature reordering process reduces the training time and the number of loops required for convergence.</div></div>","PeriodicalId":11641,"journal":{"name":"Energy and Buildings","volume":"337 ","pages":"Article 115659"},"PeriodicalIF":6.6000,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Energy and Buildings","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0378778825003895","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CONSTRUCTION & BUILDING TECHNOLOGY","Score":null,"Total":0}
引用次数: 0
Abstract
Data-driven methods have shown great promise for heating, ventilation, and air conditioning (HVAC) systems’ fault diagnosis, but their reliance on well-labeled datasets poses challenges in real-world applications where such data may not be readily available. Meanwhile, well-labeled data might exist from virtual testbeds or laboratory systems. Domain adaptation could provide a solution to utilize labeled data from a source domain (such as a virtual or laboratory testbed) to diagnose faults in an unlabeled target domain, such as faults in a real building system. This paper utilizes the contrastive adaptation network (CAN) algorithm, originally successful in image classification, to overcome the specific challenges faced by current domain adaptation algorithms in HVAC systems. Furthermore, temporal causal discovery framework (TCDF), a causality-based framework for discovering causal relationships in time series data, is implemented in the data processing step to meet the requirements of convolutional networks, where spatially closer features are more likely to be correlated. The results on air handling unit (AHU) datasets demonstrate that the CAN algorithm effectively facilitates domain adaptation in the absence of target labels and that the feature reordering process reduces the training time and the number of loops required for convergence.
期刊介绍:
An international journal devoted to investigations of energy use and efficiency in buildings
Energy and Buildings is an international journal publishing articles with explicit links to energy use in buildings. The aim is to present new research results, and new proven practice aimed at reducing the energy needs of a building and improving indoor environment quality.