Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis

Intelligent fault diagnosis for rotary machinery often suffers performance degradation under domain shifts between training and deployment environments. To address this, we propose a robust fault diagnosis framework incorporating three key components: (1) an order-frequency-based preprocessing metho...

Full description

Saved in:
Bibliographic Details
Main Authors: Hoejun Jeong, Seungha Kim, Donghyun Seo, Jangwoo Kwon
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/14/4383
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849251810419671040
author Hoejun Jeong
Seungha Kim
Donghyun Seo
Jangwoo Kwon
author_facet Hoejun Jeong
Seungha Kim
Donghyun Seo
Jangwoo Kwon
author_sort Hoejun Jeong
collection DOAJ
description Intelligent fault diagnosis for rotary machinery often suffers performance degradation under domain shifts between training and deployment environments. To address this, we propose a robust fault diagnosis framework incorporating three key components: (1) an order-frequency-based preprocessing method to normalize rotational variations, (2) a U-Net variational autoencoder (U-NetVAE) to enhance adaptation through reconstruction learning, and (3) a test-time training (TTT) strategy enabling unsupervised target domain adaptation without access to source data. Since existing works rarely evaluate under true domain shift conditions, we first construct a unified cross-domain benchmark by integrating four public datasets with consistent class and sensor settings. The experimental results show that our method outperforms conventional machine learning and deep learning models in both F1-score and recall across domains. Notably, our approach maintains an F1-score of 0.47 and recall of 0.51 in the target domain, outperforming others under identical conditions. Ablation studies further confirm the contribution of each component to adaptation performance. This study highlights the effectiveness of combining mechanical priors, self-supervised learning, and lightweight adaptation strategies for robust fault diagnosis in the practical domain.
format Article
id doaj-art-d6be204d0dc247b995fd1ceb021b1677
institution Kabale University
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-d6be204d0dc247b995fd1ceb021b16772025-08-20T03:56:49ZengMDPI AGSensors1424-82202025-07-012514438310.3390/s25144383Source-Free Domain Adaptation Framework for Rotary Machine Fault DiagnosisHoejun Jeong0Seungha Kim1Donghyun Seo2Jangwoo Kwon3Department of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of KoreaDepartment of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of KoreaDepartment of Electrical and Computer Engineering, Inha University, Incheon 22212, Republic of KoreaDepartment of Computer Engineering, Inha University, Incheon 22212, Republic of KoreaIntelligent fault diagnosis for rotary machinery often suffers performance degradation under domain shifts between training and deployment environments. To address this, we propose a robust fault diagnosis framework incorporating three key components: (1) an order-frequency-based preprocessing method to normalize rotational variations, (2) a U-Net variational autoencoder (U-NetVAE) to enhance adaptation through reconstruction learning, and (3) a test-time training (TTT) strategy enabling unsupervised target domain adaptation without access to source data. Since existing works rarely evaluate under true domain shift conditions, we first construct a unified cross-domain benchmark by integrating four public datasets with consistent class and sensor settings. The experimental results show that our method outperforms conventional machine learning and deep learning models in both F1-score and recall across domains. Notably, our approach maintains an F1-score of 0.47 and recall of 0.51 in the target domain, outperforming others under identical conditions. Ablation studies further confirm the contribution of each component to adaptation performance. This study highlights the effectiveness of combining mechanical priors, self-supervised learning, and lightweight adaptation strategies for robust fault diagnosis in the practical domain.https://www.mdpi.com/1424-8220/25/14/4383fault diagnosisdomain adaptationvariational autoencoder (VAE)self-supervised learningrotating machinerytest-time training (TTT)
spellingShingle Hoejun Jeong
Seungha Kim
Donghyun Seo
Jangwoo Kwon
Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis
Sensors
fault diagnosis
domain adaptation
variational autoencoder (VAE)
self-supervised learning
rotating machinery
test-time training (TTT)
title Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis
title_full Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis
title_fullStr Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis
title_full_unstemmed Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis
title_short Source-Free Domain Adaptation Framework for Rotary Machine Fault Diagnosis
title_sort source free domain adaptation framework for rotary machine fault diagnosis
topic fault diagnosis
domain adaptation
variational autoencoder (VAE)
self-supervised learning
rotating machinery
test-time training (TTT)
url https://www.mdpi.com/1424-8220/25/14/4383
work_keys_str_mv AT hoejunjeong sourcefreedomainadaptationframeworkforrotarymachinefaultdiagnosis
AT seunghakim sourcefreedomainadaptationframeworkforrotarymachinefaultdiagnosis
AT donghyunseo sourcefreedomainadaptationframeworkforrotarymachinefaultdiagnosis
AT jangwookwon sourcefreedomainadaptationframeworkforrotarymachinefaultdiagnosis