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...
Saved in:
| Main Authors: | , , , |
|---|---|
| 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 |