Skip to content
Open access

SATT: Partial Transfer Machinery Fault Diagnosis Based on Subdomain Adaptation and Two-Stage Training

2026 · IEEE Access · Vol 14, pp. 141308-141321 · 0 citations · 36 references

TL;DR

In this non-adversarial method, subdomain adaptation is introduced to align the distribution of relevant subdomains in the source and target domains by minimizing the local maximum mean discrepancy between the two domains.

Abstract

In recent years, unsupervised transfer learning based on deep domain adaptation techniques has successfully solved the domain shift problem in machinery fault diagnosis, with a basic assumption that target and source domains share the same label space. However, the label space of the target domain is usually a subset of the source domain in real industrial scenarios, which is beyond the capability of the existing methods. This paper proposes a new partial transfer diagnosis method based on subdomain adaptation and two-stage training (SATT) to solve this problem. In this non-adversarial method, subdomain adaptation is introduced to align the distribution of relevant subdomains in the source and target domains by minimizing the local maximum mean discrepancy between the two domains. Subdomain adaptation can effectively reduce the negative impact of source outlier classes. Additionally, SATT integrates two networks and uses the entropy minimization principle to provide more accurate target pseudo labels. Finally, a two-stage training strategy is designed to remove most of the source outlier samples. Thus, the influence of source outlier classes is further reduced. Experimental results on two diagnosis datasets show that SATT achieves more satisfactory performance than six representative comparison methods.

Read PDF

Similar papers

Sep 2026

Source-free domain adaptation framework for rotating machinery fault diagnosis by Progressive Pseudo-Labeling and Prototype-Boundary Calibration

A novel source-free DA framework for rotating machinery fault diagnosis that gradually builds a reliable pseudo-label memory bank and dynamically updates it with historical information is proposed, and the Progressive Pseudo-Labeling strategy is introduced.

You Wu, Chuan-Min Wang, Yu Hu et al. · 0 citations
Conference Open access Sep 2026

Fault diagnosis method for unbalanced gearbox bearing under variable working conditions based on generation-enhanced domain adaptation

The proposed fault diagnosis method provides a data-driven diagnostic scheme for prognostics and health management of marine transmission equipment and supports intelligent ship operation and maintenance under limited fault data and variable operating conditions.

Hong-Cheng Huang, Bao-Zhu Jia, Zai-Mi Xie et al. · 0 citations
Open access Sep 2026

A novel source-free domain adaptation with high-confidence sample selection and feature disentanglement for machinery fault diagnosis

This paper proposes a novel SFDA with high-confidence sample selection and feature disentanglement for machinery fault diagnosis, which effectively alleviates the adverse influence of noisy pseudo-labels during the stage of adaptation.

Yi-Ming Yuan, Kang Wu, Xing-Xing Jiang et al. · 0 citations
Aug 2026

Dual-adaptive unknown faults separation network: An open-set domain adaptation method for industrial fault diagnosis

The proposed Dual-Adaptive Unknown Faults Separation Network (DAUFSN) approach integrates a shared feature extractor with two specialized networks: a closed-set adversarial unknown separation network and an open-set adversarial domain adaptation network.

Yi-Xing Xie, Ying Tian, Zhong Yin et al. · 0 citations
Oct 2026

DASAN-based cross-working-condition fault diagnosis for rolling bearings

To address the insufficient discriminability problems of fault features extracted from rolling bearing data under complex operating conditions and low fault diagnosis accuracies caused by the lack of labeled data in the target domain, this study proposes a cross-operating-condition fault diagnosis method based on the D...

Zheng Han, Yu-Qi Fan, Ya-Ping Wang et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.