Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
June 20, 2026Structural Health Monitoring

Transfer learning fault diagnosis of axial piston pumps by fusing knowledge from multisource subdomains and simulation-driven soft labels

View Full Paper
Ask AI
Bookmark
Share

Authors

QCQun ChaoZWZhongrui WangWWW Wang

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved diagnostic accuracy in axial piston pumps, suggesting enhanced reliability through new methods.

Key Points

  • This research aims to enhance fault diagnosis accuracy of axial piston pumps by addressing domain discrepancies in data.
  • Developed a novel transfer learning framework that integrates multisource subdomains and simulation-driven soft labels.
  • Each source subdomain employs an independent domain-specific classifier, weighted by data distribution discrepancies.
  • Utilized computational fluid dynamics to simulate discharge pressure signals for target operating conditions.
  • The proposed model increases diagnostic accuracy by 28.03% over conventional single-source methods.
  • Integration of simulation-driven soft labels yields an additional 13.59% accuracy gain.
  • Achieved superior average accuracy of 99.02% in diagnosis.

Cite This Study

Chao et al. (2026) studied this question.

synapsesocial.com/papers/6a3632a0db0793dc1a539211https://doi.org/10.1177/14759217261459311
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Fault severity recognition in axial piston pumps using attention-based adversarial discriminative domain adaptation neural network2024 · 13 citations
  2. 2Ensemble weighted DJPMMD based deep transfer metric learning method for fault diagnosis of bearing under variable working conditions2025 · 1 citations
  3. 3Domain Adaptation From Multiple Sources: A Domain-Dependent Regularization Approach2012 · 351 citations
  4. 4A Survey on Transfer Learning2009 · 23,890 citations
  5. 5A Multi-Source Weighted Deep Transfer Network for Open-Set Fault Diagnosis of Rotary Machinery2022 · 206 citations