Mechanical Systems and Signal Processing, Journal Year: 2025, Volume and Issue: 228, P. 112460 - 112460
Published: Feb. 14, 2025
Language: Английский
Mechanical Systems and Signal Processing, Journal Year: 2025, Volume and Issue: 228, P. 112460 - 112460
Published: Feb. 14, 2025
Language: Английский
Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: 252, P. 110449 - 110449
Published: Aug. 22, 2024
Language: Английский
Citations
22Reliability Engineering & System Safety, Journal Year: 2025, Volume and Issue: unknown, P. 110854 - 110854
Published: Jan. 1, 2025
Language: Английский
Citations
3Mechanical Systems and Signal Processing, Journal Year: 2024, Volume and Issue: 215, P. 111421 - 111421
Published: April 15, 2024
Language: Английский
Citations
18Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 60, P. 102400 - 102400
Published: Feb. 17, 2024
Language: Английский
Citations
17Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: 253, P. 110570 - 110570
Published: Oct. 6, 2024
Language: Английский
Citations
13Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 64, P. 103063 - 103063
Published: Dec. 19, 2024
Language: Английский
Citations
11Advanced Engineering Informatics, Journal Year: 2025, Volume and Issue: 65, P. 103140 - 103140
Published: Feb. 3, 2025
Language: Английский
Citations
2Computers in Industry, Journal Year: 2024, Volume and Issue: 164, P. 104169 - 104169
Published: Sept. 7, 2024
Language: Английский
Citations
8Structural Health Monitoring, Journal Year: 2024, Volume and Issue: 23(6), P. 3904 - 3920
Published: Feb. 28, 2024
Equipment operating conditions, referred to as domains, can induce domain drift in monitoring data, affecting data-driven fault diagnosis. Researchers have explored multi-domain generalization methods tackle this issue. However, actual industrial scenarios, the availability of data may be limited a specific condition due cost or feasibility constraints associated with collecting extensive data. This limitation hampers ability these methods, posing major challenge for robust diagnosis under variable conditions. To address challenge, we proposed gradient-based domain-augmented meta-learning (GDM) single-domain method. We analyze restrictions generating fake domains and construct loss by evaluating diagnostic tasks minimization, semantic consistency, distribution diversity samples. Using technique, are generated iteratively, providing diverse knowledge improved generalization. Instead using time-consuming ensemble develop novel method train highly efficient generalizable model, relaxing requirement auxiliary datasets existing methods. Two case studies consistently demonstrate effectiveness superiority GDM Our findings suggest that study offers promising competitive solution within real scenarios.
Language: Английский
Citations
7Reliability Engineering & System Safety, Journal Year: 2024, Volume and Issue: 250, P. 110252 - 110252
Published: June 8, 2024
Language: Английский
Citations
7