A knowledge-guided two-stage Transformer framework achieves 92.61% average accuracy in cross-domain bearing fault diagnosis using only 10% labeled target data on four real-world datasets, outperforming prior methods by 17.24 points.
An ensemble deep learning network based on 2D convolutional neural network and 1D LSTM with self-attention for bearing fault diagnosis,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An LLM-based Two-Stage Transformer Framework for Cross-Domain Bearing Fault Diagnosis with Limited Data
A knowledge-guided two-stage Transformer framework achieves 92.61% average accuracy in cross-domain bearing fault diagnosis using only 10% labeled target data on four real-world datasets, outperforming prior methods by 17.24 points.