A global and joint knowledge distillation method with gradient-modulated dynamic parameter adaption for EMU bogie bearing fault diagnosis
Authors:
- Tongyang PanTongyang Pan
- Tiantian WangTWTiantian Wang
- Jinglong ChenJCJinglong Chen
- Jingsong XieJXJingsong Xie
- Sha CaoSCSha Cao
- 18 May 2024
- journal article
- research article
- Published by Elsevier in Measurement
- Vol. 235
Abstract
No abstract availableKeywords
Funding Information
- Natural Science Foundation of Hunan Province (2024JJ6500)
- National Natural Science Foundation of China (52275129)
This publication has 30 references indexed in Scilit:
- LiConvFormer: A lightweight fault diagnosis framework using separable multiscale convolution and broadcast self-attentionExpert Systems with Applications, 2023
- Multiple hierarchical compression for deep neural network toward intelligent bearing fault diagnosisEngineering Applications of Artificial Intelligence, 2022
- Generative adversarial network in mechanical fault diagnosis under small sample: A systematic review on applications and future perspectivesISA Transactions, 2022
- Knowledge distillation for BERT unsupervised domain adaptationKnowledge and Information Systems, 2022
- Deep multiple auto-encoder with attention mechanism network: A dynamic domain adaptation method for rotary machine fault diagnosis under different working conditionsKnowledge-Based Systems, 2022
- Reliability and availability assessment of railway locomotive bogies under correlated failuresEngineering Failure Analysis, 2022
- Few-shot fault diagnosis of rotating machinery with two-branch prototypical networksJournal of Intelligent Manufacturing, 2022
- Multiple degradation mode analysis via gated recurrent unit mode recognizer and life predictors for complex equipmentComputers in Industry, 2020
- A lightweight neural network with strong robustness for bearing fault diagnosisMeasurement, 2020
- Unsupervised rotating machinery fault diagnosis method based on integrated SAE–DBN and a binary processorJournal of Intelligent Manufacturing, 2020