Measuring Domain Shift in Vibration Signals to Improve Cross-Domain Diagnosis of Piston Aero Engine Faults
Open Access
Abstract
Transfer learning is an effective approach to address the decline in generalizability of intelligent fault diagnosis methods. However, there has been a persistent lack of comprehensive and effective metrics for assessing the transferability of cross-domain data, making it challenging to answer the fundamental question in transfer learning: “When to transfer”. This study proposes a novel hybrid transferability metric (HTM) based on weighted correlation-diversity shift. The metric introduces a correlation shift measurement based on sparse principal component analysis, effectively quantifying distribution differences in domain-invariant features based on the sparse representation theory. It also designs a diversity shift measurement based on label space differences, addressing the previously overlooked impact of label variation on transferability. The proposed transferability metric is validated on four types of cross-domain diagnosis tasks involving piston aero engines. The results show that in diagnostic scenarios involving both supervised transfer learning and extreme class imbalance problems, HTM accurately predicted the transferability of the target tasks, which aligned with the actual diagnostic accuracy trends. It provides a feasible method for predicting and evaluating the applicability of transfer learning methods in real-world scenarios.Keywords
Funding Information
- Chinese National Natural Science Fund (12227801, U23A6017, QN2022159)
- Science and Technology Research Project of Higher Education in Hebei Province of China (12227801, U23A6017, QN2022159)
This publication has 35 references indexed in Scilit:
- Generalized Out-of-Distribution Detection: A SurveyInternational Journal of Computer Vision, 2024
- Multi-label feature selection based on fuzzy rough sets with metric learning and label enhancementInternational Journal of Approximate Reasoning, 2024
- Maximum mean square discrepancy: A new discrepancy representation metric for mechanical fault transfer diagnosisKnowledge-Based Systems, 2023
- A communication-efficient and privacy-aware distributed algorithm for sparse PCAComputational Optimization and Applications, 2023
- How Stable Are Transferability Metrics Evaluations?2022
- A systematic review of rolling bearing fault diagnoses based on deep learning and transfer learning: Taxonomy, overview, application, open challenges, weaknesses and recommendationsAin Shams Engineering Journal, 2022
- An adversarial transferability metric based on SVD of Jacobians to disentangle the correlation with robustnessApplied Intelligence, 2022
- A Guide for Sparse PCA: Model Comparison and ApplicationsPsychometrika, 2021
- Transfer learning with stacked reconstruction independent component analysisKnowledge-Based Systems, 2018
- A fractional-order model-based battery external short circuit fault diagnosis approach for all-climate electric vehicles applicationJournal of Cleaner Production, 2018