A front-door adjustment based cross-component few-shot learning fault diagnosis approach considering unobservable confounders
Authors:
- Juan XuJXJuan Xu
- Lele ChenLCLele Chen
- Jintao YingJYJintao Ying
- Xu DingXDXu Ding
- Xiaochuan LiXLXiaochuan Li
- Qile RenQRQile Ren
- 12 December 2025
- journal article
- Published by Elsevier in Engineering Applications of Artificial Intelligence
- Vol. 165
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (52375089)
- Ministry of Science and Technology of the People's Republic of China
- National Key Research and Development Program of China (2024YFB3311600)
This publication has 22 references indexed in Scilit:
- Research, application, and challenges of causal inference in industrial fault diagnosis: A surveyEngineering Applications of Artificial Intelligence, 2025
- Automated processing of eXplainable Artificial Intelligence outputs in deep learning models for fault diagnostics of large infrastructuresEngineering Applications of Artificial Intelligence, 2025
- Adversarial-Causal Representation Learning Networks for Machine fault diagnosis under unseen conditions based on vibration and acoustic signalsEngineering Applications of Artificial Intelligence, 2024
- Interpreting what typical fault signals look like via prototype-matchingAdvanced Engineering Informatics, 2024
- TFPred: Learning discriminative representations from unlabeled data for few-label rotating machinery fault diagnosisControl Engineering Practice, 2024
- Meta-learning with elastic prototypical network for fault transfer diagnosis of bearings under unstable speedsReliability Engineering & System Safety, 2024
- Bayesian variational transformer: A generalizable model for rotating machinery fault diagnosisMechanical Systems and Signal Processing, 2023
- Causal Graph Attention Network with Disentangled Representations for Complex Systems Fault DetectionReliability Engineering & System Safety, 2023
- Metric-based meta-learning model for few-shot fault diagnosis under multiple limited data conditionsMechanical Systems and Signal Processing, 2021
- An intelligent fault diagnosis approach based on transfer learning from laboratory bearings to locomotive bearingsMechanical Systems and Signal Processing, 2019