AEDIO-ETCN: alleviating inter-class overlap via error detection and optimization for imbalanced fault diagnosis of aero-engine two-dimensional nozzle
Authors:
- Guanxiang FengGFGuanxiang Feng
- Yingxue ChenYCYingxue Chen
- Huihui LiHLHuihui Li
- Linfeng GouLGLinfeng Gou
- 12 June 2025
- journal article
- Published by Elsevier in Advanced Engineering Informatics
- Vol. 67
Abstract
No abstract availableFunding Information
- Shanxi Provincial Key Research and Development Project (P2022-DB-V-001-001)
- Northwestern Polytechnical University (ST2023JGY05)
- National Natural Science Foundation of China (62203364)
- Shaanxi Province Key Research and Development Projects (2024GX-YBXM-473)
This publication has 38 references indexed in Scilit:
- Triplet attention-enhanced residual tree-inspired decision network: A hierarchical fault diagnosis model for unbalanced bearing datasetsAdvanced Engineering Informatics, 2023
- A novel fault diagnosis method for wind turbine based on adaptive multivariate time-series convolutional network using SCADA dataAdvanced Engineering Informatics, 2023
- Machine fault diagnosis with small sample based on variational information constrained generative adversarial networkAdvanced Engineering Informatics, 2022
- Highly imbalanced fault diagnosis of gas turbines via clustering-based downsampling and deep siamese self-attention networkAdvanced Engineering Informatics, 2022
- A novel synthetic minority oversampling technique based on relative and absolute densities for imbalanced classificationApplied Intelligence, 2022
- SMOTE-WENN: Solving class imbalance and small sample problems by oversampling and distance scalingApplied Intelligence, 2020
- A self‐adaptive synthetic over‐sampling technique for imbalanced classificationInternational Journal of Intelligent Systems, 2020
- Safe-Level-SMOTE: Safe-Level-Synthetic Minority Over-Sampling TEchnique for Handling the Class Imbalanced Problem2009
- Combined Effects of Class Imbalance and Class Overlap on Instance-Based Classification2006
- Borderline-SMOTE: A New Over-Sampling Method in Imbalanced Data Sets Learning2005