Multihead Self-Attention Incremental Network for Rotating Machinery Fault Diagnosis Across Nonstationary Operating Conditions
- 16 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75 (00189456) , 1-16
Abstract
The advancement of artificial intelligence has enabled significant progress in data-driven fault diagnosis for rotating machinery. However, in real-world industrial environments, such machinery often operates under time-varying and non-stationary conditions, leading to continuous changes in data distributions. These variations pose a major challenge to conventional deep learning models, which are prone to catas-trophic forgetting when sequentially learning new diagnostic tasks. To address this, this paper proposes a novel Multi-head Self-attention Incremental Network (MSIN) for fault diagnosis across non-stationary operating conditions. MSIN employs a stack of multi-head self-attention encoder layers to effectively extract fault-relevant features from frequency-domain signals. To alleviate catastrophic forgetting, the model integrates a selective exemplar replay strategy and introduces a joint cross-head knowledge distillation loss, enabling effective knowledge retention across tasks. The proposed method is evaluated on two benchmark datasets under both stationary and non-stationary conditions. Experimental results demonstrate that MSIN achieves superior diagnostic accuracy and knowledge retention compared to existing Incremental Learning methods, offering a promising solution for continuous fault diagnosis in dynamic industrial settings. The source code of the MSIN model is available at: https://github.com/bankuaimianbao/MSIN-Non-stationary-Code.Keywords
Funding Information
- National Natural Science Foundation of China (52505127)
- Fundamental Research Funds for the Central Universities, Northwestern Polytechnical University (G2023KY05102)
This publication has 41 references indexed in Scilit:
- Multi-mode fault diagnosis datasets of gearbox under variable working conditionsData in Brief, 2024
- Continual Unsupervised Domain Adaptation for Bearing Fault Diagnosis Under Variable Working Conditions2024
- Diagnosisformer: An efficient rolling bearing fault diagnosis method based on improved TransformerEngineering Applications of Artificial Intelligence, 2023
- Bearing fault diagnosis under various conditions using an incremental learning-based multi-task shared classifierKnowledge-Based Systems, 2023
- Finding compact and well-separated clusters: Clustering using silhouette coefficientsPattern Recognition, 2022
- Multi-scale convolutional network with channel attention mechanism for rolling bearing fault diagnosisMeasurement, 2022
- PODNet: Pooled Outputs Distillation for Small-Tasks Incremental Learning2020
- Overcoming catastrophic forgetting in neural networksProceedings of the National Academy of Sciences, 2017
- The spectral analysis of cyclo-non-stationary signalsMechanical Systems and Signal Processing, 2016
- Deterministic-random separation in nonstationary regimeJournal of Sound and Vibration, 2016