Class-Incremental Unsupervised Domain Adaptation for Rotating Machinery Fault Diagnosis via Reliable Shared-Class Identification and Selective Adversarial Alignment
Preprint
- 1 September 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
Rotating machinery continuously generates unlabeled monitoring data during long-term operation, and the data distribution dynamically evolves with changing operating conditions. Conventional static offline diagnostic methods lack continuous adaptation capability, making it difficult to simultaneously handle newly emerging fault categories and cross-condition distribution shifts. This paper investigates class-incremental unsupervised domain adaptation for fault diagnosis (CIUDA-FD). In this setting, a diagnostic model is required to incrementally learn emerging fault categories from an unlabeled target-domain data stream while retaining previously acquired diagnostic knowledge. To address this challenge, this paper proposes a reliable shared-class identification and selective adversarial alignment (ReSCI-SAA) framework. Specifically, a tri-criteria shared-class identification (TriSCI) module with confidence fusion is first designed to identify reliable shared classes by jointly considering cumulative prediction probability, intra-domain clustering compactness, and inter-domain similarity. Based on the identified shared classes, a pseudo-label-guided selective adversarial alignment strategy is developed to align reliable class distributions across domains and reduce negative transfer from unreliable target samples. Furthermore, a prototype-accumulated knowledge distillation mechanism is introduced to mitigate catastrophic forgetting during class-incremental adaptation. Experimental results on the public CWRU bearing dataset and a self-built motor fault dataset demonstrate that the proposed method achieves superior average diagnostic performance over the best-performing existing method across multiple transfer tasks.Keywords
This publication has 25 references indexed in Scilit:
- Speed-invariant prototypical network for rolling bearing fault diagnosis under variable speed conditionsExpert Systems with Applications, 2026
- Cross-domain Intelligent Fault Diagnosis Method for rotating machinery based on deep universal domain adaptationEngineering Applications of Artificial Intelligence, 2025
- Intelligent fault diagnosis of bearings based on unsupervised domain adaptive adversarial graph neural network under variable operating conditionsMeasurement, 2025
- Multi-source structural fusion and synchronous heterogeneous network for power transformers partial domain adaptation fault diagnosisMeasurement, 2025
- Data-driven machinery fault diagnosis: A comprehensive reviewNeurocomputing, 2025
- A dynamic collaborative adversarial domain adaptation network for unsupervised rotating machinery fault diagnosisReliability Engineering & System Safety, 2024
- Pseudo-label assisted contrastive learning model for unsupervised open-set domain adaptation in fault diagnosisReliability Engineering & System Safety, 2024
- University of Ottawa constant and variable speed electric motor vibration and acoustic fault signature datasetData in Brief, 2024
- Multi-level weighted dynamic adversarial adaptation network for partial set cross-domain fault diagnosisMeasurement, 2023
- A multi-feature fusion-based domain adversarial neural network for fault diagnosis of rotating machineryMeasurement, 2022