Adaptively Weighted Semantic Autoencoder for Zero-Shot Compound Fault Diagnosis
- 4 October 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 24 (22) , 37472-37481
Abstract
It is a great challenging task to diagnose compound faults of rolling bearings because of the complex coupling characteristics of the single faults. Compound fault samples are generally requisite to establish traditional compound fault diagnosis models. However, the infrequency of compound faults in bearings within industrial scenarios may result in a lack of available corresponding data for training the models. To address the above issue, this paper proposes a new model named adaptively weighted semantic autoencoder (AWSAE) for bearing compound fault diagnosis based on zero-shot learning. Specifically, the proposed AWSAE constructs compound fault semantics by weighted superposition of the semantics of the accessible single faults, in which the weights are adaptively determined by an attention mechanism. A projection matrix is established by the semantic autoencoder that can effectively project the features of the tested compound fault samples to the corresponding semantics. Euclidean distances are then calculated in the semantic space to diagnose the types of the compound faults. In addition, to realize generalization zero-shot diagnosis, a pre-judgment strategy is designed by integrating the idea of decoupling learning. The architecture of the proposed AWSAE model is simple because the feature extractor is used repeatedly in the pre-judgment, the obtaining of adaptive weights, as well as the classification of all the health states. The proposed method is verified on two bearing datasets acquired from a rotor-bearing system and a wheel-rail system. The results show that the proposed AWSAE model performs well in identifying the bearing compound faults and is superior to the most advanced zero-shot learning models.Keywords
Funding Information
- Excellent Young Scientists Fund of Jiangsu Province (BK20240153)
- National Natural Science Foundation of China (52275121, 52275157)
This publication has 31 references indexed in Scilit:
- Domain fuzzy generalization networks for semi-supervised intelligent fault diagnosis under unseen working conditionsMechanical Systems and Signal Processing, 2023
- A zero-shot fault semantics learning model for compound fault diagnosisExpert Systems with Applications, 2023
- A label description space embedded model for zero-shot intelligent diagnosis of mechanical compound faultsMechanical Systems and Signal Processing, 2022
- A sudden fault detection network based on Time-sensitive gated recurrent units for bearingsMeasurement, 2021
- Multi-source fidelity sparse representation via convex optimization for gearbox compound fault diagnosisJournal of Sound and Vibration, 2021
- Zero-Shot Object Detection: Joint Recognition and Localization of Novel ConceptsInternational Journal of Computer Vision, 2020
- Deep learning and its applications to machine health monitoringMechanical Systems and Signal Processing, 2019
- Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualizationMechanical Systems and Signal Processing, 2018
- Compound fault prediction of rolling bearing using multimedia dataMultimedia Tools and Applications, 2017
- An improved multiscale noise tuning of stochastic resonance for identifying multiple transient faults in rolling element bearingsJournal of Sound and Vibration, 2014