Cross-domain fault diagnosis of ceramic bearings using multi-source data fusion: Vibration, acoustic, and infrared signals
- 15 August 2025
- journal article
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
- Vol. 239 (21) , 8970-8988
Abstract
The diagnosis of ceramic bearings based on the fusion of heterogeneous data from multiple sources can reflect fault information from multiple dimensions, representing an advanced method of fault diagnosis. Nevertheless, the extant cross-domain fault diagnosis methods for ceramic bearings based on heterogeneous data fusion are constrained by the dimensionality of the data, the network’s inadequate capacity to comprehend the interrelationships between the data, and the inconsistency of the fused fault features, which impede cross-domain fault diagnosis for ceramic bearings. In this paper, we propose a meta-learning network based on the fusion of heterogeneous data from vibration, sound, and infrared sources for cross-domain fault diagnosis of ceramic bearings under variable operating conditions. First, the non-parametric encoding of Gram Angle Field is employed to align and fuse the one-dimensional and two-dimensional heterogeneous data dimensions, thereby addressing the issue of dimensional disparity inherent in heterogeneous data. Second, a multi-source feature reconstruction module is designed to enhance the network’s ability to comprehend heterogeneous data features. To improve fault feature consistency, a multi-channel feature consistency module is developed to facilitate more consistent and generalizable feature representation. The results of the experiments demonstrate that the method attains an average diagnosis accuracy of 98.91% across six distinct cross-domain scenarios and exhibits robust performance in noise resistance experiments. The proposed method combines meta-learning with multimodal data fusion to address the limitations of single-modal sensing of rotating machinery under multi-physical field coupling conditions. It provides some practical application value for multimodal data monitoring of rotating systems such as aero-engines, high-speed machine tool spindles, and wind power gearboxes.Keywords
Funding Information
- Natural Science Foundation of Liaoning Provincial of China (2024-MSLH-390)
- National Key Research and Development Program of Liaoning Provincial of China (2024JH2/102400045)
- National Key Research and Development Program of China (2024YFB3410202)
- National Key Research and Development Program of China (2024YFB3410205)
- National Natural Science Foundation of China (Joint Fund) - Key Project (U23A20631)
This publication has 39 references indexed in Scilit:
- Multi-modal data cross-domain fusion network for gearbox fault diagnosis under variable operating conditionsEngineering Applications of Artificial Intelligence, 2024
- Dynamic analysis of full-ceramic bearing-rotor system under thermally induced loosening in aerospace applicationsEngineering Failure Analysis, 2024
- Generalized MAML for few-shot cross-domain fault diagnosis of bearing driven by heterogeneous signalsExpert Systems with Applications, 2023
- An unsupervised domain adaptation approach with enhanced transferability and discriminability for bearing fault diagnosis under few-shot samplesExpert Systems with Applications, 2023
- Simulation-Driven Subdomain Adaptation Network for bearing fault diagnosis with missing samplesEngineering Applications of Artificial Intelligence, 2023
- A fault diagnosis method based on stiffness evaluation model for full ceramic ball bearings containing subsurface cracksEngineering Failure Analysis, 2023
- Non-contact diagnosis for gearbox based on the fusion of multi-sensor heterogeneous dataInformation Fusion, 2023
- Domain adaptation network base on contrastive learning for bearings fault diagnosis under variable working conditionsExpert Systems with Applications, 2022
- Machine learning-based techniques for fault diagnosis in the semiconductor manufacturing process: a comparative studyThe Journal of Supercomputing, 2022
- Incipient Fault Detection of Full Ceramic Ball Bearing Based on Modified ObserverInternational Journal of Control, Automation, and Systems, 2022