Hybrid digital twin-based data enrichment strategy for reliable machine learning-based diagnosis of ball bearings under multi-regime operating conditions
- 20 March 2026
- journal article
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 37 (11) , 116107
Abstract
Reliable fault diagnosis is essential for condition monitoring of rotating machinery, yet the scarcity of experimental data often limits the effectiveness of machine learning algorithms. A promising approach lies in constructing hybrid datasets that combine experimental and numerical data. However, if performed arbitrarily, such hybridization may degrade diagnostic reliability. This study proposes a systematic methodology for building hybrid databases for ball bearing fault diagnosis across multiple fault severities and varying operating conditions. The methodology is evaluated along three complementary axes: (i) single-condition performance, (ii) expandability to a wide range of speeds through the identification of a reliable variation range, and (iii) transferability of calibration parameters to neighboring regime operating conditions. Both homogeneous (quantitative enrichment) and heterogeneous (qualitative enrichment with unseen fault labels) hybridizations are investigated. Results demonstrate that even a small experimental fraction (≈10%) substantially enhances classification accuracy compared with purely numerical models, while stable performance (>90%) is achieved from about 30% of experimental data. In multi-speed scenarios, hybridization maintains generalization provided sufficient experimental anchoring, though the reliable range remains narrow and asymmetric. In heterogeneous configurations, high accuracy is preserved even with a single EC, as numerical enrichment effectively compensates for missing severities, provided the enrichment is balanced with the operating range.Keywords
Funding Information
- Campus France
- French Embassy in the Democratic Republic of Congo
- French Government
This publication has 34 references indexed in Scilit:
- Towards Accurate Gear Fault Diagnosis: Hybrid Data Enrichment by Digital Twins for Machine Learning-Based MonitoringJournal of Vibration Engineering & Technologies, 2025
- A fault diagnosis data augmentation method integrating multimodal non-Gaussian denoising diffusion generative adversarial networkAdvanced Engineering Informatics, 2025
- A modified domain adversarial approach based on model and data-driven for bearing fault diagnosisExpert Systems with Applications, 2025
- Spectral kurtosis attention network (SKAN): Synergizing signal processing and deep learning for fault diagnosis of rolling element bearingsExpert Systems with Applications, 2025
- Unsupervised multiple-target domain adaptation for bearing fault diagnosisEngineering Applications of Artificial Intelligence, 2025
- A new difference feature extraction method of slewing bearings in wind turbines via optimization bispectrum domain modelExpert Systems with Applications, 2025
- A dual-discriminator network based on Sobel gradient operator for digital twin-assisted fault diagnosisEngineering Applications of Artificial Intelligence, 2025
- Domain generalization for rotating machinery fault diagnosis: A surveyAdvanced Engineering Informatics, 2024
- Digital twin-assisted fault diagnosis framework for rolling bearings under imbalanced dataApplied Soft Computing, 2024
- Digital Twin applications toward Industry 4.0: A ReviewCognitive Robotics, 2023