Search

• A gearbox fault diagnosis method based on bearing force identification is proposed. • Identified bearing dynamic forces outperform vibration signals for fault diagnosis. • The proposed method avoids the dependence on the layout of measuring points. • The method can theoretically be combined with the feature extraction algorithms. In the area of gearbox fault diagnosis, to obtain sufficient and effective vibration information, traditional studies are usually conducted from the perspective of optimizing the layout of measuring points. This paper focuses on a gearbox fault diagnosis method based on bearing dynamic force identification. Gearbox bearing dynamic forces under the operating condition are modeled as excitation sources, and vibration signals measured at any position on the housing are modeled as receivers. Then mutual coupling effect of different structure transfer paths of housing on the excitation signals can be quantitatively modeled. The bearing dynamic forces are finally constructed with the transfer function matrix and vibration signals by solving the inverse problem. The identified bearing dynamic forces is capable of clearly reflecting the gear fault characteristics, which outperforms the original vibration signals measured on the gearbox housing due to poor signal quality and the effect of structure transfer paths. Numerical simulation and experimental studies show the effectiveness of the estimated bearing dynamic force signals for gear fault diagnosis. The proposed method is demonstrated to be insensitive to the location of measuring points, and shows a good potential in complicated mechanical system fault diagnosis. [ABSTRACT FROM AUTHOR]

• The proposed unsupervised method merges anomaly detection and fault tracing. • Signal decomposition-based energy features are extracted to make the diagnosis more robust. • The model training process only requires normal data. • The diagnostic process can be performed without labeled fault samples. The absence of detailed fault data presents a significant challenge in diagnosing faults of rotating machinery. This paper focuses on addressing abnormal detection and fault localization challenges in drivetrain components under the assumption that only normal data is available. Specifically, this paper proposes an unsupervised hypersphere description (UHD) framework by seamlessly integrating abnormal detection and localization. By constructing a one-class description hypersphere, this UHD method achieves fault detection without special fault samples. Abnormal samples can be detected based on their distance from the center of hypersphere, enabling accurate localization of the underlying abnormality. Validation of experimental data demonstrates that the UHD approach effectively detects anomalies and accurately localizes faults within specific locations. Remarkably, the UHD approach surpasses several mainstream unsupervised methods in terms of fault tracing accuracy. This shows the potential of the UHD approach in abnormal detection and localization in a drivetrain, particularly when only normal data is available. [ABSTRACT FROM AUTHOR]