A Bearing Fault Feature Cross-Domain Transfer Method Based on Motor Current Signals

Yin, Kexin; Chen, Chunjun; Luo, Beice; Deng, Ji

doi:10.1109/tim.2023.3323048

Cited by 2 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It promotes a diagnosis knowledge transfer across related motors by correcting the data distribution shift [27]. Yin et al [28] implemented a fault feature proxy transfer approach to facilitate the cross-operating condition domain diagnosis under imbalanced class distribution. Xia et al [29] utilized three-phase current signals by a digital twin-enhanced semi-supervised framework for labelscarce motor fault diagnosis.…”

Section: Introductionmentioning

confidence: 99%

Intelligent fault diagnosis of ultrasonic motors based on graph-regularized CNN-BiLSTM

Li,

Qin,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

The ultrasonic motor is peculiarly prone to failure due to continuous high-frequency friction-related power transfer, whose failure mechanisms are remarkably different from traditional induction motors. Intelligent fault diagnosis provides a way to alarm and avoid catastrophic losses proactively. However, previous studies using deep learning usually ignore the inherent geometric structure of the signal distribution. This paper proposes an intelligent multi-signal fault diagnosis framework for ultrasonic motors to restore the linear or nonlinear manifold structure by preserving the internal structure by integrating graph regularization with deep neural networks. Firstly, the one-dimensional CNN to learn spatial correlations and BiLSTM to exploit temporal dependencies are coalesced to build the deep neural network. Then, an improved k-nearest neighbor graph is proposed to protect the geometric structure information and force the latent features to be more concentrated within their classes. Moreover, the layer in the deep architecture to integrate graph regularization is designed to reduce computation cost, and an adaptive decay strategy is considered to adjust the coefficient of graph regularized automatically. A two-stage training algorithm is developed by considering the time to calculate the graph regularization term. Finally, the proposed multi-signal fault diagnosis framework is validated using datasets from the fault injection experiment of ultrasonic motors in China’s Yutu rover of Chang’e lunar probe. Experimental results show that the proposed method can effectively discriminate different fault types.

show abstract

Section: Introductionmentioning

confidence: 99%

Intelligent fault diagnosis of ultrasonic motors based on graph-regularized CNN-BiLSTM

Li,

Qin,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

show abstract

Bidirectional Current WP and CBAR Neural Network Model-Based Bearing Fault Diagnosis

Zhu,

Liu

2023

IEEE Access

View full text Add to dashboard Cite

In the era of artificial intelligence, the development of an efficient bearing, fault diagnosis method is of vital importance to ensure smooth production operations and avoid major economic losses. To this end, this paper proposes a bearing fault diagnosis method based on biphasic currents. The method first performs wavelet denoising on the biphasic current signal, then extracts its features by simple vector representation and algebraic operations, and finally, combines the CBAR model of Convolutional Block Attention Module (CBAM) and Residual Network (ResNet) for bearing fault diagnosis. The experimental results show that the highest accuracy rate reaches 100% in both single-point fault and single-point mixed with multiple faults conditions on the open source current bearing fault diagnosis dataset, respectively. Compared with other methods, the method proposed in this paper has the advantage of simple data processing, concise model structure, and high-fault diagnosis accuracy, which provides an effective way for dual-phase current-based bearing fault diagnosis. It is worth emphasizing that based on wavelet denoising, this paper uses the simplest vector representation and algebraic operations to preprocess the signal (WP), making the method more efficient and easy to implement.

show abstract

A Bearing Fault Feature Cross-Domain Transfer Method Based on Motor Current Signals

Cited by 2 publications

References 20 publications

Intelligent fault diagnosis of ultrasonic motors based on graph-regularized CNN-BiLSTM

Intelligent fault diagnosis of ultrasonic motors based on graph-regularized CNN-BiLSTM

Bidirectional Current WP and CBAR Neural Network Model-Based Bearing Fault Diagnosis

Contact Info

Product

Resources

About