Xinxin Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Xinxin Li has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Jian Tang
Army Engineering University of PLA
1 shared publication - Jing Zhang
Army Engineering University of PLA, China
1 shared publication - Pengfei Pang
Army Engineering University, Nanjing, China
1 shared publication - Yinchuan Hou
Army Engineering University, Nanjing, China
1 shared publication
Latest Publications
- Open Access
- 1 January 2025
- Published by FapUNIFESP (SciELO) in Latin American Journal of Solids and Structures
- Vol. 22 (9)
An improved CS - Transformer for fault diagnosis of rotating machinery bearings under strong noise conditions
To address the issues of poor noise resistance and the lack of mechanistic analysis in the classification and diagnosis of fault vibration signals collected by sensors using existing deep learning models, this paper proposes a Transformer-based fault diagnosis model incorporating squared convolution under strong noise conditions, namely CS-Transformer. This model enhances the local feature representation of fault vibration signals through wide convolution kernels and squaring operations, improves the robustness of global features by leveraging global average pooling, and employs a single-layer Transformer encoder to uncover the correlations among global features, thereby further focusing on key fault features. Fault diagnosis experiments were conducted based on the CWRU and Paderborn bearing datasets. When the signal-to-noise ratio is -6 dB, the noise resistance of the model exceeds 91%, significantly outperforming other comparable models. This validates the superior classification performance and generalization ability of this model for bearing faults of varying degrees under strong noise conditions. Moreover, the analysis of the visualized envelope spectrum further confirms that this model can effectively enhance the target fault frequency and suppress the noise.
- 1 January 2025
- Published by FapUNIFESP (SciELO) in Latin American Journal of Solids and Structures
- Vol. 22 (9)
Open AccessAn improved CS - Transformer for fault diagnosis of rotating machinery bearings under strong noise conditions
To address the issues of poor noise resistance and the lack of mechanistic analysis in the classification and diagnosis of fault vibration signals collected by sensors using existing deep learning models, this paper proposes a Transformer-based fault diagnosis model incorporating squared convolution under strong noise conditions, namely CS-Transformer. This model enhances the local feature representation of fault vibration signals through wide convolution kernels and squaring operations, improves the robustness of global features by leveraging global average pooling, and employs a single-layer Transformer encoder to uncover the correlations among global features, thereby further focusing on key fault features. Fault diagnosis experiments were conducted based on the CWRU and Paderborn bearing datasets. When the signal-to-noise ratio is -6 dB, the noise resistance of the model exceeds 91%, significantly outperforming other comparable models. This validates the superior classification performance and generalization ability of this model for bearing faults of varying degrees under strong noise conditions. Moreover, the analysis of the visualized envelope spectrum further confirms that this model can effectively enhance the target fault frequency and suppress the noise.