An improved CS - Transformer for fault diagnosis of rotating machinery bearings under strong noise conditions
Open Access
- 1 January 2025
- journal article
- Published by FapUNIFESP (SciELO) in Latin American Journal of Solids and Structures
- Vol. 22 (9)
Abstract
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.Keywords
Funding Information
- National Natural Science Foundation of China (51705531)
This publication has 28 references indexed in Scilit:
- Multi-scale convolutional network with channel attention mechanism for rolling bearing fault diagnosisMeasurement, 2022
- Extreme learning machine and ensemble techniques for classification of rolling element bearing defectsLife Cycle Reliability and Safety Engineering, 2022
- Weighted envelope spectrum based on the spectral coherence for bearing diagnosisISA Transactions, 2022
- Analysis of vibration signals for a ball bearing-rotor system with raceway local defects and rotor eccentricityMechanism and Machine Theory, 2022
- Intelligent fault diagnosis of rotating machinery based on continuous wavelet transform-local binary convolutional neural networkKnowledge-Based Systems, 2021
- End-to-end CNN + LSTM deep learning approach for bearing fault diagnosisApplied Intelligence, 2020
- Bearing fault diagnosis base on multi-scale CNN and LSTM modelJournal of Intelligent Manufacturing, 2020
- An improved deep convolutional neural network with multi-scale information for bearing fault diagnosisNeurocomputing, 2019
- A Generic Intelligent Bearing Fault Diagnosis System Using Compact Adaptive 1D CNN ClassifierJournal of Signal Processing Systems, 2018
- Intelligent fault diagnosis of rolling bearing using hierarchical convolutional network based health state classificationAdvanced Engineering Informatics, 2017