Research on a Fault Diagnosis Method for Rolling Bearings Based on the Fusion of PSR-CRP and DenseNet
Open Access
Abstract
To address the challenges of unstable vibration signals, indistinct fault features, and difficulties in feature extraction during rolling bearing operation, this paper presents a novel fault diagnosis method based on the fusion of PSR-CRP and DenseNet. The Phase Space Reconstruction (PSR) method transforms one-dimensional bearing vibration data into a three-dimensional space. Euclidean distances between phase points are calculated and mapped into a Color Recurrence Plot (CRP) to represent the bearings’ operational state. This approach effectively reduces feature extraction ambiguity compared to RP, GAF, and MTF methods. Fault features are extracted and classified using DenseNet’s densely connected topology. Compared with CNN and ViT models, DenseNet improves diagnostic accuracy by reusing limited features across multiple dimensions. The training set accuracy was 99.82% and 99.90%, while the test set accuracy is 97.03% and 95.08% for the CWRU and JNU datasets under five-fold cross-validation; F1 scores were 0.9739 and 0.9537, respectively. This method achieves highly accurate diagnosis under conditions of non-smooth signals and inconspicuous fault characteristics and is applicable to fault diagnosis scenarios for precision components in aerospace, military systems, robotics, and related fields.Keywords
Funding Information
- North China Institute of Aerospace Engineering (YKY-2024-23)
This publication has 32 references indexed in Scilit:
- Intelligent Fault Diagnosis of Rolling Bearings in Strong Noise Environment: An Attention-Driven Hybrid Model Based on IENEMD and Parallel Multiscale CNNInternational Journal of Precision Engineering and Manufacturing-Green Technology, 2025
- Gear fault diagnosis research based on GAF-TFR-2DCV with small sample sizeAin Shams Engineering Journal, 2025
- Few-shot fault diagnosis of EHA based on MTF-ResNet-MA and dual-attribute adaptive decision-level fusionMeasurement, 2025
- Intelligent fault diagnosis of rolling bearings in strongly noisy environments using graph convolutional networksInternational Journal of Adaptive Control and Signal Processing, 2024
- Fault Detection of Flexible DC Distribution Network Based on GAF and Improved Deep Residual NetworkJournal of Electrical Engineering & Technology, 2024
- Dynamic modeling and analysis of rolling bearings with rolling element defect considering time-varying impact forceJournal of Sound and Vibration, 2023
- A Novel Vibration Model for Explanation of the Frequency Features in Multistage Wind Turbine Gearboxes Considering the Effects of Inter-stage Meshing Frequency ModulationInternational Journal of Precision Engineering and Manufacturing-Green Technology, 2022
- A novel embedding method for characterization of low-dimensional nonlinear dynamical systemsNonlinear Dynamics, 2021
- A review on signal processing techniques utilized in the fault diagnosis of rolling element bearingsTribology International, 2016
- Short-time matrix series based singular value decomposition for rolling bearing fault diagnosisMechanical Systems and Signal Processing, 2013