Fault Diagnosis of Planetary Gear Train Crack Based on DC-DRSN
Source abstract
Abstract
To solve the problem that the existing planetary gear train fault diagnosis methods have, namely their low diagnostic accuracy under low signal-to-noise ratio (SNR), a fault diagnosis method based on a double channel-deep residual shrinkage network (DC-DRSN) is proposed. The short-time Fourier transform (STFT) is used to convert the original vibration signal into a two-dimensional time-frequency graph, which effectively enhances the ability to express information. A DC-DRSN model is constructed, and the optimal number of residual shrinkage modules is determined by combining the diagnostic characteristics with different noises, which effectively improves the accuracy and anti-noise ability of fault diagnosis. The results of bearing and planetary gear train crack fault diagnosis show that the diagnosis method based on DC-DRSN has higher diagnostic accuracy while realizing fault diagnosis, which is better than other deep learning diagnosis methods. At the same time, the method can adapt to fault diagnosis in different noise environments, and has good expression ability and generalization ability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Machine Fault Diagnosis Techniques · Fault Detection and Control Systems · Gear and Bearing Dynamics Analysis
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Mechanical Engineering, Chongqing University of Technology, Chongqing 400054, China
Funding
National Natural Science Foundation of China · Chongqing Municipal Science and Technology Bureau Innovation and Development Joint Fund Project · special key project of technological innovation and application development in Chongqing · Graduate Innovation Project of Chongqing University of Technology
References (30)
Show source-provided references
1. Application of spectral kurtosis for detection of a tooth crack in the planetary gear of a wind turbine10.1016/j.ymssp.2008.07.019 ↗
2. Fault diagnosis in dynamic systems using analytical and knowledge based redundancy10.1016/0005-1098(90)90018-D ↗
3. Research on test bench bearing fault diagnosis of improved EEMD based on improved adaptive resonance technology10.1016/j.measurement.2021.109986 ↗
4. Compound faults diagnosis and analysis for a wind turbine gearbox via a novel vibration model and empirical wavelet transform10.1016/j.renene.2018.12.094 ↗
5. Rolling Bearing Fault Diagnosis Based on DS-VMD and Correlated Kurtosis
6. The Fault Diagnosis of Rolling Bearing Based on SSD and ICA Noise Reduction
7. Cyclostationary-based multiband envelope spectra extraction for bearing diagnostics: The combined improved envelope spectrum10.1016/j.ymssp.2020.107150 ↗
8. Fault diagnosis of planetary gearbox based on parameter optimized VMD and multi-domain manifold learning
9. Bearing fault diagnosis in the mixed domain based on crossover-mutation chaotic particle swarm10.1155/2021/6632187 ↗
10. Diesel engine gearbox fault diagnosis based on multi-features extracted from vibration signals
11. Probabilistic Latent Semantic Analysis-Based Gear Fault Diagnosis under Variable Working Conditions10.1109/TIM.2019.2925410 ↗
12. Gear Fault Diagnosis Based on Variational Modal Decomposition and Wide+Narrow Visual Field Neural Networks10.1109/TASE.2021.3117288 ↗
13. Planetary Gear Fault Diagnosis Based on An Instantaneous Angular Speed Measurement System with a Dual Detector Setup10.1109/ACCESS.2020.2985170 ↗
14. An automatic speed adaption neural network model for planetary gearbox fault diagnosis10.1016/j.measurement.2020.108784 ↗
15. Convolutional Neural networks based on parallel multi-scale pooling branch: A transfer diagnosis method for mechanical vibrational signal with less computational cost10.1016/j.measurement.2022.110905 ↗
16. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep Residual Learning for Image Recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
17. Deep Residual Shrinkage Networks for Fault Diagnosis10.1109/TII.2019.2943898 ↗
18. Highly Imbalanced Fault Diagnosis of Rolling Bearings Based on Variational Mode Gaussian Distortion and Deep Residual Shrinkage Networks
19. Health Status Recognition of Rotating Machinery Based on Deep Residual Shrinkage Network under Time-Varying Conditions10.1109/JSEN.2022.3197754 ↗
20. DRSN-GAF: Deep Residual Shrinkage Network (DRSN) for Lithology Classification through Well Logging Data Transformed by Gram Angle Field10.1109/LGRS.2023.3346382 ↗
21. Bearing Running State Recognition Method Based on Feature-to-Noise Energy Ratio and Improved Deep Residual Shrinkage Network10.1109/TMECH.2021.3120755 ↗
22. Pareto-Optimal Adaptive Loss Residual Shrinkage Network for Imbalanced Fault Diagnostics of Machines10.1109/TII.2021.3094186 ↗
23. Signal estimation from modified short-time Fourier transform10.1109/TASSP.1984.1164317 ↗
24. Burrus, C.S., Gopinath, R.A., and Guo, H. (1998). Wavelets and Wavelet Transforms, Rice University.
25. A brief mental health outcome scale: Reliability and validity of the Global Assessment of Functioning (GAF)10.1192/bjp.166.5.654 ↗
26. Generalized S transform10.1109/TSP.2002.804085 ↗
27. Delving deep into spatial pooling for squeeze-and-excitation networks10.1016/j.patcog.2021.108159 ↗
28. SNR walls for signal detection10.1109/JSTSP.2007.914879 ↗
29. Vibration Signal Simulation and Fault Diagnosis of Planetary Gearboxes Based on Transmission Mechanism Analysis10.3901/JME.2014.17.061 ↗
30. Data-based techniques focused on modern industry: An overview10.1109/TIE.2014.2308133 ↗