Articles | Volume 16, issue 2
https://doi.org/10.5194/ms-16-579-2025
https://doi.org/10.5194/ms-16-579-2025
Research article
 | 
21 Oct 2025
Research article |  | 21 Oct 2025

Rub-impact fault diagnosis of rotor systems based on EMD and dynamic CNN

Jinmin Shi, Ruixiao Zhang, and Qian Wang

Cited articles

Arifin, M., Wang, W., and Uddin, M.: An enhanced empirical mode decomposition technique for rotor fault detection in induction motors, IEEE T. Instrum. Meas., 74, https://doi.org/10.1109/TIM.2025.3551988, 2025. 
Chen, L., Dong, L., Wu, Z., Fan, C., Shi, Wei., Li, H., Hua., R., and Dai, C.: ResNet diagnosis of rotor faults in oil transfer pumps, Heliyon, 10, https://doi.org/10.1016/j.heliyon.2024.e36170, 2024. 
Ding, C. and Wang, B.: Sparsity-assisted adaptive chirp mode decomposition and its application in rub-impact fault detection, Measurement, 188, https://doi.org/10.1016/j.measurement.2021.110539, 2022. 
Hou, Y., Cao, S., and Kang, Y.: Study on the frequency modulation phenomenon in the rotor system with blade-casing rub-impact fault, Int. J. Nonlin. Mech., 159, https://doi.org/10.1016/j.ijnonlinmec.2023.104626, 2024. 
Jin, M., Wang, A., Wang, Q., and Wang, L.: Rub-impact dynamic analysis of the central tie rod rotor-blade-casing coupling system with the hirth couplings connection, J. Vib. Eng. Technol., 12, 1479–1503, https://doi.org/10.1007/s42417-023-00921-9, 2023. 
Download
Short summary
In this paper, a new rotor rub-impact fault diagnosis method is proposed. The more sensitive fault features associated with the dynamics information are achieved based on the dynamic convolutional neural network. The experiment shows that the proposed method can obtain better diagnosis performance compared with traditional methods and that it has achieved the highest diagnosis accuracy of 98.5 % without noise and 98 % with noise. 
Share