Abstract
Planetary gearbox plays an important role in many industrial fields and is also a vulnerable component. It is of great significance to develop the time–frequency analysis method of planetary gearbox for ensuring the safe operation of equipment. To analyze the fault characteristics quickly and automatically in time–frequency information, this paper proposes a time–frequency analysis method based on improved U-net++. In the proposed method, the modified U-net++ is used to compress and expand the vibration time–frequency data generated by the normalized S transform, and the original overlap-tile strategy is adjusted. In addition, Tversky loss is introduced into the U-net++ model as an optimization objective. The improved U-net++ is evaluated on the gearbox vibration dataset of in-service wind turbines. The experimental results show that the Dice coefficient of the feature area analysis reached 0.949. The convergence speed and calculation efficiency are also significantly improved, which proved the effectiveness and progressiveness of the improved U-net++ in the planetary gearbox time–frequency analysis.
Similar content being viewed by others
References
Y.G. Lei, J. Lin, M.J. Zuo, Z.J. He, Condition monitoring and fault diagnosis of planetary gearboxes: a review. Measurement. 48, 292–305 (2014)
T.Y. Wang, Q.K. Han, F.L. Chu, Z.P. Feng, Vibration based condition monitoring and fault diagnosis of wind turbine planetary gearbox: a review. Mech. Syst. Signal Proc. 126, 662–685 (2019)
J.C. Yao, C. Liu, K.Y. Song, C.L. Feng, D.X. Jiang, Fault diagnosis of planetary gearbox based on acoustic signals. Appl. Acoust. 181, 108151 (2021)
D.Z. Zhao, L.L. Cu, F.L. Chu, Synchro-reassigning scaling chirplet transform for planetary gearbox fault diagnosis. IEEE Sens. J. 22(15), 15248–15257 (2022)
Y.C. Luo, L.L. Cui, J.F. Ma, An improved phenomenological model of the planetary gearbox based on meshing vibration characteristics. IEEE Access. 8, 103462–103475 (2020)
Y.Y. Nie et al., Phenomenological vibration models of planetary gearboxes for gear local fault diagnosis. Mech. Mach. Theory. 170, 104698 (2022)
J.C. Yao, C. Liu, K.Y. Song, X.C. Zhang, D.X. Jiang, Fault detection of complex planetary gearbox using acoustic signals. Measurement. 178, 109428 (2021)
M.N. Mastrone, L. Hildebrand, C. Paschold, T. Lohner, K. Stahl, F. Concli, Numerical and experimental analysis of the oil flow in a planetary gearbox. Appl. Sci.-Basel. 13(2), 1014 (2023)
H. Hou, H.Q. Ji, Improved multiclass support vector data description for planetary gearbox fault diagnosis. Control Eng. Pract. 114, 104867 (2021)
H. Hu et al., Gear fault detection in a planetary gearbox using deep belief network. Math. Probl. Eng. 2022, 9908074 (2022)
Z.P. Feng, A.R. Gao, K.Q. Li, H.Q. Ma, Planetary gearbox fault diagnosis via rotary encoder signal analysis. Mech. Syst. Signal Proc. 149, 107325 (2021)
S. Xiang, Y. Qin, C.C. Zhu, Y.Y. Wang, H.Z. Chen, Long short-term memory neural network with weight amplification and its application into gear remaining useful life prediction. Eng. Appl. Artif. Intell. 91, 103587 (2020)
Z. Jin, D. Chen, D. He, Y. Sun, X. Yin, Bearing fault diagnosis based on VMD and improved CNN. J. Fail. Anal. Preven. 23(1), 165–175 (2023)
Q. Zhang, L. Deng, An intelligent fault diagnosis method of rolling bearings based on short-time Fourier transform and convolutional neural network. J. Fail. Anal. Prev. (2023)
X.W. Chen, Z.P. Feng, Iterative generalized time-frequency reassignment for planetary gearbox fault diagnosis under nonstationary conditions. Mech. Syst. Signal Process. 80, 429–444 (2016)
H. Wang, J.W. Xu, C. Sun, R.Q. Yan, X.F. Chen, Intelligent fault diagnosis for planetary gearbox using time-frequency representation and deep reinforcement learning. IEEE-ASME Trans. Mechatron. 27(2), 985–998 (2022)
S.J. Han, Z.P. Feng, Deep subclass alignment transfer network based on time-frequency features for intelligent fault diagnosis of planetary gearboxes under time-varying speeds. Meas. Sci. Technol. 33(10), 105010 (2022)
Y.J. Xu, J.Z. Liu, Z. Wan, D.H. Zhang, D. Jiang, Rotor fault diagnosis using domain-adversarial neural network with time-frequency analysis. Machines. 10(8), 610 (2022)
C.M. Tsai, C.S. Wang, Y.J. Chung, Y.D. Sun, J.W. Perng, Multisensor fusion time-frequency analysis of thruster blade fault diagnosis based on deep learning. IEEE Sens. J. 22(20), 19761–19771 (2022)
R.B. Sun, Z.B. Yang, X.F. Chen, S.H. Tian, Y. Xie, Gear fault diagnosis based on the structured sparsity time-frequency analysis. Mech. Syst. Signal Proc. 102, 346–363 (2018)
G. Yu, A concentrated time-frequency analysis tool for bearing fault diagnosis. IEEE Trans. Instrum. Meas. 69(2), 371–381 (2020)
L. Deng et al., Vortex-U-net: an efficient and effective vortex detection approach based on U-net structure. Appl. Soft. Comput. 115, 108229 (2022)
G.A. Francia, C. Pedraza, M. Aceves, S. Tovar-Arriaga, Chaining a U-net with a residual U-net for retinal blood vessels segmentation. IEEE Access. 8, 38493–38500 (2020)
S.J. Saida, S. Ari, MU-net: modified U-net architecture for automatic ocean Eddy detection. IEEE Geosci. Remote Sens. Lett. 19, 1507005 (2022)
C. Chu, J.H. Zheng, Y. Zhou, Ultrasonic thyroid nodule detection method based on U-net network. Comput. Meth. Programs Biomed. 199, 105906 (2021)
V.W.H. Wong, M. Ferguson, K.H. Law, Y.T.T. Lee, P. Witherell, Segmentation of additive manufacturing defects using U-net. J. Comput. Inf. Sci. Eng. 22(3), 031005 (2022)
J.T. Zhao, M. Dang, Z.H. Chen, L. Wan, DSU-net: distraction-sensitive U-net for 3D lung tumor segmentation. Eng. Appl. Artif. Intell. 109, 104649 (2022)
N. Micallef, D. Seychell, C.J. Bajada, Exploring the U-net plus plus model for automatic brain tumor segmentation. IEEE Access. 9, 125523–125539 (2021)
B. Li, M.L. Liu, Z.J. Guo, Y.M. Ji, Mechanical fault diagnosis of high voltage circuit breakers utilizing EWT-improved time frequency entropy and optimal GRNN classifier. Entropy. 20(6), 448 (2018)
Y.C. Ma, C.D. Wang, D.C. Yang, C. Wang, Adaptive extraction method based on time-frequency images for fault diagnosis in rolling bearings of motor. Math. Probl. Eng. 2021, 6687195 (2021)
A.J. Yin, L. Zhao, Z.Y. Yang, B.Q. Chen, Noise reduction method for vibration signals 2D time-frequency distribution using anisotropic diffusion equation. Math. Methods Appl. Sci. 38(4), 609–616 (2015)
Z.H. Li et al., Fault diagnosis of transformer windings based on decision tree and fully connected neural network. Energies. 14(6), 1531 (2021)
J.H. Pan, L.L. Qu, K.X. Peng, Sensor and actuator fault diagnosis for robot joint based on deep CNN. Entropy. 23(6), 751 (2021)
Y. Wang, D.J. Sheng, H.Q. Hu, K.F. Han, J.W. Zhou, L.M. Hou, A novel series arc fault detection method based on mel-frequency cepstral coefficients and fully connected neural network. IEEE Access. 10, 97983–97994 (2022)
Y.K. Wang, F. Zhang, X.H. Zhang, S.W. Zhang, Series AC arc fault detection method based on hybrid time and frequency analysis and fully connected neural network. IEEE Trans. Ind. Inform. 15(12), 6210–6219 (2019)
O. Ronneberger, P. Fischer, T. Brox, U-Net: Convolutional Networks for Biomedical Image Segmentation, in 18th International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) (2015), pp. 234–241
N. Siddique, S. Paheding, C.P. Elkin, V. Devabhaktuni, U-net and its variants for medical image segmentation: a review of theory and applications. IEEE Access. 9, 82031–82057 (2021)
Z.W. Zhou, M.M.R. Siddiquee, N. Tajbakhsh, J.M. Liang, U-Net plus plus: A Nested U-Net Architecture for Medical Image Segmentation, in 4th International Workshop on Deep Learning in Medical Image Analysis (DLMIA)/8th International Workshop on Multimodal Learning for Clinical Decision Support (ML-CDS) (2018), pp. 3–11
G. Huang, Z. Liu, L. van der Maaten, K.Q. Weinberger, IEEE, Densely Connected Convolutional Networks, in 30th IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2017), pp. 2261–2269
C.Y. Lee, S.N. Xie, P.W. Gallagher, Z.Y. Zhang, Z.W. Tu, Deeply-supervised nets, in 18th International Conference on Artificial Intelligence and Statistics (AISTATS) (2015), pp. 562–570
S.S.M. Salehi, D. Erdogmus, A. Gholipour, Tversky loss function for image segmentation using 3D fully convolutional deep networks, in 8th International Workshop on Machine Learning in Medical Imaging (MLMI) (2017), pp. 379–387
M.D. Adams, F. Kossentini, R.K. Ward, Generalized S transform. IEEE Trans. Signal Process. 50(11), 2831–2842 (2002)
A. Jablonski, T. Barszcz, Validation of vibration measurements for heavy duty machinery diagnostics. Mech. Syst. Signal Proc. 38(1), 248–263 (2013)
M.D. Bloice, P.M. Roth, A. Holzinger, Biomedical image augmentation using Augmentor. Bioinformatics. 35(21), 4522–4524 (2019)
C.K. Groschner, C. Choi, M.C. Scott, Machine learning pipeline for segmentation and defect identification from high-resolution transmission electron microscopy data. Microsc. microanal. 27(3), 549–556 (2021)
S. Jha, L.H. Son, R. Kumar, I. Priyadarshini, F. Smarandache, H.V. Long, Neutrosophic image segmentation with Dice Coefficients. Measurement. 134, 762–772 (2019)
Acknowledgments
The research was supported by the National Natural Science Foundation of China (No. 51675350).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared no potential conflicts of interest concerning the research, authorship, and/or publication of this article.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Zhang, P., Chen, C. Time–Frequency Analysis for Planetary Gearbox Fault Diagnosis Based on Improved U-Net++. J Fail. Anal. and Preven. 23, 1068–1080 (2023). https://doi.org/10.1007/s11668-023-01651-6
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11668-023-01651-6