A three-dimensional clustering study of gearbox system failures based on frequency-domain feature structure analysis

Abstract

In actual operation, vibration signals from gearbox systems are susceptible to load fluctuations, speed variations, and environmental noise. The spectral differences between various fault states are often subtle, resulting in blurred sample boundaries and posing challenges for structural separation and state analysis. To address the aforementioned issues, this paper establishes a three-dimensional (3D) feature structure analysis framework based on frequency-domain statistical characteristics to investigate the structural distribution properties of gearbox vibration data. First, extract frequency-domain statistical features such as dominant frequency, energy, and bandwidth to construct a feature matrix. We then analyze the distribution patterns of different features in the sample space through two-dimensional projection analysis, identify key features that contribute significantly to the structure, and, by considering the correlations among features, perform structural consolidation and weighted fusion of features with similar trends to reduce the impact of redundant information on structural representation. Based on this, a 3D feature space is constructed to visualize the distribution patterns of samples under different operating conditions, and the structural separability is verified using the contour coefficient and various clustering methods. Experimental results demonstrate that, using field data and publicly available datasets that include various rotational speeds and multiple types of component failures, samples of different failure states all form distribution structures in 3D space characterized by clear boundaries and intra-class compactness, with contour coefficients all exceeding 0.92. Furthermore, the extracted feature sets exhibit a certain correspondence with fault vibration characteristics, indicating that this method is capable of effectively capturing the structural differences between various fault states under complex operating conditions. This provides a reliable feature foundation for gearbox system condition assessment, fault diagnosis, and subsequent intelligent recognition.

Keywords

gearbox systems no tags clustering frequency domain statistical features 3D structural analysis state recognition fault diagnosis

Get full access to this article

View all access options for this article.

References

Dong

Zhang

Zhan

, et al. A novel dynamic predictive maintenance framework for gearboxes utilizing nonlinear Wiener process. Meas Sci Technol 2024; 35(12): 126210. https://doi.org/10.1088/1361-6501/ad762e

Nguyen

Diep

. Vibration-based gearbox fault diagnosis using a multi-scale convolutional neural network with depth-wise feature concatenation. PLoS One 2025; 20(7): e0324905. https://doi.org/10.1371/journal.pone.0324905

Shi

Peng

, et al. Planetary gearbox fault diagnosis using bidirectional-convolutional LSTM networks. Mech Syst Signal Process 2022; 162: 107996. https://doi.org/10.1016/j.ymssp.2021.107996

Wang

, et al. A novel bearing intelligent fault diagnosis framework under time-varying working conditions using recurrent neural network. ISA Trans 2020; 100: 155–170. https://doi.org/10.1016/j.isatra.2019.11.010

Ahmad

Cheng

Xing

, et al. Deep learning-based fault diagnosis of planetary gearbox: a systematic review. J Manuf Syst 2024; 77: 730–745. https://doi.org/10.1016/j.jmsy.2024.10.004

Yang

, et al. Nonlinear dynamic modeling and analysis of a helicopter planetary gear set for tooth crack diagnosis. Measurement 2022; 198: 111347. https://doi.org/10.1016/j.measurement.2022.111347

Han

Feng

Zhang

, et al. Intelligent fault diagnosis of planetary gearbox across conditions based on subdomain distribution adversarial adaptation. Sensors 2024; 24(21): 7017. https://doi.org/10.3390/s24217017

Xue

Wang

Howard

, et al. The diagnostic analysis of the fault coupling effects in planet bearing. Eng Fail Anal 2020; 108: 104266. https://doi.org/10.1016/j.engfailanal.2019.104266

Hashim

Shakya

. A spectral kurtosis based blind deconvolution approach for spur gear fault diagnosis. ISA Trans 2023; 142: 492–500. https://doi.org/10.1016/j.isatra.2023.07.035

10.

Liu

Yang

, et al. Deep adversarial transfer neural network for fault diagnosis of wind turbine gearbox. Int J Green Energy 2023; 20(15): 1750–1762. https://doi.org/10.1080/15435075.2023.2194375

11.

Wei

Yang

, et al. Intelligent fault diagnosis of planetary gearbox based on refined composite hierarchical fuzzy entropy and random forest. ISA Trans 2021; 109: 340–351. https://doi.org/10.1016/j.isatra.2020.10.028

12.

Issaadi

Hemsas

Soualhi

. Wind turbine gearbox diagnosis based on stator current. Energies 2023; 16(14): 5286. https://doi.org/10.3390/en16145286

13.

Mauricio

Gryllias

. Cyclostationary-based multiband envelope spectra extraction for bearing diagnostics: the combined improved envelope spectrum. Mech Syst Signal Process 2021; 149: 107150. https://doi.org/10.1016/j.ymssp.2020.107150

14.

Huang

Zhang

Guo

, et al. Wavelet packet decomposition-based multiscale CNN for fault diagnosis of wind turbine gearbox. IEEE Trans Cybern 2021; 53(1): 443–453. https://doi.org/10.1109/TCYB.2021.3123667

15.

Dhiman

Deb

Muyeen

, et al. Wind turbine gearbox anomaly detection based on adaptive threshold and twin support vector machines. IEEE Trans Energy Convers 2021; 36(4): 3462–3469. https://doi.org/10.1109/TEC.2021.3075897

16.

Meng

Kong

, et al. Small sample fault diagnosis method for wind turbine gearbox based on optimized generative adversarial networks. Eng Fail Anal 2022; 140: 106573. https://doi.org/10.1016/j.engfailanal.2022.106573

17.

Hosseinpour-Zarnaq

Omid

Biabani-Aghdam

. Fault diagnosis of tractor auxiliary gearbox using vibration analysis and random forest classifier. Inf Process Agric 2022; 9(1): 60–67. https://doi.org/10.1016/j.inpa.2021.01.002

18.

Guo

Yang

Hua

, et al. Coupling fault diagnosis of wind turbine gearbox based on multitask parallel convolutional neural networks with overall information. Renew Energy 2021; 178: 639–650. https://doi.org/10.1016/j.renene.2021.06.088

19.

Hogea

Onchiş

Yan

, et al. LogicLSTM: logically-driven long short-term memory model for fault diagnosis in gearboxes. J Manuf Syst 2024; 77: 892–902. https://doi.org/10.1016/j.jmsy.2024.10.003

20.

Jiao

Zhang

Fang

, et al. Ensemble of simplified graph wavelet neural networks for planetary gearbox fault diagnosis. IEEE Trans Instrum Meas 2023; 72: 1–10. https://doi.org/10.1109/TIM.2023.3310092

21.

Ding

. Fault diagnosis of rotating machinery using novel self-attention mechanism TCN with soft thresholding method. Meas Sci Technol 2024; 35(4): 047001. https://doi.org/10.1088/1361-6501/ad1eb3

22.

Zhang

Wang

Zhou

, et al. Trustworthy diagnostics with out-of-distribution detection: a novel max-consistency and min-similarity guided deep ensembles for uncertainty estimation. IEEE Internet Things J 2024; 11(13): 23055–23067. https://doi.org/10.1109/JIOT.2024.3387481

23.

Zhang

Yan

Wang

, et al. Generalizable fault diagnosis under distribution shifts induced by unseen working conditions via synthetic and adversarial sample learning. IEEE Trans Reliab 2025; 74(4): 5517–5530. https://doi.org/10.1109/TR.2025.3616336

24.

Yan

Dong

Wang

, et al. An intelligent method of health state division and assessment for gearbox based on acoustic signals. Qual Reliab Eng Int 2025; 41(4): 1195–1208. https://doi.org/10.1002/qre.3717

25.

Shi

Liu

Gao

. Study of wind turbine fault diagnosis and early warning based on SCADA data. IEEE Access 2021; 9: 124600–124615. https://doi.org/10.1109/ACCESS.2021.3110909

26.

Huang

, et al. The hybrid prediction of wind turbine gearbox oil temperature based on chaotic theory. J Supercomput 2025; 81(8): 927. https://doi.org/10.1007/s11227-025-07438-w

27.

Maaten

Hinton

. Visualizing data using t-SNE. J Mach Learn Res 2008; 9(Nov): 2579–2605.

28.

Hodgson

Wang

Cristea

, et al. Partially-supervised metric learning via dimensionality reduction of text embeddings using transformer encoders and attention mechanisms. IEEE Access 2024; 12: 77536–77554. https://doi.org/10.1109/ACCESS.2024.3403991

29.

Yin

Meng

Cheng

. Failure modeling and multidimensional optimization of gearbox journal bearings to prevent wear failures and reduce friction in wind turbines. Eng Fail Anal 2025; 178: 109748. https://doi.org/10.1016/j.engfailanal.2025.109748

30.

Zhang

Wang

Zhong

, et al. Domain adaptation-based multi-task model incorporating mixture-of-experts and feature decoupling for unseen compound fault diagnosis of gearbox. Meas Sci Technol 2025; 36(10): 106113. https://doi.org/10.1088/1361-6501/ae0cef

31.

Yan

Liu

Jia

. Multiscale cascading deep belief network for fault identification of rotating machinery under various working conditions. Knowl Based Syst 2020; 193: 105484. https://doi.org/10.1016/j.knosys.2020.105484

32.

Zhao

Yao

Deng

, et al. Intelligent fault diagnosis of gearbox under variable working conditions with adaptive intraclass and interclass convolutional neural network. IEEE Trans Neural Netw Learn Syst 2022; 34(9): 6339–6353. https://doi.org/10.1109/TNNLS.2021.3135877

33.

Habbouche

Amirat

Benkedjouh

, et al. Digital twin-based gearbox fault diagnosis using variational mode decomposition and dynamic vibration modeling. Measurement 2025; 246: 116669. https://doi.org/10.1016/j.measurement.2025.116669

34.

Taylor

Merényi

. Automating t-SNE parameterization with prototype-based learning of manifold connectivity. Neurocomputing 2022; 507: 441–452. https://doi.org/10.1016/j.neucom.2022.07.009