To tackle the issues of inadequate extraction of weak fault features amid intense noise interference and the limited ability of single spectral features to characterize fault information in the fault diagnosis of turbofan engine rolling bearings, a fault identification method for aircraft engine based on cyclical extraction reconstruction and tri-modal frequency fusion-convolutional neural network (TMFF-CNN) is proposed. The method first obtains signal node components through wavelet packet decomposition, fuses kurtosis values and correlation coefficients to construct a comprehensive parameter, and cyclically extracts and reconstructs high signal-to-noise ratio (SNR) signals as signal preprocessing. Subsequently, spectrogram, Mel spectrogram, and Mel frequency cepstral coefficient features are extracted from the reconstructed signals, and multichannel input is constructed through TMFF. Lastly, a CNN is designed to achieve fault classification. Experimental verification using Case Western Reserve University bearing datasets shows that compared with methods without preprocessing, using single-index reconstruction, or adopting single spectral feature as input, the proposed method achieves a 100% recognition rate in noise-free environments and maintains a recognition rate of 99.034% at a 10 dB low SNR. Additionally, fault simulation experiments on a turbofan engine intermediate bearing are conducted to validate the effectiveness of the proposed diagnostic approach in practical complex noise environments. The findings demonstrate that this method can effectively suppress noise interference and improve the ability of feature representation. Therefore, this method can serve as a reliable solution for identifying complicated signals from turbofan engine rolling bearings.
ZhangSLiuZHeS, et al. Improved double TQWT sparse representation using the MQGA algorithm and new norm for aviation bearing compound fault detection. Eng Appl Artif Intell2022; 110: 104741. https://doi.org/10.1016/j.engappai.2022.104741
2.
WangBZhangXSunC, et al. A quantitative intelligent diagnosis method for early weak faults of aviation high-speed bearings. ISA Trans2019; 93: 370–383. https://doi.org/10.1016/j.isatra.2019.03.011
3.
YangYFTengGRWeiSH. Synchronous testing technology of aero-engine axial force and main bearing vibration. Gas Turb Exp Res2023; 36(1): 36–43 (in Chinese).
4.
CuiJQGaoJWXingRX, et al. Fault diagnosis method for rolling bearing based on attention mechanism and BiTCN model. Digit Signal Process2025; 167: 105454. https://doi.org/10.1016/j.dsp.2025.105454
5.
LiuBYanCFHeC, et al. An interpretable physics-informed subdomain moment-enhanced adaptation network for unsupervised transfer fault diagnosis of rolling bearing. Adv Eng Inform2025; 67: 103491. https://doi.org/10.1016/j.aei.2025.103491
6.
ShiHDCaoSYZuoHF, et al. Deep subdomain adversarial network with self-supervised learning for aero-engine high speed bearing fault diagnosis with unknown working conditions. Measurement2025; 241: 115668. https://doi.org/10.1016/j.measurement.2024.115668
7.
LouXSLoparoKA. Bearing fault diagnosis based on wavelet transform and fuzzy inference. Mech Syst Signal Process2004; 18(5): 1077–1095. https://doi.org/10.1016/S0888-3270(03)00077-3
8.
HuangNEShenZLongSR, et al. The empirical mode decomposition and the Hilbert spectrum for nonlinear non-stationary time series analysis. Proc R Soc1998; 454: 903–905.
9.
WangYJiaoSBYangHB, et al. Adaptive two-dimensional coupled bistable stochastic resonance and its application in bearing fault diagnosis. Chaos Soliton Fract2025; 194: 116245.
10.
HuangXXZhangGXuJQ. Adaptive multi-parameter constrained time-delay feedback tri-stable stochastic resonance combined with EEMD for rolling bearing fault diagnosis. Physica A Stat Mech Appl2025; 659: 130334. https://doi.org/10.1016/j.physa.2024.130334
11.
ZhangXQMaYMPanZK, et al. A novel stochastic resonance based deep residual network for fault diagnosis of rolling bearing system. ISA Trans2024; 148: 279–284. https://doi.org/10.1016/j.isatra.2024.03.020
12.
TanHXieSLiuR, et al. Bearing fault identification based on stacking modified composite multiscale dispersion entropy and optimised support vector machine. Measurement2021; 186: 110180. https://doi.org/10.1016/j.measurement.2021.110180
13.
JhaRKSwamiPD. Fault diagnosis and severity analysis of rolling bearings using vibration image texture enhancement and multiclass support vector machines. Appl Acoust2021; 182: 108243. https://doi.org/10.1016/j.apacoust.2021.108243
14.
LawLSKimJHLiewWYH, et al. An approach based on wavelet packet decomposition and Hilbert–Huang transform (WPD–HHT) for spindle bearings condition monitoring. Mech Syst Signal Process2012; 33: 197–211. https://doi.org/10.1016/j.ymssp.2012.06.004
ShaYDZhaoJHLuanXC, et al. Fault feature signal extraction method for rolling bearings in gas turbine engines based on threshold parameter decision screening. Measurement2024; 231: 114567. https://doi.org/10.1016/j.measurement.2024.114567
17.
ShaYDZhaoYLuanXC, et al. Feature extraction and characterization method of rolling bearing vibration signal based on multi-parameter information fusion screening. J Propuls Technol2023; 44 (7): 243–253 (in Chinese).
18.
LuanXCZhaoJHShaYD, et al. Multi-channel vibration information weighted fusion for fault feature extraction of rotating machinery main bearings. Mech Syst Signal Process2025; 228: 112476. https://doi.org/10.1016/j.ymssp.2025.112476
19.
LiMLYanCFKangJX, et al. Multiple faults separation and identification of rolling bearings based on time-frequency spectrogram. Struct Health Monit2023; 23(4): 2040–2067. https://doi.org/10.1177/14759217231197110
20.
YeMYYanXAChenN, et al. Intelligent fault diagnosis of rolling bearing using variational mode extraction and improved one-dimensional convolutional neural network. Appl Acoust2023; 202: 109143. https://doi.org/10.1016/j.apacoust.2022.109143
21.
JiangZYangBZhengR, et al. Fault diagnosis of proton exchange membrane fuel cell using multiple convolutional neural networks with multi-scale attention mechanism. Inform Sci2025; 720: 122524. https://doi.org/10.1016/j.ins.2025.122524
22.
GaoTHZhuHPWuJ, et al. A fully interpretable convolutional neural network for intelligent fault diagnosis of rotating machinery. Appl Soft Comput2025; 180: 113472. https://doi.org/10.1016/j.asoc.2025.113472
23.
LiuZPengZR. Few-shot bearing fault diagnosis by semi-supervised meta-learning with graph convolutional neural network under variable working conditions. Measurement2025; 240: 115402. https://doi.org/10.1016/j.measurement.2024.115402
24.
XuYZZhouZHLiuYL, et al. Information fusion diagnosis of switching tube open-circuit fault in V2G charging piles based on multi-scale convolutional neural network and dual-attention mechanism. Proc CSEE2025; 45(8): 2992–3003 (in Chinese).
25.
WuGHuangZLongZ, et al. Motor fault diagnosis method based on spiking convolutional neural network with multi-scale decomposition local features. ISA Trans2025; 164: 271–283. https://doi.org/10.1016/j.isatra.2025.05.035
YanHYZhouHDZhengJ, et al. Rolling bearing fault diagnosis based on 1D convolutional neural network and Kolmogorov–Arnold network for industrial internet. Comput Mater Contin2025; 83(3): 4659–4677. https://doi.org/10.32604/cmc.2025.062807
29.
PatilSSSalunkheVGJadhavPS, et al. A novel bearing faults diagnosis of rotor-bearing systems based on vibration responses and convolutional neural network. Mech Syst Signal Process2025; 236: 113055. https://doi.org/10.1016/j.ymssp.2025.113055
30.
LiXGChenYLiuY. A novel convolutional neural network with global perception for bearing fault diagnosis. Eng Appl Artif Intell2025; 143: 109986. https://doi.org/10.1016/j.engappai.2024.109986
31.
LiuBYanCFLiuYF, et al. Multiscale residual antinoise network via interpretable dynamic recalibration mechanism for rolling bearing fault diagnosis with few samples. IEEE Sens J2023; 23(24): 31425–31439. https://doi.org/10.1109/JSEN.2023.3328007
32.
HuBQLiuJXuY. A novel multi-scale convolutional neural network incorporating multiple attention mechanisms for bearing fault diagnosis. Measurement2025; 242: 115927. https://doi.org/10.1016/j.measurement.2024.115927
ChenGTangGZhuZ. VKCNN: an interpretable variational kernel convolutional neural network for rolling bearing fault diagnosis. Adv Eng Inform2024; 62: 102705. https://doi.org/10.1016/j.aei.2024.102705
35.
LuanXCXiaAGaoX, et al. Aviation gas turbine engine bearings faults diagnosis method based on multi-parameter fusion criterion judgment and AO-PNN. Struct Health Monit. Epub ahead of print 25 April 2025. https://doi.org/10.1177/1475921725132908
36.
ShiYLiuXYWeiCL. An event recognition method based on MFCC, superposition algorithm and deep learning for buried distributed optical fiber sensors. Opt Commun2022; 522: 128647. https://doi.org/10.1016/j.optcom.2022.128647
37.
JinSPWangXFDuLL, et al. Evaluation and modeling of automotive transmission whine noise quality based on MFCC and CNN. Appl Acoust2020; 172: 107562. https://doi.org/10.1016/j.apacoust.2020.107562
38.
KamangaIZhuGWangZ, et al. Enhancing Φ-OTDR vibration event classification by stacking MFCCs and differential phase features using CNNs. Opt Fiber Technol2024; 88: 104032. https://doi.org/10.1016/j.yofte.2024.104032
39.
WuQSLiuWJLiXR, et al. A multi-topology quantum convolutional neural network with qubit-measurement attention for image classification. Eng Appl Artif Intell2025; 160: 111705. https://doi.org/10.1016/j.engappai.2025.111705
40.
AzizSKhanMUUsmanA, et al. Bearing faults classification using novel log energy-based empirical mode decomposition and machine Mel-frequency cepstral coefficients. Digit Signal Process2025; 156: 104776. https://doi.org/10.1016/j.dsp.2024.104776
41.
ZhouSLChengYNXueJ, et al. A gated convolutional neural network-based tool remaining useful life prediction method. Eng Appl Artif Intell2025; 158: 111593. https://doi.org/10.1016/j.engappai.2025.111593
42.
WooGEParkSBParkGT, et al. Low-complexity hardware architecture for batch normalization of CNN training accelerator. Comput Mater Contin2025; 84(2): 3241–3257. https://doi.org/10.32604/cmc.2025.063723
43.
LuanXCShaYDLiuGM, et al. Accurate identification for early fault features of rolling bearings based on WPD-KVI-Hilbert Transform. J Propuls Technol2022; 43(2): 356–367 (in Chinese).
