The diagnosis of bearings is greatly difficult due to strong background noise and complex transmission paths. So, we designed an aviation gas turbine engine bearings fault diagnosis method. It is based on the combination of Wavelet packet decomposition (WPD) and correlation coefficient-energy ratio-kurtosis criterion judgments with AO-PNN, a probabilistic neural network (PNN) optimized by introducing the Aquila optimizer (AO). The vibration signal is firstly decomposed by WPD and reconstructed by screening Node components by correlation coefficient-energy ratio-kurtosis criterion judgment. The overlapping segmentation of reconstructed signals and the multi-scale permutation entropy of each sample are calculated as the feature vector and reduced by Kernel principal component analysis. AO-PNN is used for fault classification of fault patterns. The experimental results show that this method can effectively eliminate the interference of background noise as to improve the accuracy of fault diagnosis. Compared with the non-optimized PNN, the accuracy is improved by 11.25%.
TakoutsingPRenéWOuhroucheM, et al. Wind turbine condition monitoring: state-of-the-art review, new trends, and future challenges. Energies2014; 7(4): 2595–2630.
2.
LiXYangYHuN, et al. Discriminative manifold random vector functional link neural network for rolling bearing fault diagnosis. Eur J Med Chem2021; 211: 211–211.
3.
LiuWYGaoQWYeG, et al. A novel wind turbine bearing fault diagnosis method based on Integral Extension LMD. Measurement2015; 74: 70–77.
4.
YanXJiaM.Application of CSA-VMD and optimal scale morphological slice bispectrum in enhancing outer race fault detection of rolling element bearings. Mech Syst Signal Process2019; 122: 56–86.
5.
WenLLiXGaoL, et al. A new convolutional neural network-based data-driven fault diagnosis method. IEEE Trans Ind Electron2017; 65(7): 5990–5998.
6.
JuniorRAreiasICamposMM, et al. Fault detection and diagnosis in electric motors using 1d convolutional neural networks with multi-channel vibration signals. Measurement2022; 190: 110759–110788.
7.
PengDLiuZWangH, et al. A novel deeper one-dimensional CNN with residual learning for fault diagnosis of wheelset bearings in high-speed trains. IEEE Access2018; 7: 10278–10293.
8.
PayaBAEsatIIBadiM.Artificial neural network based fault diagnostics of rotating machinery using wavelet transforms as a preprocessor. Mech Syst Signal Process1997; 11(5): 751–765.
9.
LiuJXWenXBYuanLM, et al. A robust approach of watermarking in contourlet domain based on probabilistic neural network. Multimed Tools Appl2016; 76: 24009–24026.
10.
SinghATPrateshJ. Rolling element bearing fault investigation based on translation invariant wavelet means denoising and empirical mode decomposition (EMD). J Inst Eng (India): Series C2024; 105(1): 127–140.
11.
ZhaoCTongBZhouC, et al. Few-shot bearing fault diagnosis method based on an EEMD parallel neural network and a relation network. Adv Mech Eng2024; 16(10). DOI:10.1177/16878132241273535
12.
XiangJZhongY.A novel personalized diagnosis methodology using numerical simulation and an intelligent method to detect faults in a shaft. Appl Sci2016; 6: 414.
13.
TomaNRKimJ.Bearing fault classification of induction motors using discrete wavelet transform and ensemble machine learning algorithms. Appl Sci2020; 10(15): 5251.
14.
PengZKChuFL.Application of the wavelet transform in machine condition monitoring and fault diagnostics: a review with bibliography – ScienceDirect. Mech Syst Signal Process2004; 18(2): 199–221.
15.
YanRGaoRXChenX.Wavelets for fault diagnosis of rotary machines: a review with applications. Signal Process2014; 96: 1–15.
16.
WeiZLiuZGuoZ, et al. Research on an aeroengine bearing fault diagnosis method based on WMSST-CNN-BKA-LSSVM. J Phys2024; 2882(1): 012038.
17.
LuanXLiYXuS, et al. Rolling bearing fault diagnosis method based on wavelet packet transform and CEEMDAN. J Aerospace Power2024; 39(05): 159–173.
18.
YuanLHeYHuangJ, et al. A new neural-network-based fault diagnosis approach for analog circuits by using kurtosis and entropy as a preprocessor. IEEE Trans Instrum Meas2010; 59(3): 586–595.
19.
WangZZhangQXiongJ, et al. Fault diagnosis of a rolling bearing using wavelet packet denoising and random forests. IEEE Sens J2017; 17(17): 5581–5588.
20.
ChenBShenBChenF, et al. Fault diagnosis method based on integration of RSSD and wavelet transform to rolling bearing. Measurement2019; 131: 400–411.
21.
Li-YeZLeiWRu-QiangY.Rolling bearing fault diagnosis based on wavelet packet decomposition and multi-scale permutation entropy. Entropy2015; 17(9): 6447–6461.
22.
ZhangQGaoJDongH, et al. WPD and DE/BBO-RBFNN for solution of rolling bearing fault diagnosis. Neurocomputing2018; 312: 27–33.
23.
DepoldHRGassFD. The application of expert systems and neural networks to gas turbine prognostics and diagnostics. J Eng Gas Turb Power1999; 121(4): 607–612.
24.
StarzykJALiuDLiuZH, et al, Entropy-based optimum test points selection for analog fault dictionary techniques. IEEE Trans Instrum Meas2004; 53(3): 754–761.
25.
LouYKumarAXiangJ. Machinery fault diagnosis based on domain adaptation to bridge the gap between simulation and measured signals. In: IEEE transactions on instrumentation and measurement, vol. 71, pp. 1–9, 2022, Art no. 3514709.
26.
PengSJiangJOuQ, et al. DARTS-based morphological neural network design and application in bearing fault diagnosis. Measurement2024; 234: 114805.
27.
RandallRBAntoniJChobsaardS.The relationship between spectral correlation and envelope analysis in the diagnostics of bearing faults and other cyclostationary machine signals. Mech Syst Signal Process2001; 15(5): 945–962.
28.
WangW.Early detection of gear tooth cracking using the resonance demodulation technique. Mech Syst Signal Process2001; 15(5): 887–903.
29.
AsadiFMollakazemiNJAtyabiSA, et al. Cardiac arrhythmia recognition with robust discrete wavelet-based and geometrical feature extraction via classifiers of SVM and MLP-BP and PNN neural networks. In: 2015 Computing in cardiology conference (CinC), 2015, vol. 10, pp. 933–936. IEEE.
30.
ShaYZhaoJLuanXLiuX, et al. Fault feature signal extraction method for rolling bearings in gas turbine engines based on threshold parameter decision screening. Measurement2024; 231: 114567.
31.
SongTJamshidiMMLeeRR, et al. A modified probabilistic neural network for partial volume segmentation in brain MR image. IEEE Trans Neural2007; 18(5): 1424–1432.
32.
KusyMZajdelR.Probabilistic neural network training procedure based on Q(0)-learning algorithm in medical data classification. Appl Intell2014; 41(3): 837–854.
33.
LiXTMaSYangGSynthesis of difference patterns for monopulse antennas by an improved cuckoo search algorithm. IEEE Antenn Wirel Propagation Lett2016; 16: 141–144.
34.
LeeJHKimJ-WSongJY, et al. A novel memetic algorithm using modified particle swarm optimization and mesh adaptive direct search for PMSM design. IEEE Trans Magn2015; 52(3): 1–4.
35.
ChoiKJangDHKangSI, et al. Hybrid algorithm combing genetic algorithm with evolution strategy for antenna design. IEEE Trans Magn2015; 52(3): 1–4.
36.
XueJKShenB.Dung beetle optimizer: a new meta-heuristic algorithm for global optimization. J Supercomput2022; 79(7): 7305–7336.
37.
ZhaoWWangLMirjaliliS.Artificial hummingbird algorithm: a new bio-inspired optimizer with its engineering applications. Comput Methods Appl Mech Eng2022; 388: 114194.
38.
HuangWZhangG.Bearing fault-detection method based on improved grey wolf algorithm to optimize parameters of multistable stochastic resonance. Sensors (Basel)2023; 23(14): 6529.
39.
CuiHXiaoYHussienAG, et al. Multi-strategy boosted Aquila optimizer for function optimization and engineering design problems. Cluster Comput2024; 27: 7147–7198.
40.
LuanXLeiZLiuX, et al. Fault characterization enhancement method for rolling bearings based on com bination of weighted indicator screening and IMOMEAStruct Health Monit2025. DOI:10.1177/14759217241 310840
41.
LuanXLiYShaY, et al. Rolling bearing fault diagnosis method based on mean singular value screening. J Mech Sci Technol2025; 39: 13–25.
42.
LuanXZhaoJShaY, et al. Rolling bearing state monitoring method based on fusion of multichannel vibration signals with oil debrisinformation. Struct Health Monit2025. DOI 10.1177/14759217241301305
43.
NiuQTongQCaoJ, et al. Feature extraction method for condition monitoring of rolling element bearings based on dual-tree complex wavelet packet transform and VMD. Wireless Pers Commun2018; 103(1): 831–845.
44.
LuanXZhongCZhaoF, et al. Bearing fault damage degree identification method based on SSA VMD and Shannon entropy–exponential entropy decision. Struct Health Monit2024; 23(5): 3105–3133.
45.
FuDLuQTangL, et al. Complementary ensemble empirical mode decomposition and maximum correlated kurtosis deconvolution for wind turbine bearing fault feature extraction. Journal of Physics: Conference Series2023; 2659(1): 012010.
46.
LuanXZhaoJShaY, et al. Multi-channel vibration information weighted fusion for fault feature extraction of rotating machinery main bearings. Mech Syst Signal Pr2025; 228: 112476.
47.
LiDLiMYangL, et al. Rolling bearing fault diagnosis in strong noise background based on vibration signals. Signal ImageVideo P2023;18 (2):1295–1303.
48.
AliJBSaidiLMouelhiA, et al. Linear feature selection and classification using PNN and SFAM neural net-works for a nearly online diagnosis of bearing naturally rogressing degradations, Eng Appl Artif Intel2015; 42: 67–81.
49.
AbualigahLYousriDAbd ElazizM, et al. Aquila optimizer: a novel meta-heuristic optimization algorithm. Comput Ind Eng2021; 157: 107250.
50.
LuanXLiuXLeiZ, et al. Fault feature extration method for rolling bearing in gas turbine engines based on comprehensive dynamic screening. Meas Sci Technol2025. DOI:10.1088/1361-6501/adc325
