Fault diagnosis is important in monitoring the entire lifecycle of mechanical equipment. And Feature selection can explain the relationships between different fault types and reduce the complexity of the fault diagnosis model. However, due to the correlation among the fault features, a single method is unable to effectively determine the importance of the features. In order to enhance the analytical ability of the feature selection for features and thereby improve the universality of the method, this paper proposes a new feature analysis method – the multi-factor dual analysis method. This method is designed to conduct in-depth analysis of the fault data and utilize statistical methods to determine the optimal ranking of feature importance. By testing on different fault data sets, it has been proved that this method can effectively reduce the feature dimension while maintaining the classification accuracy.
ShaalanAAMeftehWFrihidaAM.Review on deep learning classifiers for faults diagnosis of rotating industrial machinery. Serv Oriented Comput Appl2024; 18(4): 361–379.
2.
QianQZhangBLiC, et al. Federated transfer learning for machinery fault diagnosis: a comprehensive review of technique and application. Mech Syst Signal Process2025; 223: 111837.
3.
WaqasPKCheolYB.A review of machine learning techniques for wind turbine’s fault detection, diagnosis, and prognosis. Int J Green Energy2024; 21(4): 771–786.
4.
MataniaODattnerIBortmanJ, et al. A systematic literature review of deep learning for vibration-based fault diagnosis of critical rotating machinery: limitations and challenges. J Sound Vib2024; 590: 118562.
5.
PuntambekarRVyasPThakkarA, et al. A survey of machine learning and deep learning methods for vibration-based bearing fault diagnosis: the need, challenges, and potential future research directions. Neurocomputing2026; 659: 131628.
6.
WangYDuX.Rolling bearing fault diagnosis based on SCNN and optimized HKELM. Mathematics2025; 13(12): 2004.
7.
CaoYSunYLiP, et al. Vibration-based fault diagnosis for railway point machines using multi-domain features, ensemble feature selection and SVM. IEEE Trans Veh Technol2024; 73(1): 176–184.
8.
SunYCaoYLiP, et al. Vibration-based fault diagnosis for railway point machines using VMD and multiscale fluctuation-based dispersion entropy. Chin J Electron2024; 33(3): 803–813.
9.
VenkateshBAnuradhaJ.A review of feature selection and its methods. Cybern Inf Technol2019; 19(1): 3–26.
10.
LiCYangXNiX, et al. Urban waterlogging susceptibility assessment based on feature selection optimization and interpretable machine learning. J Environ Manage2025; 393: 127126.
11.
XuZYuZNingX, et al. Characteristics prediction and optimization for fan duct surface heat exchanger using regional heat transfer correlation and NSWOA aided by Sobol. Case Stud Therm Eng2025; 73: 106563.
12.
ChaturvediASarmaMChaturvediKS.Assessing fault severity in power converters with multiple component degradation using random forest regressor and statistical feature analysis. Int J Syst Assur Eng Manag. Epub ahead of print 2 September 2025. DOI: 10.1007/s13198-025-02921-2.
13.
LiuWLingQHanF, et al. Feature selection based on multimodal multi-objective particle swarm optimization and prior information. Pattern Anal Appl2025; 28(4): 181.
14.
CuiCJiangHZhangX, et al. Three-stage feature selection and fault diagnosis method of gearbox based on MOBPSO algorithm parallel optimization. Eng Res Express2025; 7(4): 045541.
15.
MaheshwariDKelkarTFrancisS.An optimized hybrid deep learning based approach for brain tumor classification. Biomed Signal Process Control2026; 113(Part B): 108935.
16.
PriceDMirlyFDeHartM.Uncertainty quantification and sensitivity analysis for SPERT III E-core reactivity measurement benchmarking. Nucl Eng Technol2025; 57(12): 103792.
17.
MenZHuCLiY, et al. A hybrid intelligent gearbox fault diagnosis method based on EWCEEMD and whale optimization algorithm-optimized SVM. Int J Struct Integr2023; 2: 322–336.
18.
YangQWangHYangC, et al. Research on surrogate models and optimization algorithms of compressor characteristic based on digital twins. J Eng Res2025; 13(2): 962–974.
19.
DuYLiuXRenL, et al. Multidimensional feature analysis of Meniere’s disease and vestibular migraine: insights from machine learning and vestibular testing. J Assoc Res Otolaryngol2025; 26(3): 1–14.
20.
SongHWangJWangY, et al. Cancer gene expression data feature selection with ReliefF guided binary Pelican Optimization Algorithm. Eng Lett2025; 33(7): 2309.
21.
MiaoMWuJCaiF, et al. Feature selection for stock movement direction prediction using sparse support vector machine. Appl Stoch Models Bus Ind2025; 41(3): e70011.
22.
DuttaLPParthibanTKNathI, et al. Physico-chemical and thermochemical profiling of Mulberry (Morus spp.) clones for sustainable bioenergy application: a PCA-based selection approach for sustainable bioenergy application. Int J Environ Clim Change2025; 15(8): 465–484.
23.
JiCTaoTWangJ, et al. Dynamic process monitoring based on integrated statistic of principal component analysis and slow feature analysis. IFAC Pap OnLine2022; 55(7): 655–660.
24.
XiaQZhouDYeG, et al. Numerical simulation and optimization of dynamic characteristics of a bi-directional relief valve for vehicle shock absorbers. Flow Meas Instrum2025; 104: 102871.
25.
Sobol’IMMyshetskayaEE.Monte Carlo estimators for small sensitivity indices. Monte Carlo Methods Appl2008; 13(5–6): 455–465.
26.
YagdjianHLecompagnonJHirschP, et al. Optimization of thermal shock response spectrum as infrared thermography post-processing methodology using Latin hypercube sampling and analytical thermal N-layer model. Infrared Phys Technol2024; 143: 105582.
27.
TangHWangHLiC.Explainable fault diagnosis method based on statistical features for gearboxes. Eng Appl Artif Intell2025; 148: 110503.
28.
SmithAWRandallBR.Rolling element bearing diagnostics using the Case Western Reserve University data: a benchmark study. Mech Syst Signal Process2015; 64–65: 100–131.
29.
YangQZhangJWangH, et al. A novel feature reconstruction method for compound fault diagnosis based on vibration signal information. Proc Inst Mech Eng Part D: J Automob Eng. Epub ahead of print 1 September 2025. DOI: 10.1177/09544070251363785.
30.
QianCYangZHeJ, et al. An uneven maximum classifier discrepancy rolling bearing transfer fault diagnosis method combining GCN and KAN. Meas Sci Technol2025; 36(12): 126105.
31.
WuJShanYWeiS, et al. VMD-FastICA denoising combined with adaptive GCN learning for rolling bearing fault diagnosis. J Gun Launch Control2025; 47(01): 1–8.
