Rotating machinery is a linchpin in industrial processes, guaranteeing productivity and safety; however, faults like imbalance and misalignment jeopardize efficiency and reliability. Efficient condition monitoring, mainly via vibration analysis, is pivotal in preserving machinery performance and mitigating expensive operational disruptions. This research presents an innovative method for identifying compound imbalance-misalignment faults, which are frequently encountered yet often underestimated in industrial settings due to the intricacies involved in their detection. To tackle this challenge, the proposed methodology employs a novel Bessel transform for time-frequency domain (TFD) analysis and advanced nonlinear TFD features known as HU descriptors. A multidomain feature fusion strategy synthesizes comprehensive fault information, incorporating time, frequency, and TFD features. Additionally, feature selection using FA-based methods is employed to reduce the dimensionality of the feature space and enhance fault identification accuracy. Finally, a BiLSTM network is deployed to classify the features accurately and identify the faults. Through rigorous testing in a case study, the proposed methodology achieves a remarkable fault identification accuracy. This research offers a robust framework for addressing compound faults, significantly contributing to fault diagnosis in industrial settings.
ZhangZWangYWangK.Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network. J Intell Manuf2013; 24(6): 1213–1227.
2.
BarshikarRRBaviskarPR.Evaluation of performance of vibration signatures for condition monitoring of worm gearbox by using ANN. Int J Interact Design Manuf2023; 18(10): 7291–7304.
3.
ShaoSMcAleerSYanR, et al. Highly accurate machine fault diagnosis using deep transfer learning. IEEE Trans Indus Inform2019; 15(4): 2446–2455.
4.
Saucedo-DorantesJJDelgado-PrietoMOsornio-RiosRA, et al. Diagnosis methodology for identifying gearbox wear based on statistical time feature reduction. Proc IMechE, Part C: J Mechanical Engineering Science2018; 232(15): 2711–2722.
5.
UpadhyayNKankarPK.Diagnosis of bearing defects using tunable Q-wavelet transform. J Mech Sci Technol2018; 32(2): 549–558.
6.
HanHChoSKwonS, et al. Fault diagnosis using improved complete ensemble empirical mode decomposition with adaptive noise and power-based intrinsic mode function selection algorithm. Electronics (Switzerland)2018; 7(2): 16.
7.
InturiVSabareeshGRSupradeepanK, et al. Integrated condition monitoring scheme for bearing fault diagnosis of a wind turbine gearbox. J Vibr Control2019; 25(12): 1852–1865.
8.
ZhangXZhangQChenM, et al. A two-stage feature selection and intelligent fault diagnosis method for rotating machinery using hybrid filter and wrapper method. Neurocomputing2018; 275: 2426–2439.
9.
XueYDouDYangJ.Multi-fault diagnosis of rotating machinery based on deep convolution neural network and support vector machine. Measurement2020; 156: 107571.
10.
YiZPanNGuoY.Mechanical compound faults extraction based on improved frequency domain blind deconvolution algorithm. Mech Syst Signal Proc2018; 113: 180–188.
11.
WangLLiuZMiaoQ, et al. Time – frequency analysis based on ensemble local mean decomposition and fast kurtogram for rotating machinery fault diagnosis. Mech Syst Signal Proc2018; 103: 60–75.
12.
ZhangYXingKBaiR, et al. An enhanced convolutional neural network for bearing fault diagnosis based on time–frequency image. Measurement2020; 157: 107667.
13.
FengZLiangMChuF.Recent advances in time – frequency analysis methods for machinery fault diagnosis: a review with application examples. Mech Syst Signal Proc2013; 38(1): 165–205.
14.
CaiJHChenQY.Bearing fault diagnosis method based on local mean decomposition and wigner higher moment spectrum. Exp Techn2016; 40(5): 1437–1446.
15.
RajagopalanSRestrepoJAAllerJM, et al. Nonstationary motor fault detection using recent quadratic time-frequency representations. IEEE Trans Indus Appl2008; 44(3): 735–744.
16.
IbrahimGRAlbarbarA.Comparison between Wigner-Ville distribution- and empirical mode decomposition vibration-based techniques for helical gearbox monitoring. Proc IMechE, Part C: J Mechanical Engineering Science2011; 225(8): 1833–1846.
17.
RexFMTAndrewsAKrishnakumariA, et al. A hybrid approach for fault diagnosis of spur gears using HU. Metrol Meas Syst2020; 27(3): 451–464.
18.
MouraMMMAnaLGraçaRM.Fast calculation of the bessel time-frequency distribution. IFAC Proc Vol2002; 35(1): 321–325.
19.
TangZWangMOuyangT, et al. A wind turbine bearing fault diagnosis method based on fused depth features in time–frequency domain. Energy Rep2022; 8: 12727–12739.
20.
SunYWangW.Role of image feature enhancement in intelligent fault diagnosis for mechanical equipment: a review. Eng Fail Anal2024; 156: 107815.
21.
KumarDPMuralidharanVRavikumarS.Histogram as features for fault detection of multi point cutting tool – a data driven approach. Appl Acoust2022; 186: 108456.
22.
ChenJZhouDWangY, et al. Image feature extraction based on HOG and its application to fault diagnosis for rotating machinery. J Intell Fuzzy Syst2018; 34: 3403–3412.
23.
YanSJinLZhangZ, et al. Research on fault diagnosis of transmission line based on SIFT feature. Multimed Tools Appl2022; 81: 569–577.
24.
BarreiroJCastejónMAlegreE, et al. Use of descriptors based on moments from digital images for tool wear monitoring. Int J Mach Tools Manuf2008; 48(9): 1005–1013.
25.
HuM-K.Visual pattern recognition by moment invariants. IRE Trans Inform Theory1962; 8(2): 179–187.
26.
LengJ. Analysis of Hu’s moment invariants on image scaling and rotation. In: 2nd International conference on computer engineering and technology (IEEE), Sydney, Australia, 2015, pp. 476–480.
27.
XueYWenCWangZ, et al. A novel framework for motor bearing fault diagnosis based on multi-transformation domain and multi-source data. Knowl Based Syst2024; 283: 111205.
28.
LiuSJiZWangY, et al. Multi-feature fusion for fault diagnosis of rotating machinery based on convolutional neural network. Comput Commun2021; 173: 160–169.
29.
Gang ChengXCHongyuLi, et al. Study on planetary gear fault diagnosis based on entropy feature fusion of ensemble empirical mode decomposition. Measurement2016; 91: 140–154.
30.
YuYKarimiHRShiP, et al. A new multi-source information domain adaption network based on domain attributes and features transfer for cross-domain fault. Mech Syst Signal Proc2024; 211: 111194.
31.
JainIKumarVJainR.Correlation feature selection based improved-Binary Particle Swarm Optimization for gene selection and cancer classification. Appl Soft Comput J2018; 62: 203–215.
32.
TangZBoLLiuX, et al. A semi-supervised transferable LSTM with feature evaluation for fault diagnosis of rotating machinery. Appl Intell2021; 52: 1703–1717.
33.
AthisayamAKondalM.A multi-stage diagnosis method using CEEMD, ABC, and ANN for identifying compound gear-bearing faults. Proc IMechE Part C: J Mechanical Engineering Science2022; 237(8): 2030–2045.
34.
AthisayamAKondalM.A unified approach for compound gear - bearing fault diagnosis using bessel transform, artificial bee colony - based feature selection and LSTM networks. J Vibr Eng Technol2023; 12: 2959–2973.
35.
AthisayamAKondalM.Noise-resilient bearing fault diagnosis using DTW-based IMF selection and wavelet-fused features with the Bat Algorithm. Signal Image Video Proc2025;19: 607.
36.
AthisayamAKondalM.Fault feature selection for the identification of compound gear - bearing faults using firefly algorithm. Int J Adv Manuf Technol2023; 125: 1777–1788.
37.
HuYZhouQGaoJ, et al. Compound fault diagnosis of rolling bearings based on improved tunable Q-factor wavelet transform. Meas Sci Technol2021; 32: 105018.
38.
LyuXHuZZhouH, et al. Application of improved MCKD method based on QGA in planetary gear compound fault diagnosis. Measurement2019; 139: 236–248.
39.
FanJQiYGaoX, et al. Compound fault diagnosis of rolling element bearings using multipoint sparsity – multipoint optimal minimum entropy deconvolution adjustment and adaptive resonance-based signal sparse decomposition. J Vibr Control2020; 27(11–12): 1212–1230.
40.
TangJChengXSunJ, et al. A novel method for untrained detection of compound fault in rolling bearing via fast Fourier Transform-Transformer model. Measurement2025; 253: 117755.
41.
JiangZLiFLiM, et al. Advanced engineering informatics noise-robust compound fault feature extraction of variable speed rotating machinery via an amplitude modulation-driven decomposition framework. Adv Eng Inform2025; 67: 103501.
42.
QinYLiuXLiX, et al. Simulation-data driven generalized zero-shot learning for multi-agent bearing compound fault diagnosis. Knowl Based Syst2025; 318: 113595.
43.
CaoLWangYLiJ, et al. MT-CDGAT: a multi-label diagnosis model for untrained planetary gearbox compound faults based on multi-task cross dynamic graph attention networks. Neurocomputing2025; 639: 130307.
44.
ZhangWHeJMaC, et al. Compound fault diagnosis method of rotating machinery using multi-view multi-label feature selection based on label compression and local label correlation. Adv Eng Inform2025; 65: 103310.
45.
SongBLiuYFangJ, et al. An optimized CNN-BiLSTM network for bearing fault diagnosis under multiple working conditions with limited training samples. Neurocomputing2024; 574: 127284.
MazaSZouacheD. Binary firefly algorithm for feature selection in classification. In: 2019 International conference on theoretical and applicative aspects of computer science (ICTAACS), Skikda, Algeria, 2019, pp. 9–14.
48.
YangX.Firefly algorithm, stochastic test functions and design optimisation. Optim Control2010; 2(2): 1–12.
49.
AliyuI.Selection of optimal wavelet features for epileptic EEG signal classification with LSTM. Neural Comput Appl2023; 35(2): 1077–1097.
