Electric motors are primary actuators in modern manufacturing, and timely diagnosis of motor faults is crucial for ensuring production safety, improving parts quality, and controlling maintenance costs. Research on data-driven fault diagnosis approaches plays a critical role in the effective utilization of motor monitoring information. However, early failure signal of motors is faint and often coupled with a significant amount of noise, making it necessary to develop advanced data enhancement techniques. Thus, this study develops a novel diagnostic model that integrates band-adaptive adaptive chirp mode decomposition (BAACMD) and multi-stage cyclic kinematic deconvolution (MCKD) methods. Specifically, BAACMD is used to adaptively decompose fault signals, effectively removing noise and isolating the relevant fault features. Then, MCKD is employed to enhance the periodicity and cyclic behavior of fault data, making fault characteristics more distinguishable. Finally, a convolutional neural network is used to categorize enhanced fault features, improving diagnostic accuracy. We evaluated our proposed approach’s performance on the motor bearing dataset and compared it to other cutting-edge techniques. Results show that our method outperforms existing deep learning methods in terms of fault diagnosis accuracy and robustness.
YangYHaqueMMMBaiD, et al. Fault diagnosis of electric motors using deep learning algorithms and its application: a review. Energies2021; 14(21): 7017.
2.
GlowaczA.Thermographic fault diagnosis of electrical faults of commutator and induction motors. Eng Appl Artif Intell2023; 121: 105962.
3.
GundewarSKKanePV.Condition monitoring and fault diagnosis of induction motor. J Vibr Eng Technol2021; 9: 643–674.
4.
LangWHuYGongC, et al. Artificial intelligence-based technique for fault detection and diagnosis of EV motors: a review. IEEE Trans Transp Electrif2021; 8(1): 384–406.
5.
NiuGDongXChenY.Motor fault diagnostics based on current signatures: a review. IEEE Trans Instrum Meas2023; 72: 1–19.
6.
XuFDingNLiN, et al. A review of bearing failure modes, mechanisms and causes. Eng Fail Anal2023; 152: 107518.
7.
TahmasbiDShiraliHSouqSSMN, et al. Diagnosis and root cause analysis of bearing failure using vibration analysis techniques. Eng Fail Anal2024; 158: 107954.
8.
DaiPLiangXWangJ, et al. Mathematical model for mesh analysis of gear pair in gear-shaft-bearing systems with localized failure on raceway. J Sound Vibr2024; 584: 118458.
9.
SahuDDewanganRKMatharuSPS. An investigation of fault detection techniques in rolling element bearing. J Vibr Eng Technol2024; 12(4): 5585–5608.
10.
HuangXHanYYanJ, et al. Hybrid forecasting model of building cooling load based on EMD-LSTM-Markov algorithm. Energy Build2024; 321: 114670.
11.
WangSTianJLiangP, et al. Single and simultaneous fault diagnosis of gearbox via wavelet transform and improved deep residual network under imbalanced data. Eng Appl Artif Intell2024; 133: 108146.
12.
YiCZhangWCaoH, et al. Cyclostationary harmonic product spectrum with its application for rolling bearing fault resonance frequency band adaptive location. Expert Syst Appl2024; 254: 124453.
13.
JayakumarEPSathideviPS.An integrated acoustic echo and noise cancellation system using cross-band adaptive filters and wavelet thresholding of multitaper spectrum. Appl Acoust2018; 141: 9–18.
14.
BharathiSLKThanigaivelanVShenbagaramanS, et al. Hybrid EVO-CFNN approach for improve voltage stability of distribution system performance using superconducting magnetic energy storages inter linked with wind turbine. J Energy Storage2025; 112: 115465.
15.
DuanX.Settlement prediction of Nanjing Metro Line 10 with HOA-VMD-LSTM. Measurement2025; 244: 116477.
16.
XuYHuangXZhengX, et al. VMD-ATT-LSTM electricity price prediction based on grey wolf optimization algorithm in electricity markets considering renewable energy. Renew Energy2024; 236: 121408.
17.
KarAShobaSBurraS, et al. Adaptive tap-length based sub-band mean M-estimate filtering for active noise cancellation. Circ Syst Signal Proc2024; 43: 5912–5932.
18.
DingJWangYQinY, et al. Deep time–frequency learning for interpretable weak signal enhancement of rotating machineries. Eng Appl Artif Intell2023; 124: 106598.
19.
ZhangSWangTWordenK, et al. Canonical-correlation-based fast feature selection for structural health monitoring. Mech Syst Signal Proc2025; 223: 111895.
20.
ChamlalHOuaderhmanTAaboubF.A graph based preordonnances theoretic supervised feature selection in high dimensional data. Knowl Based Syst2022; 257: 109899.
21.
Di MauroMGalatroGFortinoG, et al. Supervised feature selection techniques in network intrusion detection: a critical review. Eng Appl Artif Intell2021; 101: 104216.
22.
HanTZhangLYinZ, et al. Rolling bearing fault diagnosis with combined convolutional neural networks and support vector machine. Measurement2021; 177: 109022.
23.
WangMChenYZhangX, et al. Roller bearing fault diagnosis based on integrated fault feature and SVM. J Vibr Eng Technol2021; 10: 853–862.
24.
JogdeoAAPatangeADAtnurkarAM, et al. Robustification of the random forest: a multitude of decision trees for fault diagnosis of face milling cutter through measurement of spindle vibrations. J Vibr Eng Technol2024; 12(3): 4521–4539.
25.
SoaresJLLCostaTBMouraLS, et al. Fault diagnosis of belt conveyor idlers based on gradient boosting decision tree. Int J Adv Manuf Technol2024; 132: 3479–3488.
26.
GuJPengYLuH, et al. A novel fault diagnosis method of rotating machinery via VMD, CWT and improved CNN. Measurement2022; 200: 111635.
27.
LiuXZhangZMengF, et al. Fault diagnosis of wind turbine bearings based on CNN and SSA–ELM. J Vibr Eng Technol2023; 11(8): 3929–3945.
28.
NiuZZhongGYuH.A review on the attention mechanism of deep learning. Neurocomputing2021; 452: 48–62.
29.
GuoMXuTLiuJ, et al. Attention mechanisms in computer vision: a survey. Comput Visual Media2022; 8: 331–368.
30.
MaZLuFLiuS, et al. A parameter-adaptive ACMD method based on particle swarm optimization algorithm for rolling bearing fault diagnosis under variable speed. J Mech Sci Technol2021; 35(5): 1851–1865.
31.
WangX.Compound fault diagnosis of rolling bearing based on ACMD, Gini Index Fusion and AO-LSTM. Symmetry2021; 13(12): 2386.
32.
ShiJWangFHuangY, et al. Rolling bearing fault diagnosis under strong background noise based on ACMD and optimized MOMEDA. J Sensors2024; 2024: 3293579.
33.
KeZLiuHShiJ, et al. Fault diagnosis method of weak vibration signal based on improved VMD and MCKD. Meas Sci Technol2024; 35: 025113.
34.
ZhouJWuZDuanZ, et al. Application of the hybrid integration displacement algorithm based on CEEMDAN and wavelet threshold denoising in vibration screening equipment. Meas Sci Technol2025; 36(1): 016194.
35.
WangXWangYSuX, et al. Deep reinforcement learning-based air combat maneuver decision-making: literature review, implementation tutorial and future direction. Artif Intell Rev2024; 57(1): 1.
36.
WuRQinKFangY, et al. Application of CNN in the diagnosis for the invasion depth of gastrointestinal cancer: a systematic review and meta-analysis. J Gastrointest Surg2024; 28(4): 538–547.
37.
LyuXHuZZhouH, et al. Application of improved MCKD method based on QGA in planetary gear compound fault diagnosis. Measurement2019; 139: 236–248.
38.
ZhangXYangYLiuJ, et al. A CNN-BILSTM monthly rainfall prediction model based on SCSSA optimization. J Water Clim Change2024; 15(22): 4862–4876.
39.
GeHYanZYuW, et al. An attention mechanism based convolutional LSTM network for video action recognition. Multimed Tools Appl2019; 78: 20533–20556.
