Compressed sensing (CS) is a promising tool for data compression reconstruction. However, fault diagnosis methods for high-speed train bearings based on CS and acoustic emission (AE) technologies have not been reported yet. Notably, the accuracy and speed of CS two-stage reconstruction methods are affected and restricted by prior initial conditions. Therefore, this article proposes adaptive dynamic thresholds applicable to adaptive stepsize forward–backward pursuit (ASFBP), and bearing health state assessment method. First, the adaptive dynamic thresholds for atom selection and deletion are constructed based on the residual feedback mechanism and the atom quality distribution law, which enables ASFBP to realize high-precision rapid reconstruction of signal without any atom priori initial conditions. Second, the initial dictionary length is improved based on the AE hit characteristics. Furthermore, a damage state comprehensive evaluation index (DSCEI) is established using principal component analysis based on AE time-domain hit parameters and compression-domain energy parameter. Compared with the kurtosis index and permutation entropy index, the DSCEI demonstrates better monotonicity and stability in the quantitative evaluation of high-speed train bearing condition. Finally, the validity and stability of the method are verified by testing under complex test conditions resembling actual high-speed train lines, providing valuable insights for the CS-based data-driven bearing fault diagnosis.
QiHHanDHouD, et al. A novel acoustic emission sensor design and modeling method for monitoring the status of high-speed train bearings. Struct Health Monit2023: 22(6): 3761–3784.
2.
LiCLuoKYangL, et al. A zero-shot fault detection method for UAV sensors based on a novel CVAE-GAN model. IEEE Sens J2024: 24(12): 1–1.
3.
ManJDongHYangX, et al. GCG: graph convolutional network and gated recurrent unit method for high-speed train axle temperature forecasting. Mech Syst Signal Process2022; 163: 108102.
4.
HouDQiHWangC, et al. High-speed train wheel set bearing fault diagnosis and prognostics: fingerprint feature recognition method based on acoustic emission. Mech Syst Signal Process2022; 171: 108947.
5.
WangJMaXQiuQ, et al. A hybrid inspection-replacement policy for multi-stage degradation considering imperfect inspection with variable probabilities. Reliab Eng Syst Safe2023; 241: 109629.
6.
MahajanHBanerjeeS.Acoustic emission source localisation for structural health monitoring of rail sections based on a deep learning approach. Meas Sci Technol2023; 34(4): 044010.
7.
YoshiokaTFujiwaraT.Application of acoustic emission technique to detection of rolling bearing failure. Am Soc Mech Eng1984; 14(1): 55–76.
8.
EftekharnejadBCarrascoMRCharnleyB, et al. The application of spectral kurtosis on acoustic emission and vibrations from a defective bearing. Mech Syst Signal Process2011; 25(1): 266–284.
9.
MahajanHBanerjeeS.Quantitative investigation of acoustic emission waveform parameters from crack opening in a rail section using clustering algorithms and advanced signal processing. Sensors2022; 22(22): 8643.
10.
HouDQiHLuoH, et al. Comparative study on the use of acoustic emission and vibration analyses for the bearing fault diagnosis of high-speed trains. Struct Health Monit2022; 21(4): 1518–1540.
11.
KannanVDaoDVLiH.An information fusion approach for increased reliability of condition monitoring with homogeneous and heterogeneous sensor systems. Struct Health Monit2023; 22(3): 1601–1612.
12.
DonohoDL.Compressed sensing. IEEE Trans Inf Theory2006; 52(4): 1289–1306.
13.
CandèsEJTaoT.Decoding by linear programming. IEEE Trans Inf Theory2005; 51(12): 4203–4215.
14.
KhanIXuYKarS, et al. Compressive sensing and morphology singular entropy-based real-time secondary voltage control of multiarea power systems. IEEE Trans Ind Inform2018; 15(7): 3796–3807.
15.
PengYQiaoWQuL.Compressive sensing-based missing-data-tolerant fault detection for remote condition monitoring of wind turbines. IEEE Trans Ind Electron2021; 69(2): 1937–1947.
16.
TangZBaoYLiH.Group sparsity-aware convolutional neural network for continuous missing data recovery of structural health monitoring. Struct Health Monit2021; 20(4): 1738–1759.
17.
BaoYTangZLiH.Compressive-sensing data reconstruction for structural health monitoring: a machine-learning approach. Struct Health Monit2020; 19(1): 293–304.
18.
LiuCWuXMaoJ, et al. Acoustic emission signal processing for rolling bearing running state assessment using compressive sensing. Mech Syst Signal Process2017; 91: 395–406.
19.
BaoYShiZWangX, et al. Compressive sensing of wireless sensors based on group sparse optimization for structural health monitoring. Struct Health Monit2018; 17(4): 823–836.
20.
SawantSBanerjeeSTallurS.Performance evaluation of compressive sensing based lost data recovery using OMP for damage index estimation in ultrasonic SHM. Ultrasonics2021, 115: 106439.
21.
ChengZLuZ.Two novel reconstruction methods of sparsity adaptive adjustment for road roughness compressive signal based on I-SA and GSM. Mech Syst Signal Process2022; 171: 108915.
22.
ZhangGMZhangCZHarveyDM.Sparse signal representation and its applications in ultrasonic NDE. Ultrasonics2012; 52(3): 351–363.
23.
KimTLeeGYounBD.PHM experimental design for effective state separation using Jensen–Shannon divergence. Reliab Eng Syst Safe2019; 190: 106503.
24.
MallatSGZhangZ.Matching pursuits with time-frequency dictionaries. IEEE Trans Signal Process1993; 41(12): 3397–3415.
25.
TroppJAGilbertAC.Signal recovery from random measurements via orthogonal matching pursuit. IEEE Trans Inform Theory2007; 53(12): 4655–4666.
26.
WangJKwonSShimB.Generalized orthogonal matching pursuit. IEEE Trans Signal Process2012; 60(12): 6202–6216.
27.
NeedellDVershyninR.Uniform uncertainty principle and signal recovery via regularized orthogonal matching pursuit. Found Comput Math2009; 9: 317–334.
28.
LiFHongSGuY, et al. An optimization-oriented algorithm for sparse signal reconstruction. IEEE Signal Process Lett2019; 26(3): 515–519.
29.
DaiWMilenkovicO.Subspace pursuit for compressive sensing signal reconstruction. IEEE Trans Inform Theory2009; 55(5): 2230–2249.
30.
NeedellDTroppJA.CoSaMP: iterative signal recovery from incomplete and inaccurate samples. Appl Comput Harmon A2009; 26(3): 301–321.
31.
SuLTanSQiY, et al. An improved orthogonal matching pursuit method for denoising high-frequency ultrasonic detection signals of flip chips. Mech Syst Signal Process2023; 188: 110030.
32.
DoTTGanLNguyenN, et al. Sparsity adaptive matching pursuit algorithm for practical compressed sensing. In 42nd Asilomar conference on signals, systems and computers, Pacific Grove, CA, 26-29 October 2008, pp. 581–587. Piscataway, NJ: IEEE Press.
33.
WangCZhangYSunL, et al. Improved sparsity adaptive matching pursuit algorithm based on compressed sensing. Displays2023; 77: 102396.
34.
KarahanogluNBErdoganH.Compressed sensing signal recovery via forward–backward pursuit. Digit Signal Process2013; 23(5): 1539–1548.
35.
AzizAOsamyWKhedrAM, et al. Iterative selection and correction based adaptive greedy algorithm for compressive sensing reconstruction. J King Saud Univ Comput Inf Sci2022; 34(3): 892–900.
36.
PanZMengZZhangY, et al. High-precision bearing signal recovery based on signal fusion and variable stepsize forward-backward pursuit. Mech Syst Signal Process2021; 157: 107647.
37.
LvCMaJLiuH, et al. Fault diagnosis and prognostics based on cognitive computing and geometric space transformation. Beijing, China: National Defense Industry Press, 2021.
38.
ChangYHWangWChangJY, et al. Compressed sensing for OMA using full-field vibration images. Mech Syst Signal Process2019; 129: 394–406.
39.
AharonMEladMBrucksteinA.K-SVD: an algorithm for designing overcomplete dictionaries for sparse representation. IEEE Trans Signal Process2006; 54(11): 4311–4322.
40.
DuZChenXZhangH, et al. Learning collaborative sparsity structure via nonconvex optimization for feature recognition. IEEE Trans Ind Inform2017; 14(10): 4417–4430.
41.
JolliffeIT.Principal component snalysis. New York, NY: Springer, 2002.
42.
LeiYLiNLinJ.A new method based on stochastic process models for machine remaining useful life prediction. IEEE Trans Instrum Meas2016; 65(12): 2671–2684.
43.
TianYWangZLuC.Self-adaptive bearing fault diagnosis based on permutation entropy and manifold-based dynamic time warping. Mech Syst Signal Process2019; 114: 658–673.
