Blade crack detection is the key to ensuring the smooth and safe operation of centrifugal fans. However, a single vibration signal is difficult to fully reflect the health state of the blade and is susceptible to noise interference in the industrial field, which makes it difficult to detect blade cracks. Therefore, a two-level fusion model of vibro-acoustic signals is proposed for blade crack detection of centrifugal fans. Firstly, based on the designed correlated degree of cyclostationarity fusion rule, the data-level fusion of multi-source homogeneous vibro-acoustic signals is completed, and the fused signals with more obvious fault features are obtained. Then, a one-dimensional feature pyramid network is proposed to extract the vibro-acoustic features and generate initial decisions. Finally, a basic probability assignment acquisition method based on the precision of the initial classifiers and a weighted average method based on the Pignistic probability distance are proposed to minimize the conflict between multi-source evidence, and the Dempster-Shafer evidence theory method is used to obtain the blade crack detection results. The effectiveness of the proposed method is verified by the centrifugal fan blade crack detection experiments. Compared with other related methods, the proposed method has better detection performance and stronger robustness.
SongDShenJMaT, et al. Multi-objective acoustic sensor placement optimization for crack detection of compressor blade based on reinforcement learning. Mech Syst Signal Process2023; 197: 110350.
2.
MaTSongDShenJ, et al. Blade crack detection using variational model decomposition and time-delayed feedback nonlinear tri-stable stochastic resonance. Struct Health Monit2023; 22(2): 1478–1493.
3.
SongDXuFMaT. Crack damage monitoring for compressor blades based on acoustic emission with novel feature and hybridized feature selection. Struct Health Monit2022; 21(6): 2641–2656.
4.
SongDXuFHuJ, et al. Fault feature recognition of centrifugal compressor with cracked blade based on SNR estimation and adaptive stochastic resonance. Struct Health Monit2023; 22(1): 131–150.
5.
MaTXuFHuJ, et al. Double Gaussian potential stochastic resonance method and its application in centrifugal fan blade crack detection. Chinese J Phys2021; 74: 279–295.
6.
WengCLuBGuQ, et al. A novel multisensor fusion transformer and its application into rotating machinery fault diagnosis. IEEE Trans Instrum Meas2023; 72: 1–12.
7.
HuangZLiuJ. A joint vibro-acoustic method for periodic track short-wave defect identification. Appl Acoust2023; 204: 109239.
8.
ZhangTXuFJiaM. A centrifugal fan blade damage identification method based on the multi-level fusion of vibro-acoustic signals and CNN. Measurement2022; 199: 111475.
9.
SongDMaTLiY, et al. Data and decision level fusion-based crack detection for compressor blade using acoustic and vibration signal. IEEE Sens J2022; 22(12): 12209–12218.
10.
WangXMaoDLiX. Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network. Measurement2021; 173: 108518.
11.
MaMSunCChenX. Deep coupling autoencoder for fault diagnosis with multimodal sensory data. IEEE Trans Ind Inform2018; 14(3): 1137–1145.
12.
LuPDaiF. An overview of multi-sensor information fusion. In: 2021 6th International conference on intelligent informatics and biomedical sciences (ICIIBMS), Oita, Japan, 2021, pp. 5–9.
13.
JaramilloVOttewillJDudekR, et al. Condition monitoring of distributed systems using two-stage Bayesian inference data fusion. Mech Syst Signal Process2017; 87: 91–110.
14.
ZhengZQiuHWangZ, et al. Data fusion based multi-rate Kalman filtering with unknown input for on-line estimation of dynamic displacements. Measurement2019; 131: 211–218.
15.
LiZWangDDeyN, et al. Plantar pressure image fusion for comfort fusion in diabetes mellitus using an improved fuzzy hidden Markov model. Biocybern Biomed Eng2019; 39(3): 742–752.
16.
GaoSZhongYLiW. Random weighting method for multisensor data fusion. IEEE Sens J2011; 11(9): 1955–1961.
17.
GaoSZhongY. Random weighting estimation of kernel density. J Stat Plan Infer2010; 140(9): 2403–2407.
18.
YuHLiHLiY. Vibration signal fusion using improved empirical wavelet transform and variance contribution rate for weak fault detection of hydraulic pumps. ISA Trans2020; 107: 385–401.
19.
WenPLiYChenS, et al. Remaining useful life prediction of IIoT-enabled complex industrial systems with hybrid fusion of multiple information sources. IEEE Internet Things2021; 8(11): 9045–9058.
20.
GuanYMengZSunD, et al. 2MNet: Multi-sensor and multi-scale model toward accurate fault diagnosis of rolling bearing. Reliab Eng Syst Safe2021; 216: 108017.
21.
JiangW and W. Hu, An improved soft likelihood function for Dempster–Safer belief structures. Int J Intell Syst2018; 33(6): 1264–1282.
22.
ZadehL. A note on Z-numbers. Inf Sci2011; 181(14): 2923–2932.
23.
DengXJiangW. A total uncertainty measure for D numbers based on belief intervals. Int J Intell Syst2019; 34(12): 3302–3316.
GaryHRaniD. Some results on information measures for complex intuitionistic fuzzy sets. Int J Intell Syst2019; 34(10): 2319–2363.
26.
YuCYangJYangD, et al. An improved conflicting evidence combination approach based on a new supporting probability distance. Expert Syst Appl2015; 42(12): 5139–5149.
27.
YagerR. On the dempster-shafer framework and new combination rules. Inf Sci1987; 41(2): 93–137.
28.
FloreaMJousselmeABosséÉ, et al. Robust combination rules for evidence theory. Inf Fusion2009; 10(2): 183–197.
29.
LefèvreEElouediZ. How to preserve the conflict as an alarm in the combination of belief functions. Decis Support Syst2013; 56: 326–333.
30.
MurphyC. Combining belief functions when evidence conflicts. Decis Support Syst2000; 29(1): 1–9.
31.
JousselmeAGrenierDBosséÉ. A new distance between two bodies of evidence. Inf Fusion2001; 2(2): 91–101.
32.
LiuW. Analyzing the degree of conflict among belief functions. Artif Intell2006; 170(11): 909–924.
33.
DengYShiWZhuZ, et al. Combining belief functions based on distance of evidence. Decis Support Syst2004; 38(3): 489–493.
34.
DempsterA. Upper and lower probabilities induced by a multivalued mapping. The Annals of Mathematical Statistics1967; 38(2): 325–339.
35.
ShaferG. A mathematical theory of evidence. Int J Approx Reason2016; 79: 667–672.
36.
JiangMChenJQinK. Performance for time-varying amplitude modulation signal using cyclostationary approach. J Shanghai Jiaotong Univ2001; 35(12): 1798–1801.
37.
ŽivanovićGGardnerW. Degrees of cyclostationarity and their application to signal detection and estimation. Signal Process1991; 22(3): 287–297.
38.
LuoCMoZMiaoQ. Cyclic harmonic ratio defined in squared envelope spectrum and log-envelope spectrum for gearbox fault diagnosis. IEEE Trans Instrum Meas2020; 69: 9568–9577.
39.
BorghesaniPShahriarMR. Cyclostationary analysis with logarithmic variance stabilisation. Mech Syst Signal Process2016; 70–71: 51–72.
40.
YuanCZhangJCChenL, et al. Timber moisture detection using wavelet packet decomposition and convolutional neural network. Smart Mater Struct2021; 30: 035022.
41.
KongQZJiKYGuJX, et al. A CNN-integrated percussion method for detection of FRP-concrete interfacial damage with FEM reconstruction. Struct Health Monit2023; 22(1): 216–231.
42.
FuJLiWDuJ, et al. A multiscale residual pyramid attention network for medical image fusion. Biomed Signal Process Control2021; 66: 102488.
43.
LiSWangHSongL, et al. An adaptive data fusion strategy for fault diagnosis based on the convolutional neural network. Measurement2020; 165: 108122.
44.
LiuYChengYZhangZ, et al. Multi-information fusion fault diagnosis based on KNN and improved evidence theory. J Vib Eng Technol2022; 10(3): 841–852.
