Nowadays, acoustic and vibration signals have been widely used to detect crack and its degree on compressor blades for non-destructive evaluation and structural health monitoring. Due to complex working conditions and interference of strong noise, single signal-based methods reach unsatisfactory accuracy. To improve the reliability and accuracy of crack detection, the two-level fusion method based on Mahalanobis distance (MD) and self-attention mechanism is proposed based on multi-acoustic, vibration, and acoustic emission information. First, the MD is calculated to measure the similarity between raw samples and group, which can fuse the same type of samples in data level. Then, the processed raw and data-level fusion samples are inputted to one-dimensional convolutional neural network, and the preliminary decisions are obtained. Finally, the decision-level fusion based on self-attention mechanism and credit assignment is proposed to modify and correct the preliminary decisions. The compressor experiments are implemented to test the proposed method under single and mixed working conditions with strong noise intensity. Further, the results illustrate that the proposed method can accurately detect crack for compressor blades. By comparing with other data fusion approaches, the advantage of the proposed method is validated under complex conditions.
AhsanNRashidAZaidiA, et al. Performance analysis of hydrogen fuel cell with two-stage turbo compressor for automotive applications. Energy Rep2021; 7: 2635–2646.
2.
KhaljaniMVennardAHarrisonJ, et al. Experimental and modelling analysis of efficiency enhancement in a liquid piston gas compressor using metal plate inserts for compressed air energy storage application. J Energy Storage2021; 43: 103240.
3.
XuJQiaoBLiuM, et al. Crack propagation monitoring of rotor blades using synchroextracting transform. J Sound Vib2021; 509: 116253.
4.
LiYXuF. Acoustic emission and moving window-improved kernel entropy component analysis for structural condition monitoring of hoisting machinery under various working conditions. Struct Health Monit2022; 21(4): 1407–1431.
5.
RaniSAgrawalARastogiV. Vibration analysis for detecting failure mode and crack location in first stage gas turbine blade. J Mech Sci Technol2019; 33: 1–10.
6.
XuJFuZHanQ, et al. Micro-cracking monitoring and fracture evaluation for crumb rubber concrete based on acoustic emission techniques. Struct Health Monit2018; 17: 946–958.
7.
HuaZSunZJiaH, et al. Track occupation detection based on a maximum posterior probability model using multi sensor data fusion. Comput Sci Eng2019; 21: 40–54.
8.
KumarPSaimuruganMHaranR, et al. A multi-sensor information fusion for fault diagnosis of a gearbox utilizing discrete wavelet features. Meas Sci Technol2019; 30: 85101.
9.
NooriFRieglerMUddinM, et al. Human activity recognition from multiple sensors data using multi-fusion representations and CNNs. ACM T Multim Comput2020; 16: 1–19.
10.
GunerkarRJalanA. Classification of ball bearing faults using vibro-acoustic sensor data fusion. Exp Techniques2019; 43: 635–643.
11.
DaKLiTZhuY, et al. Recent advances in multisensor multitarget tracking using random finite set. Front Inform Technol Elect Eng2021; 22: 5–24.
12.
GuelNHamamZGodinN, et al. Data merging of AE sensors with different frequency resolution for the detection and identification of damage in oxide-based ceramic matrix composites. Materials2020; 13: 4691.
13.
WenPLiYChenS, et al. Remaining useful life prediction of IIoT-enabled complex industrial systems with hybrid fusion of multiple information sources. IEEE Internet Things J2021; 8: 9045–9058.
14.
GhorbaniSSalahshoorK. Estimating remaining useful life of turbofan engine using data-level fusion and feature-level fusion. J Fail Anal Prev2020; 20: 323–332.
15.
JingLWangTZhaoM, et al. An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox. Sensors-Basel2017; 17: 414.
16.
ZhangQGuJLiuJ, et al. Gearbox fault diagnosis using data fusion based on self-organizing map neural network. Int J Distrib Sens Netw2020; 16: 1–11.
17.
MauryaSSinghVVermaN. Condition monitoring of machines using fused features from EMD-based local energy with DNN. IEEE Sens J2020; 20: 8316–8327.
18.
MengXZhangJXiaoG, et al. Tool wear prediction in milling based on a GSA-BP model with a multisensor fusion method. Int J Adv Manuf Tech2021; 114: 3793–3802.
19.
NasirVKooshkbaghiMCoolJ, et al. Cutting tool temperature monitoring in circular sawing: measurement and multi-sensor feature fusion-based prediction. Int J Adv Manuf Tech2021; 112: 2413–2424.
20.
SegretoTAddonaDTetiR. Tool wear estimation in turning of Inconel 718 based on wavelet sensor signal analysis and machine learning paradigms. Prod Eng-Res Dev2020; 14: 693–705.
21.
YeQLiuSLiuC. A deep learning model for fault diagnosis with a deep neural network and feature fusion on multi-channel sensory signals. Sensors-Basel2020; 20: 4300.
22.
StiefAOttewillJBaranowskiJ, et al. A PCA and two-stage bayesian sensor fusion approach for diagnosing electrical and mechanical faults in induction motors. IEEE T Ind Electron2019; 66: 9510–9520.
23.
TengSChenGLiuZ, et al. Multi-sensor and decision-level fusion-based structural damage detection using a one-dimensional convolutional neural network. Sensors-Basel2021; 21: 3950.
24.
ZhangSLiuTWangC. Multi-source data fusion method for structural safety assessment of water diversion structures. J Hydroinform2021; 23: 249–266.
25.
WeiYWuDTerpennyJ. Decision-level data fusion in quality control and predictive maintenance. IEEE T Autom Sci Eng2021; 18: 184–194.
26.
LiYHouLTangM, et al. Prediction of wind turbine blades icing based on feature selection and 1D-CNN-SBiGRU. Multimed Tools Appl2022; 81: 4365–4385.
27.
YuLYaoXYangJ, et al. Gear fault diagnosis through vibration and acoustic signal combination based on convolutional neural network. Information2020; 11: 266.
28.
YaoXLiSYaoY, et al. Health monitoring and diagnosis of equipment based on multi-sensor fusion. Int J Online Eng2018; 14: 4–19.
29.
JesusJJoseMDavidC, et al. A new damage index based on statistical features, PCA, and mahalanobis distance for detecting and locating cables loss in a cable-stayed bridge. Int J Struct Stab Dy2021; 21: 2150127.
30.
FukushimaYKawadaN. Online monitoring method for mold deformation using mahalanobis distance. Int J Autom Tech2021; 15: 689–695.
31.
HuoJMaYLuC, et al. Mahalanobis distance-based similarity regression learning of NIRS for quality assurance of tobacco product with different variable selection methods. Spectrochim Acta A2021; 251: 119364.
32.
VaswaniAShazeerNParmarN, et al. Attention is all you need. In: 31st International conference on neural information processing systems (NIPS 2017), Long Beach, CA, USA, 4–9 December 2017, pp. 6000–6010.
33.
SunHChenMWengJ, et al. Anomaly detection for in-vehicle network using CNN-LSTM with attention mechanism. IEEE T Veh Technol2021; 70: 10880–10893.
34.
CaoYDingYJiaM, et al. A novel temporal convolutional network with residual self-attention mechanism for remaining useful life prediction of rolling bearings. Reliab Eng Syst Safe2021; 215: 107813.
35.
KimHParkKJeonJ, et al. Candidate point selection using a self-attention mechanism for generating a smooth volatility surface under the SABR model. Expert Syst Appl2021; 173: 114640.
36.
WangXMaoDLiX. Bearing fault diagnosis based on vibro-acoustic data fusion and 1D-CNN network. Measurement2021; 173: 108518.
37.
DuYWangS. Multiple criteria group decision-making method with dempster-shafer theory and probabilistic linguistic term sets. Math Probl Eng2020; 2020: 6537048.
38.
MohanrajTYerchuruJKrishnanH, et al. Development of tool condition monitoring system in end milling process using wavelet features and Hoelder’s exponent with machine learning algorithms. Measurement2021; 173: 108671.
