In machinery condition monitoring, it is often vital to consider information from multiple sources due to possible sensor failure or signal distortion, which may result in misclassification of the health status. An issue with multiple sensor data fusion, however, is that the classification can be affected by conflicting results between sensor signals. The proposed method uses a novel three-module approach to information fusion in order to address the problem. Features corresponding to signal integrity are extracted and employed for training a one-class support vector machine to detect unwanted distortions or sensor failures. Different classifiers are trained for the different sensor types available and each signal recorded is used to determine machine health. Decision-level fusion is conducted through a majority voting system using the integrity scores derived from the OCSVMs and the separate classification results. From this, a dynamically weighted fault diagnosis based on sensor signal quality is obtained. Experimental verification using vibration and acoustic emission signals show that the framework is viable and allows for an increased reliability in machinery health diagnosis.
CastanedoF. A review of data fusion techniques. Sci World J2013; 2013: 1–19.
2.
DuanZWuTGuoS, et al.Development and trend of condition monitoring and fault diagnosis of multi-sensors information fusion for rolling bearings: a review. Int J Adv Manuf Technol2018; 96: 803–819.
3.
WangHLiSSongL, et al.A novel convolutional neural network based fault recognition method via image fusion of multi-vibration-signals. Comput Ind2019; 105: 182–190.
4.
XiaMLiTXuL, et al.Fault diagnosis for rotating machinery using multiple sensors and convolutional neural networks. IEEE/ASME Trans Mechatronics2018; 23(1): 101–110.
5.
JingLWangTZhaoM, et al.An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox. Sensors (Switzerland)2017; 17(2): 414.
6.
ChenZLiW. Multisensor feature fusion for bearing fault diagnosis using sparse autoencoder and deep belief network. IEEE Trans Instrum Meas2017; 66(7): 1693–1702.
7.
TaoJLiuYYangD. Bearing fault diagnosis based on deep belief network and multisensor information fusion. Shock Vib2016; 2016: 1–9.
8.
VanrajDhamiSSPablaBS. Hybrid data fusion approach for fault diagnosis of fixed-axis gearbox. Struct Heal Monit2018; 17(4): 936–945.
9.
NiuGHanTYangBS, et al.Multi-agent decision fusion for motor fault diagnosis. Mech Syst Signal Process. 2007; 21(3): 1285–1299.
10.
SafizadehMSLatifiSK. Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell. Inf Fusion2014; 18: 1–8.
11.
ZhongJHWongPKYangZX. Fault diagnosis of rotating machinery based on multiple probabilistic classifiers. Mech Syst Signal Process2018; 108: 99–114.
12.
LiXWanSLiuS, et al.Bearing fault diagnosis method based on attention mechanism and multilayer fusion network. ISA Trans. 2021. In Press.
ElforjaniMMbaD. Accelerated natural fault diagnosis in slow speed bearings with Acoustic Emission. Eng Fract Mech2010; 77(1): 112–127.
15.
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.
16.
Van HeckeBYoonJHeD. Low speed bearing fault diagnosis using acoustic emission sensors. Appl Acoust2016; 105: 35–44.
17.
LiCSanchezRVZuritaG, et al.Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals. Mech Syst Signal Process2016; 76–77: 283–293.
18.
MeyOSchneiderAEnge-RosenblattO, et al.Condition monitoring of drive trains by data fusion of acoustic emission and vibration sensors†. Processes2021; 9(7): 1–13.
19.
GirondinVLoudahiMMorelH, et al.Vibration-based fault detection of accelerometers in helicopters. IFAC Proc Volumes (IFAC-PapersOnline)2012: 45: 720–725. Elsevier
20.
AbboudDElbadaouiMBecquerelleS, et al.Detection of sensor detachment in aircraft engines using vibration signals. In: CavalcaKLWeberHI (eds) Proceedings of the 10th International Conference on Rotor Dynamics ‐‐ IFToMM. Cham: Springer International Publishing, 2019. p. 351–365.
21.
RandallRBSmithWA. Detection of faulty accelerometer mounting from response measurements. J Sound Vib2020; 477: 115318.
22.
KhaleghiBKhamisAKarrayFO, et al.Multisensor data fusion: a review of the state-of-the-art. Inf Fusion2013; 14(1): 28–44.
23.
AbdiHWilliamsLJ. Principal component analysis. Wiley Interdiscip Rev Comput Stat2010; 2: 433–459. John Wiley & Sons, Ltd.
24.
SchölkopfBWilliamsonRSmolaA, et al.Support vector method for novelty detection. Adv Neural Inf Process Syst2000; 14: 582–588.
25.
MollasalehiE. Data-driven and model-based bearing fault analysis - wind turbine application. Unpublished doctoral thesis. Calgary, AB: University of Calgary, 2017.
26.
DyerDStewartRM. Detection of rolling element bearing damage by statistical vibration analysis. Am Soc Mech Eng1977; 100(2): 229–235.
27.
ShenZHeZChenX, et al.A monotonic degradation assessment index of rolling bearings using fuzzy support vector data description and running time. Sensors (Switzerland)2012; 12(8): 10109–10135.
28.
TomKF. A primer on vibrational ball bearing feature generation for prognostics and diagnostics algorithms. Army Research Lab. Adelphi; 2015. https://apps.dtic.mil/sti/citations/ADA614145
29.
CaesarendraWTjahjowidodoT. A review of feature extraction methods in vibration-based condition monitoring and its application for degradation trend estimation of low-speed slew bearing. Machines2017; 5(4): 21.
30.
KannanVLiHDaoDV. Demodulation band optimization in envelope analysis for fault diagnosis of rolling element bearings using a real-coded genetic algorithm. IEEE Access2019; 7: 168828–168838.
