Feature extraction for gear diagnostics based on EEMD in different crack size



Suck-Joo HAM Sung-Ho PARK Joo-Ho CHOI


In these days, diagnostics techniques enabling the condition based maintenance are being paid great attention in many industry fields to achieve increased reliability of the system as well as the reduction of operating cost. The techniques are particularly useful to the system that costs a
tremendous amount for the maintenance or leads to the catastrophic results when failure occurs. In such systems, the gearbox is usually employed to deliver the power under extreme loading conditions which are expensive to maintain and replace when failure occurs. Among the many gear faults, crack is the most critical in the sense that it grows suddenly to the tooth breakage, resulting in the whole system loss. To diagnose tooth cracks, many authors have conducted studies using gear vibration signals. Choi and Li estimated gear tooth transverse crack size using vibration signals by fusing selected gear condition indices [1]. G.R proposed vibration signature to estimate fault size [2]. This study classifies features of fault signal in different crack size using TE. In the previous study [4], authors have conducted a fault classification study of spall and crack, in which a pair of gears are operated in a testbed, faults are imbedded to the gear, and features are extracted based on the Ensemble Empirical Mode Decomposition (EEMD) technique using the transmission error (TE) signals [3-4]. Types of the fault are then identified based on the finite element analysis (FEA) of the faulted gears. In this study, further progress is made with the goal to evaluate the severity of the crack faults from the signal. To this end, gears with different crack size are prepared. The FEAs are conducted and compared with the measured signals, from which the critical size is identified that requires maintenance action. Since the measured crack signals include various noise and uncertainties, study on the statistical
significance is also made to check whether the signal can be large enough to detect the fault. Once successful, the technique can be applied to estimate not only the size of the crack fault but also its severity against the critical level, using the measured TE signals of the gears in operation.

Abstract 5 | PDF Downloads 11




Choi, Sukhwan, and C. James Li. "Estimation of gear tooth transverse crack size from vibration by fusing selected gear condition indices." Measurement Science and Technology 17.9 (2006): 2395.
Biswal, Sailendu, Jithin Donny George, and G. R. Sabareesh. "Fault Size Estimation Using Vibration Signatures in a Wind Turbine Test-rig." Procedia Engineering 144 (2016): 305-311.
Times New Roman Loutridis, S. J. (2006). Damage detection in gear systems using empirical mode decomposition. Engineering Structures, 26(12), 1833-1841
Sung-Ho PARK & Joo-Ho CHOI (2016). A study on feature extraction and fault classification for crack and spall in spur gears.
Wu, Zhaohua, and Norden E. Huang. "Ensemble empirical mode decomposition: a noise-assisted data analysis method." Advances in adaptive data analysis 1.01 (2009): 1-41..
Wang, Tong, et al. "Comparing the applications of EMD and EEMD on time–frequency analysis of seismic signal." Journal of Applied Geophysics 83 (2012): 29-34.
Taylor, Michael. Gear fault detection using non-contact magnetic rotation position sensors. Diss. 2010.
Special Session Papers