With the combination of the near-field acoustic holography (NAH) and pattern recognition technique, a NAH-based diagnosis technique is proposed and applied to diagnose gearbox faults by analyzing the sound field distribution information first. After visualizing the sound fields under different working conditions by NAH, the spatial gray level co-occurrence matrices based textural features can be obtained from the NAH images. Then, the support vector machine is employed to identify different working conditions and diagnose the faults. Two gearbox experiments with different gear faults and fault severity are studied in a semi-anechoic chamber to verify the NAH-based diagnosis technique. The experimental results demonstrate that the NAH-based diagnosis method is feasible and effective, and can be anticipated as a choice for gearbox fault diagnosis.
BadaouiMELAntoniJGuilletF. (2001) Use of the moving cepstrum integral to detect and localise tooth spalls in gears. Mech Syst Signal Process15: 873–885.
2.
BaydarNBallA. (2000) Detection of gear deterioration under varying load conditions by using the instantaneous power spectrum. Mech Syst Signal Process14: 907–921.
3.
BaydarNBallA. (2001) A comparative study of acoustic and vibration signals in detection of gear failures using Wigner–Ville distribution. Mech Syst Signal Process15: 1091–1107.
4.
BaydarNBallA. (2003) Detection of gear failures vibration and acoustic signals using wavelet transform. Mech Syst Signal Process17: 787–804.
5.
BenkoUPetrovcicJJuricicD. (2005) An approach to fault diagnosis of vacuum cleaner motors based on sound analysis. Mech Syst Signal Process19: 427–445.
6.
BurgesCJC. (1998) A tutorial on support vector machines for pattern recognition. Data Mining Knowledge Discov2: 955–974.
ChenLWangGZ. (2005) Noise fault diagnosis based on time-frequency domain model. J Vibration Shock24: 54–57.
9.
CombetFGelmanL. (2007) An automated methodology for performing time synchronous averaging of a gearbox signal without speed sensor. Mech Syst Signal Process21: 2590–2606.
DalpiazGPivolaGRubiniR. (2000) Effectiveness and sensitivity of vibration processing techniques for local fault detection in gears. Mech Syst Signal Process14: 387–412.
12.
Dempsey PJ (2000) A Comparison of Vibration and Oil Debris Gear Damage Detection Methods Applied to Pitting Damage. Technical report NASA/TM-2000-210371.
13.
Dempsey PJ (2003) Integrating Oil Debris and Vibration Measurements for Intelligent Machine Health Monitoring. Technical report NASA/TM-2003-211307.
14.
Dempsey PJ and Afjeh AA (2002) Integrating Oil Debris and Vibration Gear Damage Detection Technologies using Fuzzy Logic. Technical report NASA/TM-2002-211126.
15.
HaralickRMDinsteinIShanmugamK. (1973) Textural features for image classification. IEEE Trans Syst Man Cybernet3: 610–621.
16.
HsuCWLinCJ. (2002) A comparison of methods for multi-class support vector machines. IEEE Trans Neural Networks13: 415–425.
17.
JackLBNandiAK. (2002) Fault detection using support vector machines and artificial neural networks, augmented by genetic algorithms. Mech Syst Signal Process16: 373–390.
18.
LiWDRobertMParkinJC. (2002) Acoustic based condition monitoring of a diesel engine using self-organizing map networks. Appl Acoust63: 699–711.
19.
LoutasTHSotiriadesGKalaitzoglouI. (2009) Condition monitoring of a single-stage gearbox with artificially induced gear cracks utilizing on-line vibration and acoustic emission measurements. Appl Acoust70: 1148–1159.
20.
LuXJWeiZ. (1999) Spectral analysis and diagnosis of gearbox noise. J Vibration Shock18: 75–78.
21.
MaynardJDWilliamsEGLeeY. (1985) Near field acoustic holography: I. Theory of generalized holography and the development of NAH. J Acoust Soc Am78: 1395–1413.
22.
SamantaB. (2004) Gear fault detection using artificial neural networks and support vector machines with genetic algorithms. Mech Syst Signal Process20: 625–644.
23.
ShibataKTakahashiAShiraiT. (2000) Fault diagnosis of rotating machinery through visualisation of sound signals. Mech Syst Signal Process14: 229–241.
24.
StaszewskiWJWordenKTomlinsonGR. (1997) Time–frequency analysis in gearbox fault detection using the Wigner–Ville distribution and pattern recognition. Mech Syst Signal Process11: 673–692.
25.
WanQJiangWK. (2006) Near field acoustic holography (NAH) theory for cyclostationary sound field and its application. J Sound Vibration290: 956–967.
26.
WangWQIsmailFGolnaraghiMF. (2001) Assessment of gear damage monitoring techniques using vibration measurements. Mech Syst Signal Process15: 902–922.
27.
WuCMChenYCHsiehKS. (1992) Texture feature analyses and classification in medical images. IEEE Trans Med Imaging11: 141–152.
28.
XuGLianXMJiangXY. (2000) Extraction of sound frequency features of gear processing error in transmissions. Automotive Engng22: 55–58.
