In this study, features are extracted from time vibration signals for the purpose of diagnosing motor faults. On the basis of the specific distance criterion, a simple genetic algorithm (GA) is employed to evaluate and select the optimized features for induction motor fault classification. The selected features are applied to the decision tree and the k-nearest neighbour (k-NN) algorithm in order to show the efficiency of the proposed feature selection method. The diagnostic results show that the optimal feature selection is useful to improve the fault diagnosis performance.
SugumaranV.MuralidharanV.RamachandranK. I.Feature selection using decision tree and classification through proximal support vector machine for fault diagnostics of roller bearing. Mech. Syst. Signal Process.200721930–942.
2.
SunW.ChenJ.LiJ.Decision tree and PCA-based fault diagnosis of rotating machinery. Mech. Syst. Signal Process.2007211300–1317.
3.
YangB. S.ParkC. H.KimH. J.An efficient method of vibration diagnostics for rotating machinery using a decision tree. Int. J. Rotating Mach.20006(1)19–27.
4.
LimD. S.YangB. S.KimD. J.An expert system for vibration diagnosis of rotating machinery using decision tree. Int. J. COMADEM2000331–36.
5.
YangY.YuD.ChengJ.A fault diagnosis approach for roller bearing based on IMF envelope spectrum and SVM. Measurement200740943–950.
6.
SamantaB.Al-BalushiK. R.Artificial neural network based fault diagnostics of rolling element bearings using time-domain features. Mech. Syst. Signal Process.200317317–328.
7.
SamantaB.Al-BalushiK. R.Al-AraimiS. A.Artificial neural networks and genetic algorithm for bearing fault detection. Soft Comput.200610264–271.
8.
LeiY.HeZ.ZiY.HuQ.Fault diagnosis of rotating machinery based on multiple ANFIS combination with GAs. Mech. Syst. Signal Process.2007212280–2294.
9.
BenbouzidM. E. H.KlimanG. B.What stator current processing-based technique to use for induction motor rotor faults diagnosis?IEEE Trans. Energy Convers.200318(2)238–244.
10.
CombastelC.LesecqS.PetropolS.GentilS.Model-based and wavelet approaches to induction motor on-line fault detection. Control Eng. Pract.200210(5)493–509.
11.
KimK.ParlosA. G.Model-based fault diagnosis of induction motors using non-stationary signal segmentation. Mech. Syst. Signal Process.200216(2–3)223–253.
12.
LimH. S.ChongK. T.SuH.Motor fault detection method for vibration signal using FFT residuals. Int. J. Appl. Electromagn. Mech.200624(3–4)209–223.
13.
NiuG.SonJ. D.WidodoA.YangB. S.HwangD. H.KangD. S.A comparison of classifier performance for fault diagnosis of induction motor using multitype signals. Struct. Health Monit.20076(3)215–229.
