This paper employs three neural networks that are BP, RBF and PNN for rolling bearing fault diagnosis and compares their performance. The preprocessed vibration signals of rolling bearing provide fused feature vectors after the process of wavelet package decomposition and feature fusion. Then the fused feature vectors serve as the inputs of networks. The fault diagnostic aims to recognize health condition, fault types and fault severity of rolling bearings. The simulation results demonstrate that BP has the best accuracy and very complex computation efforts, and RBF has the fastest classification with the lowest precision. Meanwhile, PNN achieves perfect accuracy and speed that can be received.
BellR.N., McWilliamsD.W., O'DonnellP., SinghC. and WellsS.J., Report of large motor reliability survey of industrial and commercial installations, I. IEEE Transactions on Industry Applications21(4) (1985), 853-864.
2.
BelliniA., FilippettiF., TassoniC. and CapolinoG.A., Advances in diagnostic techniques for induction machines, Industrial Electronics, IEEE Transactions on55(12) (2008), 4109-4126.
3.
LiuX., BoL. and LuoH., Bearing faults diagnostics based on hybrid LS-SVM and EMD method, Measurement59 (2015), 145-166.
4.
AliJ.B., FnaiechN., SaidiL., Chebel-MorelloB. and FnaiechF., Application of empirical mode decomposition and artificial neural network for automatic bearing fault diagnosis based on vibration signals, Applied Acoustics89 (2015), 16-27.
5.
YinC., ChenY.Q. and ZhongS.M., Fractional-order sliding mode based extremum seeking control of a class of nonlinear systems, Automatica50 (2014), 3173-3181.
6.
UnalM., OnatM., DemetgulM. and KucukH., Fault diagnosis of rolling bearings using a genetic algorithm optimized neural network, Measurement58 (2014), 187-196.
7.
ChenX., ZhouJ., XiaoJ., ZhangX., XiaoH., ZhuW. and FuW., Fault diagnosis based on dependent feature vector and probability neural network for rolling element bearings, Applied Mathematics and Computation247 (2014), 835-847.
8.
MingA.B., ZhangW., QinZ.Y. and ChuF.L., Envelope calculation of the multi-component signal and its application to the deterministic component cancellation in bearing fault diagnosis, Mechanical Systems and Signal Processing50 (2015), 70-100.
9.
DelgadoM., CirrincioneG., GarciaA., OrtegaJ.A. and HenaoH., Accurate bearing faults classification based on statistical-time features, curvilinear component analysis and neural networks, In IECON 2012-38th Annual Conference on IEEE Industrial Electronics Society (2012), 3854-3386.
10.
ImmovilliF., BelliniA., RubiniR. and TassoniC., Diagnosis of bearing faults in induction machines by vibration or current signals: A critical comparison, Industry Applications, IEEE Transactions on46(4) (2010), 1350-1359.
11.
ZhangY. and RandallR.B., Rolling element bearing fault diagnosis based on the combination of genetic algorithms and fast kurtogram, Mechanical Systems and Signal Processing23(5) (2009), 1509-1517.
12.
WuJ.D. and ChiangP.H., Application of Wigner-Ville distribution and probability neural network for scooter engine fault diagnosis, Expert Systems with Applications36(2) (2009), 2187-2199.
13.
YinC., ZhongS.M. and ChenW.F., Design of sliding mode controller for a class of fractional-order chaotic systems, Communications in Nonlinear Science and Numerical Simulation17 (2012), 356-366.
14.
PereraN. and RajapakseA.D., Recognition of fault transients using a probabilistic neural-network classifier, Power Delivery, IEEE Transactions on26(1) (2011), 410-419.
15.
LiuY.Y., JuY.F., DuanC.D. and ZhaoX.F., Structure damage diagnosis using neural network and feature fusion, Engineering Applications of Artificial Intelligence24(1) (2011), 87-92.
16.
Al-RaheemK.F. and Abdul-KaremW., Rolling bearing fault diagnostics using artificial neural networks based on Laplace wavelet analysis, International Journal of Engineering, Science and Technology2(6) (2010).
17.
LoparoK.A., Bearings Vibration Data Set, Case Western Reserve University, <http://csegroups.case.edu/bearingdata center/home>.
18.
PereraN. and RajapakseA.D., Recognition of fault transients using a probabilistic neural-network classifier, Power Delivery, IEEE Transactions26(1) (2011), 410-419.
