Fault diagnosis and prognosis using wavelet packet decomposition, Fourier transform and artificial neural network
- 1.4k Downloads
This paper proposes a method for classification of fault and prediction of degradation of components and machines in manufacturing system. The analysis is focused on the vibration signals collected from the sensors mounted on the machines for critical components monitoring. The pre-processed signals were decomposed into several signals containing one approximation and some details using Wavelet Packet Decomposition and, then these signals are transformed to frequency domain using Fast Fourier Transform. The features extracted from frequency domain could be used to train Artificial Neural Network (ANN). Trained ANN could predict the degradation (Remaining Useful Life) and identify the fault of the components and machines. A case study is used to illustrate the proposed method and the result indicates its higher efficiency and effectiveness comparing to traditional methods.
KeywordsDiagnosis Prognosis Wavelet packet decomposition Fourier transform and artificial neural network
Unable to display preview. Download preview PDF.
- Chen, C., Sun, C., Zhang, Y. & Wang, N. (2005). Fault diagnosis for large-scale wind turbine rolling bearing using stress wave and wavelet analysis. In ICEMS 2005 proceedings of the eighth international conference on electrical machines and systems (Vol. 3, pp. 2239–2244).Google Scholar
- He, S., He, Z.,& Wang, G. (2011). Online monitoring and fault identification of mean shifts in bivariate processes using decision tree learning techniques. Journal of Intelligent Manufacturing, 1–10. doi: 10.1007/s10845-011-0533-5.
- Kegg R. L. (1984) On-line machine and process diagnostics. Annals of the CIRP 32(2): 469–573Google Scholar
- Lee, I. (2011). Fault diagnosis of induction motors using discrete wavelet transformation and artificial neural network. In C. Stephanidis (Ed.), HCI international 2011—Posters’ extended abstract, Vol. 573, (pp.510–514).Google Scholar
- Li, R., Sopon, P., & He, D. (2009). Fault features extraction for bearing prognostics. Journal of Intelligent Manufacturing. doi: 10.1007/s10845-009-0353-z.
- Meng, X., & Meng, X. (2010). Nonlinear system simulation based on the BP neural network. In 2010 3rd international conference on intelligent networks and intelligent systems (ICINIS), pp. 334–337.Google Scholar
- Momoh, J. A.,& Button, R. (2003). Design and analysis of aerospace DC arcing fault using fast fourier transformation and artificial neural network. In Power engineering society general meeting, pp. 788–793.Google Scholar
- Rumelhart D. E., Hinton G. E., Williams R. J. (1986) Learning internal representational by error propagation. In: Rumenhart D. E., McCelland J. L. (Eds.) Parallel distributed processing: Exploration in the microstructure of cognition. MIT Press, Cambridge, MA, pp 318–362Google Scholar
- Sohn, R. H., Son, J. S., Hwang, H. J., IM, C. H., & Kim, Y. H. (2010). SSVEP-based functional electrical stimulation system For motor control of patients with spinal cord injury. In Proceedings of 6th word congress of biomechanics (Vol. 31. pp. 655–658).Google Scholar
- Tian, Z. (2006). An artificial neural network method for remaining useful life prediction of equipment subject to condition monitoring. Journal of Intelligent Manufacturing. doi: 10.1007/s10845-009-0356-9.
- Wang K. (2002) Intelligent condition monitoring and diagnosis systems. IOS Press, AmsterdamGoogle Scholar
- Wang, K. (2005). Applied computational intelligence in intelligent manufacturing systems. Advanced Knowledge International Pty Ltd, Australia.Google Scholar