Skip to main navigation menu Skip to main content Skip to site footer
International Journal of Robotics and Automation Technology

Articles

Vol. 1 No. 1 (2014)

Fault Diagnosis of Linear Control Systems Based on the Discrete Wavelet Transform and an ART2 Neural Network

DOI
https://doi.org/10.15377/2409-9694.2014.01.01.2
Submitted
March 10, 2014
Published
10.03.2014

Abstract

Fault detection and isolation of systems continues to be important problems to be addressed due to the increased complexities of more advanced systems. Early detection and isolation of faults can assist in avoidance of major system breakdowns. Many methods require some model of the plant in order to perform the fault diagnosis. In this paper we present a fault diagnosis method for dynamic systems based on discrete wavelet transform (DWT) and an adaptive resonance theory 2 neural network (ART2 NN). In the proposed method a fault is detected when an error between the system output and the nominal system output cross a predetermined threshold. Once a fault in the system is detected the ART2 NN based fault classifier isolates the fault. The algorithm contains three main steps: fault detection through the threshold test, data preprocessing via DWT, and fault isolation using the fault classifier. The simulation results demonstrate the effectiveness of the proposed DWT and ART2 NN based fault diagnosis method.

References

  1. Wagner J, Shoureshi R. A failure isolation strategy for thermofluid system diagnostics. ASME J Eng Industry 1993; 115: 459-465. http://dx.doi.org/10.1115/1.2901790
  2. Isermann R. Process fault detection based on modeling and estimation methods-a survey. Automatica 1984; 20(4): 387- 404. http://dx.doi.org/10.1016/0005-1098(84)90098-0
  3. Doraiswami R, Jiang J. Performance monitoring in expert control systems. Automatica 1989; 25(6): 799-811. http://dx.doi.org/10.1016/0005-1098(89)90049-6
  4. Polycarpou MM, Vemuri AT. Learning methodology for failure detection and accommodation. IEEE Contr. Syst Mag 1995; 16-24. http://dx.doi.org/10.1109/37.387613
  5. Sorsa T, Koivo HN, Koivisto H. Neural networks in process fault diagnosis. IEEE Trans Syst Man Cybern 1991; 21(4): 815-825. http://dx.doi.org/10.1109/21.108299
  6. Srinivasan A, Batur C. Hopfield /ART-1 neural network-based fault detection and isolation. IEEE Trans Neural Networks 1994; 5(6): 890-899. http://dx.doi.org/10.1109/72.329685
  7. Kung SY. Digital neural networks Prentice Hall 1993.
  8. Lee IS, Shin PJ, Geon GJ. Diagnosis of a linear system using ART2 neural networks. J Contr Automat Syst Eng 1997; 3(3): 244-251.
  9. Zuppa M, Distante C, Persaud KC, Siciliano P. Recovery of drifting sensor responses by means of DWT analysis. Sensors Actuators B 2007; 120: 411-416. http://dx.doi.org/10.1016/j.snb.2006.02.049
  10. Ionescu R, Llobet E. Wavelet transform-based fast feature extraction from temperature modulated semiconductor gas sensors. Sensors Actuators B 2002; 81: 289-295. http://dx.doi.org/10.1016/S0925-4005(01)00968-6
  11. Huang MC. Wave parameters and functions in wavelet analysis with filtering. Ocean Eng 2004; 31: 813-831. http://dx.doi.org/10.1016/j.oceaneng.2003.10.004