Health Assessment of Aircraft Based on Wavelet Neural Network

Abstract:

Health assessment is one of the key technology in the aircraft operating system. Aiming at the characteristic of aircraft structure, the aircraft fault prediction method based on data mining is presented in this paper. The concept of health assessment is introduced first, the wavelet neural network provide the mathematical model reflecting aircraft health state. The experiment results show that the health prediction applying wavelet neural network works well with high fidelity and real time. Focusing at a typical heavy-duty gas turbine, the critical information collected by the sensor is applied as the network input, then the wavelet neural network is constructed, the quick training and learning speed is proved. The results indicate proposed approach is promising for reliable diagnostics of aircraft.

• Periodical: Advanced Materials Research (Volumes 756-759)
• Pages: 4581-4585
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.756-759.4581
• Online since: September 2013
• Authors: Chen Guang Zhao, Xu Ping Qi, Chen Ming Mi, Teng Fei Miao
• Keywords: Aircraft, Data Mining (DM), Fault Diagnosis, Health Assessment, Wavelet Neural Network (WNN)

References

[1] Chen Tian. Aircraft Gas Path Fault Diagnosis Using Rough Sets and Neural Networks, Journal of Aerospace Power 2006-01.

[2] Arita M, Syrmos V. Multi Source Data Integration for Aircraft Health Management, IEEE Aerospace Conference, (2008).

DOI: 10.1109/aero.2008.4526625

[3] JI Qian, Zhao Chen-guang. Experimantal Study on Pressure Atomising injector Performance of a Heavy-duty Gas Turbine, Aircraft, 2011, Vol. 37 No. 2 33-37.

[4] QING-YANG XU. Gas Turbine Fault Diagnosis Based on Wavelet Neural Network, Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recgonition, Beijing, China, 738-741.

DOI: 10.1109/icwapr.2007.4420766

[5] Suhartono and Subanar, Development of Model Building Procedures in Wavelet Neural Networks for Forecasting Non-Stationary Time Series, European Journal of Science Research, 34 (2009), No. 3, 416-427.

[6] S. Haykins, Neural Networks-A comprehensive Foundation, McGraw Hill, (1993).

[7] K. Ko and M. Vannucci, Bayesian wavelet analysis of autoregressive fractionally integrated moving-average processes, Elsevier, Science Direct, 136 (2006), 3415-3434.

DOI: 10.1016/j.jspi.2005.01.010

[8] Y. Kopsinis and S. McLaughlin, Empirical Mode Decomposition Based Soft-Thresholding, Proceedings of the 16th European Signal Processing Conference, EUSIPCO (2008).

[9] Zekeriya Uykan，Cuneyt Guzelis，M．Ertugml Celebi．Analysis of Input Output Clustering for Determining Centers of RBFN，IEEE Trans On NN，2000．7，11(4).

DOI: 10.1109/72.857766