Hilbert-Huang轉換方法於振動信號之故障診斷

Fault Diagnosis for Vibration Signal Using Hilbert-Huang Transform

曾獻毅(Hsien-Yi Tseng)

指導教授 ： ARRAY(0xc8a000c)

中原大學/工學院/機械工程研究所/碩士(2009年)

https://doi.org/10.6840/CYCU.2009.00884

摘要

本文以Hilbert-Huang轉換方法應用於非穩態振動信號之故障診斷，先以經驗模態分解將振動信號轉換到固有模態函數分量，再使用Hilbert轉換得到瞬時振幅及瞬時頻率以時頻函數，呈現出不同類型信號的能量分佈，最後針對各固有模態函數分量之瞬時振幅取能量特徵，輸入至倒傳遞類神經網路中，實現人工智慧識別故障狀態，本文並以實測驗證所提方法的可行性。

關鍵字

類神經網路 ； Hilbert-Huang 轉換 ； 時頻分析 ； 故障診斷

並列摘要

The paper applies Hilbert-Huang Transform (HHT) in the vibration signals by the empirical mode decomposition (EMD), and the data can be decomposed into several intrinsic mode functions (IMFs). With the Hilbert transform (HT), the presentation of the instantaneous frequencies and amplitude that is an time-frequency-energy distribution. The energy features is excited from each intrinsic mode function and entered the back-propagation neural network to proof the intelligence fault diagnosis.

並列關鍵字

Hilbert-Huang Transform ； Time-Frequency Analysis ； neural network ； Fault diagnosis

參考文獻

1. Huang, N. E., “The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis, ” Proc. Roy. Soc. Lond.,vol. 454, pp. 903-995, 1998.

3. Zhidong, Z., Min, P. and Yuquan, C., “Instantaneous frequency estimate for non-stationary signal,” Fifth World Congress on Intelligent Control and Automation, vol. 4, pp. 3641-3643, 2004.

4. Ruqiang, Y. and Gao, R.X., “Hilbert–Huang Transform-Based Vibration Signal Analysis for Machine Health Monitoring,” IEEE Transactions on Instrumentation and Measurement, vol. 55, pp. 2320-2329, 2006.

5. Yuping, Z., “Hilbert-Huang Transform and Marginal Spectrum for Detection of Bearing Localized Defects,” The Sixth World Congress on Intelligent Control and Automation, vol.2, pp. 5457-5461, 2006.

6. Rumelhart, D. E., Hinton, G. E. and Williams, R. J., “Learning Representations by Back- Propagating Errors,” Nature, Vol. 323, No. 6088, pp. 533-536, 1986.