基于分数阶Hilbert变换的模拟电路双层故障特征提取方法

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (356 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract According to the flexibility of the fractional order p value and the detail characteristics can be extracted from the analytical signal. A new method of analog circuit two-layer fault feature extraction based on fractional Hilbert transform is proposed. The entropy of amplitude and phase and instantaneous frequency value calculated from the analytical signal are the feature values. Firstly, by using the Fisher criterion and the genetic algorithm to obtain the optimal fractional order p₁ value which lead to the greatest distinction between the normal samples and other samples, extracting the features and then using the two-class SVM classifier to diagnose the normal samples. Secondly, to obtain the optimal fractional order p₂ value in the same way, it makes the greatest distinction between the different classes of fault samples. Afterwards, the different fault samples are diagnosed by the multi-class SVM classifier. The experiment results show that this method can improve the performance of fault diagnosis.

Key words： Fractional Hilbert transform Fisher criterion analog circuit fault diagnosis feature extraction

Received: 26 March 2009 Published: 04 March 2014

PACS:

TP206+.3

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Luo Hui
	Wang Youren
	Cui Jiang

Cite this article:

Luo Hui,Wang Youren,Cui Jiang. A Method of Analog Circuit Two-Layer Fault Feature Extraction Based on Fractional Hilbert Transform[J]. Transactions of China Electrotechnical Society, 2010, 25(6): 150-154.

URL:

http://dgjsxb.ces-transaction.com/EN/ OR http://dgjsxb.ces-transaction.com/EN/Y2010/V25/I6/150

[1] Tan Yanghong, He Yigang, Cui Chun, et al. A novel method for analog fault diagnosis based on neural networks and genetic algorithms [J]. IEEE Transactions on Instrumentation and Measurement, 2008, 57(11): 2631-2639.
[2] 崔江, 王友仁. 一种云样本的控制产生及在电路故障诊断中的应用[J]. 控制理论与应用, 2008, 25(3): 556-559.
[3] Hiroshi Toda, Zhang Zhong. Perfect translation invariance with a wide range of shapes of Hilbert transform pairs of complex wavelets[C]. Proceedings of the 2007 International Conference on Wavelet Analysis and Pattern Recognition, Beijing, 2007: 1565-1570.
[4] Lohmann A W, Mendlovic D, Zalevsky Z. Fractional Hilbert transform[J]. Optics Letters, 1996, 21: 281-283.
[5] Soo Chang Pei, Min Hung Yeh, Chien Cheng Tseng. Discrete fractional fourier transform based on orthogonal projections[J]. IEEE Transactions on Signal Processing, 1999, 47(5): 1335-1347.
[6] Soo Chang Pei, Min Hung Yeh. Discrete fractional Hilbert transform[J]. IEEE Transactions on Circuits and Systems-Ⅱ: Analog and Digital Signal Processing, 2000, 11(47): 1307-1311.
[7] Chien Cheng Tseng, Soo Chang Pei. Design and application of discrete-time fractional Hilbert transformer[J]. IEEE Transactions on Circuits and Systems-Ⅱ: Analog and Digital Signal Processing, 2000, 12(47): 1529-1533.
[8] Tao Ran, Li Xuemei, Wang Yue. Generalization of the fractional Hilbert transform[J]. Signal Processing Letters, 2008, 15: 365-368.
[9] Ewa Hermanowicz, Hakan Johansson, Miroslaw Rojewski. A fractionally delaying complex Hilbert transform filter[J]. IEEE Transactions on Circuits and Systems-Ⅱ: Express Briefs 2008, 55(5): 452-456.
[10] Aminian Farzan, Aminian Mehran, Collins H W. Analog fault diagnosis of actual circuits using neural networks[J]. IEEE Transactions on Instrumentation and Measurement, 2002, 51(3): 544-555.