-
A new feedback neural network model is proposed. The network has the sinusoidal basis functions as its weights. Neuronal activation function is a linear function. The network connection form is feedback structure. An energy function is defined for the feedback neural network. And then, the network stability issue in operation is analyzed. In the Liapunov sense, the proposed feedback network stability is proved. During the operation of the network, the network states are changed ceaselessly but network weights vary according to time-dependent sinusoidal law. As the network state changes continuously, its energy will be reduced. Finally, when network comes to a stable state, its energy arrivs at a minimum value. The network is particularly suited for the adaptive approximation and the detection for periodic signals because of its sinusoidal basis function weights. It is, in practice, a new and effective way for periodic signal detection and processing. The very good detection results are obtained in the detection of power system voltage sag characteristics. Simulation examples show that the dynamic response speed of the network is very high.
-
Keywords:
- feedback neural network /
- sinusoidal basis function weights /
- Liapunov stability /
- signal detection
[1] Xing H Y, Xu W 2007 Acta Phys. Sin. 56 3771 (in Chinese)[行鸿彦, 徐伟2007 56 3771]
[2] Watabe K, Shimizu K, Yonyama M 2003 IEEE Trans. MicrowaveTheory and Techniques 51 1512
[3] Reznik L, Von Pless G., Al Karim T 2011 IEEE Sensors Journal11 791
[4] Wei Q, Fung K S A, Chan F H Y 2002 IEEE Trans. on BiomedicalEngineering 49 225
[5] Selvan S, Srinivasan R 1999 IEEE Signal Processing Letters 6 330
[6] Li H Q, Liao X F, Huang H Y 2011 Acta Phys. Sin. 60 020512 (in Chinese)[李华青, 廖晓峰, 黄宏宇2011 60 020512]
[7] Yuan X F, Wang Y N, Wu L H 2010 IEEE Transactions on VehicularTechnology 59 3757
[8] Mevawalla Z N, May G S, Kiehlbauch M W 2011 IEEE Transactionson Semiconductor Manufacturing 24 182
[9] Ma Q L, Zheng Q L, Peng H 2009 Acta Phys. Sin. 58 1410 (in Chinese)[马千里, 郑启伦, 彭宏 2009 58 1410]
[10] De W E, Chu Q P Mulder J A 2009 IEEE Trans. on Neural Networks20 638
[11] Barbarosou M P, Maratos N G. 2008 IEEE Trans. Neural Networks19 1665
[12] Qiu S S, Deng F Q, Liu Y Q 2004 Acta Auto. Sin. 30 507 (in Chinese)[邱深山, 邓飞其, 刘永清 2004 自动化学报 30 507]
[13] Gao W X, Luo X J 2005 Trans. of China Elecrotechnical Society20 58 (in Chinese)[高炜欣, 罗先觉 2005 电工技术学报 20 58]
[14] Ma Z E, Zhou Y C 2001 Qualitative and Stability Method of OrdinaryDifferential Equation(Beijing Science Press) pp78–95 (in Chinese)[马知恩, 周义仓 2001 常微分方程定性与稳定性方法(北京:科学出版社)第78—95页]
[15] Chung Y H, Kim H J, Kwon G H 2007 IEEE on Power EngineeringSociety General Meeting070701-7
-
[1] Xing H Y, Xu W 2007 Acta Phys. Sin. 56 3771 (in Chinese)[行鸿彦, 徐伟2007 56 3771]
[2] Watabe K, Shimizu K, Yonyama M 2003 IEEE Trans. MicrowaveTheory and Techniques 51 1512
[3] Reznik L, Von Pless G., Al Karim T 2011 IEEE Sensors Journal11 791
[4] Wei Q, Fung K S A, Chan F H Y 2002 IEEE Trans. on BiomedicalEngineering 49 225
[5] Selvan S, Srinivasan R 1999 IEEE Signal Processing Letters 6 330
[6] Li H Q, Liao X F, Huang H Y 2011 Acta Phys. Sin. 60 020512 (in Chinese)[李华青, 廖晓峰, 黄宏宇2011 60 020512]
[7] Yuan X F, Wang Y N, Wu L H 2010 IEEE Transactions on VehicularTechnology 59 3757
[8] Mevawalla Z N, May G S, Kiehlbauch M W 2011 IEEE Transactionson Semiconductor Manufacturing 24 182
[9] Ma Q L, Zheng Q L, Peng H 2009 Acta Phys. Sin. 58 1410 (in Chinese)[马千里, 郑启伦, 彭宏 2009 58 1410]
[10] De W E, Chu Q P Mulder J A 2009 IEEE Trans. on Neural Networks20 638
[11] Barbarosou M P, Maratos N G. 2008 IEEE Trans. Neural Networks19 1665
[12] Qiu S S, Deng F Q, Liu Y Q 2004 Acta Auto. Sin. 30 507 (in Chinese)[邱深山, 邓飞其, 刘永清 2004 自动化学报 30 507]
[13] Gao W X, Luo X J 2005 Trans. of China Elecrotechnical Society20 58 (in Chinese)[高炜欣, 罗先觉 2005 电工技术学报 20 58]
[14] Ma Z E, Zhou Y C 2001 Qualitative and Stability Method of OrdinaryDifferential Equation(Beijing Science Press) pp78–95 (in Chinese)[马知恩, 周义仓 2001 常微分方程定性与稳定性方法(北京:科学出版社)第78—95页]
[15] Chung Y H, Kim H J, Kwon G H 2007 IEEE on Power EngineeringSociety General Meeting070701-7
Catalog
Metrics
- Abstract views: 7965
- PDF Downloads: 903
- Cited By: 0
下载:
