Study on Transient Signals Recognition in Power System Based on Multiwavelet Packet Coefficient Entropy and Artificial Neural Network
- 10.2991/iske.2007.65How to use a DOI?
- Multiwavelet packet;Traditional wavelet packet;RBF neural network;Multiwavelet packet coefficent entropy;Transient signals recognition;
Multiwavelets own better properties than those of traditional wavelets. In the paper multiwavelet packet coefficient entropy (MPCE) is defined through combining decomposition coefficient of multiwavelet packet with entropy. A novel transient signals recognition method based on MPCE and artificial neural network (ANN) is proposed. Firstly, the appropriate multiwavelet packet decomposition of the sampled transient current signal is performed and each MPCE of transient current is calculated. Then eigenvector of multiwavelet packet of the current signal is constructed, and by taking the eigenvector as training samples the radial basis function (RBF) neural network is trained to implement the transient signals recognition. At last the proposed method is compared with the means based on traditional wavelet packet and ANN. Simulation results show that the proposed method is effective and feasible and the recognition capability is better than the method based on traditional wavelet packet and ANN.
- © 2007, the Authors. Published by Atlantis Press.
- Open Access
- This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).
Cite this article
TY - CONF AU - Dongmin Li AU - Zhigang Liu AU - Baichao Huo AU - Yuxiang Su PY - 2007/10 DA - 2007/10 TI - Study on Transient Signals Recognition in Power System Based on Multiwavelet Packet Coefficient Entropy and Artificial Neural Network BT - Proceedings of the 2007 International Conference on Intelligent Systems and Knowledge Engineering (ISKE 2007) PB - Atlantis Press SP - 385 EP - 391 SN - 1951-6851 UR - https://doi.org/10.2991/iske.2007.65 DO - 10.2991/iske.2007.65 ID - Li2007/10 ER -