论文信息 - Predicting of wire network signal based on improved RBF network

Predicting of wire network signal based on improved RBF network

In the process of monitoring and repairing, it is difficult to measure wire net signal of power systempsilas high voltage power transmission lines accurately. In order to solve this problem, the signal measured in remote substation or laboratory is employed to make multipoint prediction to gain the needed data, and then the predicted data is send to work-field via wireless network GPRS. The needed precise data may be computed based on current time and received data in work-field, which may provide reliably basis for fault diagnosis of air bracket high voltage power transmission lines. Here, RBF neural network is employed to identify and predict the needed time signals. In order to overcome the shortcoming of general RBF net that convergence speed is slow and plunge local extremum easily, a practical learning algorithm was proposed for adjusting the node number, centers and width of Gaussian function of hidden layer nodes effectively. Off-line training and on-line identifying were combined together to train networks and identify wire net signal. Simulation experiment shows that the designed RBF network having good predicting ability, which offers accurate data for the monitoring and fault diagnosis of high voltage power transmission lines.

Shuqing Wang | Zipeng Zhang | Liqin Xue

[1] Tao Zhu,et al. An efficient learning algorithm for improving generalization performance of radial basis function neural networks , 2000, Neural Networks.

[2] Xin Yao,et al. Evolving artificial neural network ensembles , 2008 .

[3] Kumpati S. Narendra,et al. Identification and control of dynamical systems using neural networks , 1990, IEEE Trans. Neural Networks.

[4] Rey-Chue Hwang,et al. An effective learning of neural network by using RFBP learning algorithm , 2004, Inf. Sci..

[5] Xin Yao,et al. Evolving artificial neural networks , 1999, Proc. IEEE.

[6] Haralambos Sarimveis,et al. Training algorithms and learning abilities of three different types of artificial neural networks , 2000 .

[7] Kumpati S. Narendra,et al. Identification and control , 1998 .

[8] Dingli Yu,et al. Selecting radial basis function network centers with recursive orthogonal least squares training , 2000, IEEE Trans. Neural Networks Learn. Syst..

[9] Zhiye Zhao,et al. An optimal neural network and concrete strength modeling , 2002 .

[10] Dale Schuurmans,et al. Automatic basis selection techniques for RBF networks , 2003, Neural Networks.

[11] Nicolaos B. Karayiannis,et al. Accelerating the training of feedforward neural networks using generalized Hebbian rules for initializing the internal representations , 1996, Proceedings of 1994 IEEE International Conference on Neural Networks (ICNN'94).