Training algorithms and learning abilities of three different types of artificial neural networks
Systems Analysis Modelling Simulation
Automatic basis selection techniques for RBF networks
Neural Networks - 2003 Special issue: Advances in neural networks research — IJCNN'03
Selecting radial basis function network centers with recursive orthogonal least squares training
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
Power transmission line insulator is an important part for power system security. Because insulator has complex operating environment and its infection factors interact on each other, the diagnosis of insulator running state is very difficult. It is needed to use some useful information to conclude insulator operating state. 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. Experiment results show that the designed RBF network has strong reasoning and learning ability, which can diagnose insulator operating state unfailingly.