A normalized fuzzy neural network and its application

A normalized fuzzy neural network (NFNN) with five layers is proposed. Focusing on the structure optimization of network, a new node selection method and corresponding back propagation learning algorithm rules are presented. In the case of with fewer input nodes, the training is faster in this kind of neural network. The proposed method is applied successfully to water-flooded zone identification in measure-well explanation, which is an important problem in the oil field development. Test results illustrate its practicability.