A normal 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 with fewer input nodes, the training is more fast in this kind of neural network. Water-flooded zone identification in measure-well explanation is an important problem in the oil field development; especially in its later period. Complex geology conditions lead to many fuzzy characters in measure-well curves. In the combination of all kinds of fuzzy conditions, oil water-flooded behaves as strong water-flooded, middle water-flooded, weak water-flooded and no water-flooded, etc. NFNN is applied to water-flooded identification in oil well measure-well to find its mapping relation between well measure-well and water-flooded level,accordingly realize the water-flooded zone identification in measure-well explanation of fuzzy oil. Test results illustrate its practicability
Song, Kaoping; Xu, Shaohua; Liang, Jiuzhen; and Li, Ronghua, "A Normalized Fuzzy Neural Network and its Application" (2001). ICEB 2001 Proceedings (Hong Kong, SAR China). 70.