Abstract: Two-phase fluid has complex flow characteristic and the accurate identification of flow regime is the basis of the accurate measurement of two-phase flow’s parameter，as a result，the on-line intelligent identification of flow regime is an important role of two-phase flow research.Based on electrical resistance tomography system and oil-water two phase flow regime，the feature of measurement data is extracted by the method of wavelet packet analysis，then the extracted data will be taken as input information of radial basis function neural network，both the model and the simulation are made for neural network.Experiment simulation analysis shows this method is very suitable for flow regime identification，and can attain a purpose of identification of flow regime effectively.