In Petroleum Industry Petrophysical properties of reservoir consider as one of the most important parameters in the management, production, development and estimation of hydrocarbon reservoirs. These parameters are usually determined by methods such as core analysis and well testing which requires a lot of time and money and also due to lack of sufficient cores and petrography changes changes in the reservoir rock, determination of these parameters isn't very accurate with conventional methods. Therefore, the optimal method for reducing costs, time and increasing of the accuracy is using advanced softwares (Geolog) and prediction methods(artificial neural networks) which can have appropriate and accurate generalizability to the entire reservoirs of a field. Distinguish the types of electrofacies using different clustering algorithms and their use in facies modeling is one of the most important tasks of reservoir evaluation. In this study, petrophysical logs of Geolog software, artificial neural networks (MATLAB) and fuzzy logic carried out to predict these parameters in Reshadat Square precisely. Furthermore, better understanding of the reservoir, reducing the failure rate in facies studies and its reservoir the parameters was tried to select the most suitable clustering for the electrofacies. In this research, petrophysical logs including neutron, gamma, density and sonic were used to determine porosity by network and software. To obtain the water saturation, special resistance, neutron, density, and acoustic logs have been used. In addition, neural network tested in some of the wells in the field with core. Finally, the results estimated with 99% correlation coefficient approximately porosity. It was tried to achieve 11 electrofacies that have most consistent with geological characteristics and reservoir quality using a Multi-Resolution Graph-based Clustering method. The results of Geolog software are very effective in predicting petrophysical parameters. The determination of zones, stratigraphy, facies, petrophysical parameters (porosity, permeability, water and hydrocarbons saturation), and petrographyof the wells as well as continuous between the wells can be as the results of this research. In addition, the obtained results of the estimation of permeability artificial neural network, fuzzy and MRGC methods were compared with this case, the results of MRGC method was introduced as the best results. Also petrophysical analysis with probablity method shows a great deal of flexibility in data failure due to graphing problems and their uncertainty. Keywords: Geolog, Intelligent networks, Petrophysical parameters, Electrofacies