Intelligent reservoir characterization using fuzzy logic: an example from the Kangan and Fahlian carbonate reservoirs in Southern Iran hydrocarbon Fields

pereability and rock types are the most important rock properties which can be used as input parameters to build 3D petrophysical models of hydrocarbon reservoir. As well as, log data of prime importance in acquring petrophysical data from hydrocabon reservoir. Reliable log analysis in the hydrocarbon resevoir requires a compelet set of logs. For any number of reasons such as incomplete logging in old wells, destruction of logas due to inappropriate data storage, and measurement errors due to logging tool problems hole conditions, log suites are either incomplete or not reliable. In this study, a fuzzy c-means (FCM) clustering technique was use to rock types classification based on porosity and permeability data. Then base on fuzzy inference system. Then a back propagationneural network with trainlm training function was applied to verify fuzzy results for permeability modeling. For this purpose, two wells of the Southern Iran Fields were chosen to construct intelligent models of the reservoir and a third well was used as a test well to evaluate the reliability of the models. The results of this study showed that fuzzy logic approach was successful for prediction of well logs, permeability and rock type in the studied reservoirs.

Keywords:

rocktypes , permeability , well logs , fuzzy logic , fuzzy c-means clustering , back propagation neural network , carbonate reservoir