Using Intelligent System for Reservoir Properties Estimation

摘要

Reservoir description for simulation studies requires good knowledge of the permeability. Reliable permeability is only available from laboratory tests on cores, which are usually taken from a small percentage of the wells. In an offshore gas field only three wells have core data and all wells have full set of conventional log data. By using concept of hydraulic flow unit, statistical methods and intelligent systems is made a model for estimation of reservoir properties. Graphical statistical methods are applied for classification of hydraulic flow units. The Sugeno-type of fuzzy inference system conjunction with back-propagation network and subtractive clustering is used for prediction of flow zone indicator, permeability is then calculated from mean flow zone indicator value and corresponding porosity.