Estimation of fluid permeability of reservoir rocks at great depths using the fuzzy linear regression method

Abstract

The possibility of using the theory of fuzzy sets is considered. research in assessing the reserves of hard-to-recover deep-immersed hydrocarbons. At the same time, taking into account the complexity of the relationships between individual petrophysical characteristics, on the one hand, and the uncertainty of relevant information, on the other hand, fuzzy logic and flexible computing methods have been found to be more effective. In particular, the data clustering method (Sugeno fuzzy models) with the selection of child functions (membership functions) was tested. In this method, the prediction of the properties of reservoir rocks at great depths is based on a fuzzy linear regression reflecting the interdependence of properties and the natural uncertainty of information. The method was tested on real indicators of the quality of reservoirs of a well-known group of deposits in the Baku archipelago in Azerbaijan. The results of predicting the expected quality indicators of reservoirs at great depths indicate that in the section of the studied fields at depths of more than 4900 m, a decrease in the relative clay content and density of the reservoirs can be expected, but an increase in the permeability for liquid fluids is also possible. Ketwords: deep-seated; hard-to-recover hydrocarbon reserves; fuzzy set theory; reservoir quality prediction.