Fuzzy model is applied for permeability estimation in heterogeneous oil reservoirs using core porosity and gamma ray logs. Also, the basic concepts of fuzzy model is described, and how to use the constructed model to analyze and interpret the results. Fuzzy logic approach is used to represent a nonlinear relationship as a smooth concatenation of local linear submodels. The partitioning of the input space into fuzzy regions, represented by the individual rules, is obtained through fuzzy clustering. The results from the fuzzy model shows that it is not only accurate but also provides some insight into the nonlinear relationship represented by the model. Whereas, the results of the blind test developed a good agreement between the measured core permeability and the output of the fuzzy model.

Keywords:
permeability prediction, core permeability, reservoir, artificial intelligence, information, membership function, algorithm, estimation, core porosity, input variable
Subjects:
Information Management and Systems, Artificial intelligence
Copyright 2004, Society of Petroleum Engineers
You can access this article if you purchase or spend a download.