Improved sensitivity based linear learning method for permeability prediction of carbonate reservoir using interval type-2 fuzzy logic system

This paper proposed an improved sensitivity based linear learning method (SBLLM) model through the hybridization of type-2 fuzzy logic systems (type-2 FLS) and SBLLM. The generalization abilities of the SBLLM often rely on whether the available dataset is free of uncertainties to ensure successful result, which means that its generalization capability is sometimes limited depending on the nature of the dataset. Type-2 FLS has been choosing in order to better handle uncertainties existing in datasets and in the membership functions (MFs) in the traditional type-1 fuzzy logic system (FLS). In the proposed method, the type-2 FLS is used to handle uncertainties in reservoir data so that the cleaned data from type-2 FLS is then passed to the SBLLM for training and then final prediction using testing dataset follows. Comparative studies have been carried out to compare the performance of the proposed hybrid system with that of the standard SBLLM. Empirical results from simulation show that the proposed improved hybrid model has greatly improved upon the performance of the standard SBLLM.

A schematic design framework for the proposed T2-SBLLM hybrid model for predicting permeability of carbonate reservoir.Figure optionsDownload as PowerPoint slideHighlights
► An improved sensitivity based linear learning method (SBLLM) has been proposed with the type-2 FLS in a hybrid framework.
► The proposed model is a combination of type-2 fuzzy logic system (T2) and SBLLM.
► The proposed hybrid framework serves as a better improvement over the classical SBLLM.
► The proposed model has also been used to predict permeability of carbonate reservoir using real industrial datasets.
► The proposed model is a viable tool for other reservoir problems such as porosity, history matching and lithofacies.