Abstract
The unique power of type-2 fuzzy logic system is demonstrated in this work by using it to improve the prediction accuracy of permeability in a hybrid intelligent model system. A hybrid intelligent model through the hybridization of type-2 FLS (T2) and extreme learning machines (ELM) is presented and have been shown to considerably achieved improved performance over the constituent models. It is generally believed that a hybrid scheme performed better than any of its constituent model and this work has fully corroborated this established slogan in the field of machine learning and data mining. ELM, as a learning tool, have gained popularity due to its unique characteristics and performance. However, the generalization capability of ELM and other neural network based solutions often depend, to a large extent on the characteristics of the dataset, particularly on whether uncertainty is present in the dataset or not. This work proposes a hybrid system through the combination of type-2 fuzzy logic systems (type-2 FLS) and ELM, and then use it to predict permeability of carbonate reservoir. Type-2 FLS has been chosen to be a precursor to ELM in order to better handle uncertainties existing in datasets. The dataset first pass through the type-2 FLS for possible uncertainty handling and prediction and then the output from the type-2 FLS is then passed to the ELM for its training and then final prediction is done using the unseen testing dataset. Simulations have been carried out, using the built hybrid model, on different industrial permeability datasets obtained from middle Easter oil fields. Results from empirical studies show that the proposed hybrid system performed better than each of the constituent parts, though the improvement made over that of ELM performance is higher compared to that of type-2 FLS, possibly because type-2 FLS is originally adept at modeling uncertainties. Overall, the proposed scheme achieved improved permeability prediction accuracy thereby setting another unique area to be looked into in the quest to achieving better accurate predictions of other petro physical properties in the oil and gas field.
