Universiti Teknologi Malaysia Institutional Repository

An hybrid model through the fusion of sensitivity based linear learning method and type-2 fuzzy logic systems for modeling PVT properties of crude oil systems

Abdul Raheem, Abdul Azeez and Selamat, Ali and Olatunji, Sunday Olusanya (2011) An hybrid model through the fusion of sensitivity based linear learning method and type-2 fuzzy logic systems for modeling PVT properties of crude oil systems. In: 2011 5th Malaysian Software Engineering Conference (MYSEC).

Full text not available from this repository.

Official URL: http://dx.doi.org/10.1109/MySEC.2011.6140697

Abstract

Sensitivity based linear learning method (SBLLM) has recently been used as predictive tool due to its unique characteristics and performance, particularly its high stability and consistency during predictions. However, the generalization capability of SBLLM is sometimes limited depending on the nature of the dataset, particularly on whether uncertainty is present in the dataset or not. In order to reduce the effects of uncertainties in SBLLM prediction and improve its generalization ability, this paper proposes a hybrid system through the unique combination of type-2 fuzzy logic systems (type-2 FLS) and SBLLM; thereafter the hybrid system was used to model PVT properties of crude oil systems. In the proposed hybrid, the type-2 FLS is used to handle uncertainties in reservoir data so that the final output from the 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 T2-SBLLM hybrid system with each of the constituent type-2 FLS and SBLLM. Empirical results from simulation show that the proposed T2-SBLLM hybrid model greatly improved upon the performance of SBLLM.

Item Type:Conference or Workshop Item (Paper)
Uncontrolled Keywords:Uncertainty, Reservoirs, Correlation, Predictive models, Sensitivity, Training, Learning systems, PVT properties, Hybrid intelligent systems, Type-2 fuzzy logic systems, Sensitivity based linear learning method (SBLLM), Feedforward neural networks
Subjects:T Technology > T Technology (General)
Divisions:Others
ID Code:45568
Deposited By: Haliza Zainal
Deposited On:10 Jun 2015 03:01
Last Modified:17 Jul 2017 06:50

Repository Staff Only: item control page