Abstract
Abstract In this paper, a novel hybrid approach composed of adaptive neuro-fuzzy inference system (ANFIS) and imperialist competitive algorithm is proposed. The imperialist competitive algorithm (ICA) is used in this methodology to determine the most suitable initial membership functions of the ANFIS. The proposed model combines the global search ability of ICA with local search ability of gradient descent method. To illustrate the suitability and capability of the proposed model, this model is applied to predict oil flow rate of the wells utilizing data set of 31 wells in one of the northern Persian Gulf oil fields of Iran. The data set collected in a three month period for each well from Dec. 2002 to Nov. 2010. For the sake of performance evaluation, the results of the proposed model are compared with the conventional ANFIS model. The results show that the significant improvements are achievable using the proposed model in comparison with the results obtained by conventional ANFIS.
Highlights
Oil flow rate of the wells is effective parameters on reservoir behavior simulation, field development and production allocation
adaptive neuro-fuzzy inference system (ANFIS) uses the hybrid learning algorithm, which is a combination of gradient descent technique and the leastsquares method to determine the optimum value for the non-linear parameters of the membership functions and the linear parameters on the fuzzy rules, respectively
Simulation Results In the present work, ANFIS model combined with imperialist competitive algorithm (ICA) (ANFIS-ICA) was applied to predict oil flow rate of the wells by using the data set of 31 wells in one of the northern Persian Gulf oil fields of Iran
Summary
Oil flow rate of the wells is effective parameters on reservoir behavior simulation, field development and production allocation. Due to the complex nature of oilwater-gas three-phase flow in wells and pipes, the development, evaluation, and use of oil flow metering systems have been a major focus for the oil industry Result of this focus is two types meter: conventional methods and multiphase flow meters (MFMs). Temperature and pressure of lines which act important rule in production process from reservoir to production and separation unit is collected and stored from general existing sensor This set of data can be utilized as input to build a model to predict oil flow rate of the wells by soft computing techniques. ANFIS combines the self-learning ability of NN with the linguistic expression function of fuzzy inference[5] It uses a hybrid learning procedure which is a combination of the gradient descent technique and least-squares method to determine the optimal distribution of membership functions and rules parameters, respectively. The generation of fuzzy rules from numerical data or expert knowledge and adaptively construct a rule base makes this system very powerful in modeling numerous processes
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal of Computational Intelligence Systems
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
