Banca de DEFESA: KALINE SOUZA DOS SANTOS

Uma banca de DEFESA de MESTRADO foi cadastrada pelo programa.
DISCENTE : KALINE SOUZA DOS SANTOS
DATA : 07/06/2019
HORA: 09:00
LOCAL: Núcleo de Pesquisas em Inovação em Tecnolgia da Informação - NPITI
TÍTULO:

INTELLIGENT SYSTEM FOR DECISION MAKING IN AN OIL FIELD SUBMITTED TO WATER INJECTION


PALAVRAS-CHAVES:

Intelligent System. Reinforcement Learning. Q-Learning Algorithm. Economic analysis.


PÁGINAS: 99
GRANDE ÁREA: Engenharias
ÁREA: Engenharia Elétrica
SUBÁREA: Eletrônica Industrial, Sistemas e Controles Eletrônicos
ESPECIALIDADE: Automação Eletrônica de Processos Elétricos e Industriais
RESUMO:

For the development of an oil field the operational solution is quite complex, due to the high amounts of variables involved in the process, such as: well spacing, well numbers, fluid injection system for supplementary recovery, among others. Thus, it is important to have an intelligent system that provides the evaluation of several production profiles for different representations in order to establish the optimal alternative from an economic perspective. This work presents the implementation and the application of an intelligent decision support system searching for alternatives for the development of an oil field, submitted to the water injection process, using reinforcement learning based on the Q-Learning algorithm. The modeling problem is characterized as a state machine in which each line of action is concerned with closing or reducing the initial water injection flow in the injector well of an oil field with characteristics similar to those found in the Brazilian Northeast. The implementation of the algorithm is to find, in conjunction with the mathematical simulator STARS (Steam Thermal and Advanced Processes Reservoir Simulator) from CMG (Computer Modeling Group), the optimal (or near-optimal) decision policy that provides the higher Net Present Value (NPV) of the production configurations from the initial investment cost, oil price, oil production and operating costs paid during the production time, thus increasing oil production in the reservoir, reducing decision-making time and providing the most affordable operational condition in economic terms. With the results, it was verified that in several cases the application of the action line allowed significant increases in NPV and in the Recovery Factor at the end of the project. In the case with a mesh size of 300 m, the Recovery Factor increased from 45.68% to 50.29%, an increase of almost 5 percentage points in the recovered oil volume. In the case of mesh size of 100 m and initial mesh layout of Five Spot Inverted Cross, the best line of action was to reduce the initial water injection rate by 1/3 (66.66 m³/d), thus obtaining a significant increase in NPV. In view of this, it is noted that operational interventions to change (close or reduce) the initial water injection flow in the well improve profitability, reducing the costs of injecting water, treating and disposing of the produced water and increasing the time feasibility of the project.


MEMBROS DA BANCA:
Presidente - 347628 - ADRIAO DUARTE DORIA NETO
Interno - 347559 - WILSON DA MATA
Externo ao Programa - 1754344 - MARCOS ALLYSON FELIPE RODRIGUES
Externo à Instituição - DANIEL LOPES MARTINS
Externo à Instituição - ROBERTO EVELIM PENHA BORGES
Notícia cadastrada em: 03/05/2019 10:22
SIGAA | Superintendência de Tecnologia da Informação - (84) 3342 2210 | Copyright © 2006-2024 - UFRN - sigaa04-producao.info.ufrn.br.sigaa04-producao