Predição não-linear de curvas de produção de petróleo via redes neurais recursivas

One of the main activities in the petroleum engineering is to estimate the oil production in the existing oil reserves. The calculation of these reserves is crucial to determine the economical feasibility of your explotation. Currently, the petroleum industry is facing problems to analyze production due to the exponentially increasing amount of data provided by the production facilities. Conventional reservoir modeling techniques like numerical reservoir simulation and visualization were well developed and are available. This work proposes intelligent methods, like artificial neural networks, to predict the oil production and compare the results with the ones obtained by the numerical simulation, method quite a lot used in the practice to realization of the oil production prediction behavior. The artificial neural networks will be used due your learning, adaptation and interpolation capabilities

Implementação de um Módulo de Supervisão para um Sistema de Detecção de Vazamentos em Dutos de Petróleo

The transport of fluids through pipes is used in the oil industry, being the pipelines an important link in the logistics flow of fluids. However, the pipelines suffer deterioration in their walls caused by several factors which may cause loss of fluids to the environment, justifying the investment in techniques and methods of leak detection to minimize fluid loss and environmental damage. This work presents the development of a supervisory module in order to inform to the operator the leakage in the pipeline monitored in the shortest time possible, in order that the operator log procedure that entails the end of the leak. This module is a component of a system designed to detect leaks in oil pipelines using sonic technology, wavelets and neural networks. The plant used in the development and testing of the module presented here was the system of tanks of LAMP, and its LAN, as monitoring network. The proposal consists of, basically, two stages. Initially, assess the performance of the communication infrastructure of the supervisory module. Later, simulate leaks so that the DSP sends information to the supervisory performs the calculation of the location of leaks and indicate to which sensor the leak is closer, and using the system of tanks of LAMP, capture the pressure in the pipeline monitored by piezoresistive sensors, this information being processed by the DSP and sent to the supervisory to be presented to the user in real time

Caracterização ambiental de bancos areno-lamosos nos campos petrolíferos de Macau e Serra (RN), como subsídio às medidas mitigadoras ao processo erosivo

On Rio Grande do Norte northern coast the process of sediment transport are intensely controlled by wind and sea (waves and currents) action, causing erosion and shoreline morphological instability. Due to the importance of such coastal zone it was realized the multi-spectral mapping and physical-chemical characterization of mudflats and mangroves aiming to support the mitigating actions related to the containment of the erosive process on the oil fields of Macau and Serra installed at the study area. The multi-spectral bands of 2000 and 2008 LANDSAT 5 TM images were submitted on the several digital processing steps and RGB color compositions integrating spectral bands and Principal Components. Such processing methodology was important to the mapping of different units on surface, together with field works. It was possible to make an analogy of the spectral characteristics of wetlands with vegetations areas (mangrove), showing the possibility to make a restoration of this area, contributing with the environmental monitoring of that ecosystem. The maps of several units were integrated in GIS environment at 1:60,000 scale, including the classification of features according to the presence or absence of vegetation cover. Thus, the strategy of methodology established that there are 10.13 km2 at least of sandy-muddy and of these approximately 0.89 km2 with the possibility to be used in a reforestation of typical flora of mangrove. The physical-chemical characterization showed areas with potential to introduce local species of mangrove and they had a pH above neutral with a mean of 8.4. The characteristic particle size is sand in the fine fractions, the high levels of carbonate, organic matter and major and trace element in general are concentrated where the sediment had the less particles size, showing the high correlation that those elements have with smaller particles of sediment. The application of that methodological strategy is relevant to the better understanding of features behavior and physical-chemical data of sediment samples collected on field allow the analysis of efficiency/capability of sandy-muddy to reforestation with local mangrove species for mitigation of the erosive action and coastal processes on the areas occupied by the oil industry

Estudo paramétrico da recuperação de petróleo pesado por aquecimento eletromagnético resistivo

Electrical resistive heating (ERH) is a thermal method used to improve oil recovery. It can increase oil rate and oil recovery due to temperature increase caused by electrical current passage through oil zone. ERH has some advantage compared with well-known thermal methods such as continuous steam flood, presenting low-water production. This method can be applied to reservoirs with different characteristics and initial reservoir conditions. Commercial software was used to test several cases using a semi-synthetic homogeneous reservoir with some characteristics as found in northeast Brazilian basins. It was realized a sensitivity analysis of some reservoir parameters, such as: oil zone, aquifer presence, gas cap presence and oil saturation on oil recovery and energy consumption. Then it was tested several cases studying the electrical variables considered more important in the process, such as: voltage, electrical configurations and electrodes positions. Energy optimization by electrodes voltage levels changes and electrical settings modify the intensity and the electrical current distribution in oil zone and, consequently, their influences in reservoir temperature reached at some regions. Results show which reservoir parameters were significant in order to improve oil recovery and energy requirement in for each reservoir. Most significant parameters on oil recovery and electrical energy delivered were oil thickness, presence of aquifer, presence of gas cap, voltage, electrical configuration and electrodes positions. Factors such as: connate water, water salinity and relative permeability to water at irreducible oil saturation had low influence on oil recovery but had some influence in energy requirements. It was possible to optimize energy consumption and oil recovery by electrical variables. Energy requirements can decrease by changing electrodes voltages during the process. This application can be extended to heavy oil reservoirs of high depth, such as offshore fields, where nowadays it is not applicable any conventional thermal process such as steam flooding

Detecção de interface em tanques de petróleo usando transmissores de nível e controladores Fuzzy

This work presents a proposal to detect interface in atmospheric oil tanks by installing a differential pressure level transmitter to infer the oil-water interface. The main goal of this project is to maximize the quantity of free water that is delivered to the drainage line by controlling the interface. A Fuzzy Controller has been implemented by using the interface transmitter as the Process Variable. Two ladder routine was generated to perform the control. One routine was developed to calculate the error and error variation. The other was generate to develop the fuzzy controller itself. By using rules, the fuzzy controller uses these variables to set the output. The output is the position variation of the drainage valve. Although the ladder routine was implemented into an Allen Bradley PLC, Control Logix family it can be implemented into any brand of PLCs

Análise paramétrica da simulação composicional do processo de Drenagem Gravitacional Assistida por Gás (GAGD)

In Brazil and around the world, oil companies are looking for, and expected development of new technologies and processes that can increase the oil recovery factor in mature reservoirs, in a simple and inexpensive way. So, the latest research has developed a new process called Gas Assisted Gravity Drainage (GAGD) which was classified as a gas injection IOR. The process, which is undergoing pilot testing in the field, is being extensively studied through physical scale models and core-floods laboratory, due to high oil recoveries in relation to other gas injection IOR. This process consists of injecting gas at the top of a reservoir through horizontal or vertical injector wells and displacing the oil, taking advantage of natural gravity segregation of fluids, to a horizontal producer well placed at the bottom of the reservoir. To study this process it was modeled a homogeneous reservoir and a model of multi-component fluid with characteristics similar to light oil Brazilian fields through a compositional simulator, to optimize the operational parameters. The model of the process was simulated in GEM (CMG, 2009.10). The operational parameters studied were the gas injection rate, the type of gas injection, the location of the injector and production well. We also studied the presence of water drive in the process. The results showed that the maximum vertical spacing between the two wells, caused the maximum recovery of oil in GAGD. Also, it was found that the largest flow injection, it obtained the largest recovery factors. This parameter controls the speed of the front of the gas injected and determined if the gravitational force dominates or not the process in the recovery of oil. Natural gas had better performance than CO2 and that the presence of aquifer in the reservoir was less influential in the process. In economic analysis found that by injecting natural gas is obtained more economically beneficial than CO2

Influência da areia argilosa na recuperação de petróleo por injeção de vapor

Continuous steam injection is one of heavy oil thermal recovery methods used in the Brazilian Northeast because of high occurrence of heavy oil reservoir. In this process, the oil into the reservoir is heated while reduces, substantially, its viscosity and improves the production. This work analyzed how the shaly sand layers influenced in the recovery. The studied models were synthetics, but the used reservoir data can be extrapolated to real situations of Potiguar Basin. The modeling was executed using the STARS - Steam Thermal and Advanced Process Reservoir Simulator - whose version was 2007.10. STARS is a tool of CMG Computer Modeling Group. The study was conducted in two stages, the first we analyzed the influence of reservoir parameters in the thermal process, so some of these were studied, including: horizontal permeability of the reservoir and the layer of shaly sand, ratio of horizontal permeability to vertical permeability, the influence of capillary pressure layer of shaly sand and as the location and dimensions of this heterogeneity can affect the productivity of oil. Among the parameters studied the horizontal permeability of the reservoir showed the most significant influence on the process followed by diversity. In the second stage three models were selected and studied some operational parameters such as injection rate, distance between wells, production time and completion intervals. Among the operating parameters studied the low rate and intermediate distances between wells showed the best recoveries

Estimação e compensação de não linearidades inerentes aos atuadores dos processos industriais

The oscillations presents in control loops can cause damages in petrochemical industry. Canceling, or even preventing such oscillations, would save up to large amount of dollars. Studies have identified that one of the causes of these oscillations are the nonlinearities present on industrial process actuators. This study has the objective to develop a methodology for removal of the harmful effects of nonlinearities. Will be proposed an parameter estimation method to Hammerstein model, whose nonlinearity is represented by dead-zone or backlash. The estimated parameters will be used to construct inverse models of compensation. A simulated level system was used as a test platform. The valve that controls inflow has a nonlinearity. Results and describing function analysis show an improvement on system response

Correlações nos dfa de diversos perfis geológicos. estudo de caso: Bacia de Campos - RJ

This work aims to study the fluctuation structure of physical properties of oil well profiles. It was used as technique the analysis of fluctuations without trend (Detrended Fluctuation Analysis - DFA). It has been made part of the study 54 oil wells in the Campo de Namorado located in the Campos Basin in Rio de Janeiro. We studied five sections, namely: sonic, density, porosity, resistivity and gamma rays. For most of the profiles , DFA analysis was available in the literature, though the sonic perfile was estimated with the aid of a standard algorithm. The comparison between the exponents of DFA of the five profiles was performed using linear correlation of variables, so we had 10 comparisons of profiles. Our null hypothesis is that the values of DFA for the various physical properties are independent. The main result indicates that no refutation of the null hypothesis. That is, the fluctuations observed by DFA in the profiles do not have a universal character, that is, in general the quantities display a floating structure of their own. From the ten correlations studied only the profiles of density and sonic one showed a significant correlation (p> 0.05). Finally these results indicate that one should use the data from DFA with caution, because, in general, based on geological analysis DFA different profiles can lead to disparate conclusions

Análise do desempenho de um queimador infravermelho funcionando com gás liquefeito de petróleo e glicerina

The use of infrared burners in industrial applications has many advantages in terms of technical-operational, for example, uniformity in the heat supply in the form of radiation and convection, with greater control of emissions due to the passage of exhaust gases through a macro-porous ceramic bed. This paper presents an infrared burner commercial, which was adapted an experimental ejector, capable of promoting a mixture of liquefied petroleum gas (LPG) and glycerin. By varying the percentage of dual-fuel, it was evaluated the performance of the infrared burner by performing an energy balance and atmospheric emissions. It was introduced a temperature controller with thermocouple modulating two-stage (low heat / high heat), using solenoid valves for each fuel. The infrared burner has been tested and tests by varying the amount of glycerin inserted by a gravity feed system. The method of thermodynamic analysis to estimate the load was used an aluminum plate located at the exit of combustion gases and the distribution of temperatures measured by a data acquisition system which recorded real-time measurements of the thermocouples attached. The burner had a stable combustion at levels of 15, 20 and 25% of adding glycerin in mass ratio of LPG gas, increasing the supply of heat to the plate. According to data obtained showed that there was an improvement in the efficiency of the 1st Law of infrared burner with increasing addition of glycerin. The emission levels of greenhouse gases produced by combustion (CO, NOx, SO2 and HC) met the environmental limits set by resolution No. 382/2006 of CONAMA

Simulador de dano à formação, aplicado ao Projeto e à execução da perfuração de poços de petróleo

With the high oil price variability, the petroleum and the reservoir engineers are usually face to face on how they can evaluate the well performance and productivity. They can improve high productivity from the well construction to the secondary recoveries, but they have never tried a measurement in the drilling operations about the lower productivity index. As a rule, frequently the drilling operations hear from the reservoir engineering and geology that, if there is a formation damage, probably some drilling operations practices were not done properly or the good practice in petroleum engineering or mud engineering were not observed. The study in this working search is an attempt of how to measure a formation damage just from the project drilling to the drilling operations, with datum from the fields in Brazilian northeast and putting into practice a Simulator developed from the modeling on the theory offered by different experts and sources in formation damage

Incorporação de resíduo cerâmico para prevenção da retrogressão da resistência de cimentos de poços de petróleo submetidos à injeção de vapor

Steam injection is the most used thermal recovery method of oil nowadays because of the high degree of development of the technique that allows high recovery factors. However, injection of superheated steam into the reservoir affects the entire structure of the well, including the cemented layer that presents a retrogression of compressive strength and increases the permeability due to formation of more crystalline and denser phases at temperatures above 110 °C. These changes result in failures in the cement that favor the entrance of formation fluids into the annulus space resulting in unsafe operations and restrictions in the economic life of the well. But the strength retrogression can be prevented by partial replacement of cement by silica-based materials that reduce the CaO/SiO2 ratio of cement slurries changing the trajectory of the reactions, converting those deleterious phases in phases with satisfactory mechanical strength and permeability. The aim of this study was to evaluate the behavior of a ceramic waste material rich in silica in partial and total substitution of a mineral additive used to fight the strength retrogression of cement slurries subjected to high temperatures. The evaluation was made by compression, X-ray diffraction (XRD) and thermogravimetry (TG/DTG). The samples were submitted to a cycle of low temperature (38 °C) for 28 days and a cycle of low temperature followed by exposure to 280 ºC and 1000 psi by 3 days. The results showed that slurries with additions of up to 30% of the waste material are not enough to prevent the strength retrogression, while slurries with additions of the waste material combined with silica flour in various proportions produced hydrated products of low Ca/Si ratios that maintained the compressive strength at satisfactory levels

Controle preditivo neural aplicado à processos petroquímicos

A pesquisa tem como objetivo desenvolver uma estrutura de controle preditivo neural, com o intuito de controlar um processo de pH, caracterizado por ser um sistema SISO (Single Input - Single Output). O controle de pH é um processo de grande importância na indústria petroquímica, onde se deseja manter constante o nível de acidez de um produto ou neutralizar o afluente de uma planta de tratamento de fluidos. O processo de controle de pH exige robustez do sistema de controle, pois este processo pode ter ganho estático e dinâmica nãolineares. O controlador preditivo neural envolve duas outras teorias para o seu desenvolvimento, a primeira referente ao controle preditivo e a outra a redes neurais artificiais (RNA s). Este controlador pode ser dividido em dois blocos, um responsável pela identificação e outro pelo o cálculo do sinal de controle. Para realizar a identificação neural é utilizada uma RNA com arquitetura feedforward multicamadas com aprendizagem baseada na metodologia da Propagação Retroativa do Erro (Error Back Propagation). A partir de dados de entrada e saída da planta é iniciado o treinamento offline da rede. Dessa forma, os pesos sinápticos são ajustados e a rede está apta para representar o sistema com a máxima precisão possível. O modelo neural gerado é usado para predizer as saídas futuras do sistema, com isso o otimizador calcula uma série de ações de controle, através da minimização de uma função objetivo quadrática, fazendo com que a saída do processo siga um sinal de referência desejado. Foram desenvolvidos dois aplicativos, ambos na plataforma Builder C++, o primeiro realiza a identificação, via redes neurais e o segundo é responsável pelo controle do processo. As ferramentas aqui implementadas e aplicadas são genéricas, ambas permitem a aplicação da estrutura de controle a qualquer novo processo

Pastas compósitas cimento/sílica/polímero para cimentação de poços de baixa profundidade sujeitas à injeção de vapor

The production of heavy oil fields, typical in the Northeastern region, is commonly stimulated by steam injection. High bottom hole temperatures are responsible not only for the development of deleterious stresses of the cement sheath but also for cement strength retrogression. To overcome this unfavorable scenario, polymeric admixtures can be added to cement slurries to improve its fracture energy and silica flour to prevent strength retrogression. Therefore, the objective of the present study was to investigate the effect of the addition of different concentrations of polyurethane (5-25%) to cement slurries containing 40% BWOC silica flour. The resulting slurries were characterized using standard API (American Petroleum Institute) laboratory tests. In addition to them, the mechanical properties of the slurries, including elastic modulus and microhardness were also evaluated. The results revealed that density, free water and stability of the composite cement/silica/polyurethane slurries were within acceptable limits. The rheological behavior of the slurries, including plastic viscosity, yield strength and gel strength increased with the addition of 10% BWOC polyurethane. The presence of polyurethane reduced the fluid loss of the slurries as well as their elastic modulus. Composite slurries also depicted longer setting times due to the presence of the polymer. As expected, both the mechanical strength and microhardness of the slurries decreased with the addition of polyurethane. However, at high bottom hole temperatures, the strength of the slurries containing silica and polyurethane was far superior than that of plain cement slurries. In summary, the use of polyurethane combined with silica is an interesting solution to better adequate the mechanical behavior of cement slurries to heavy oil fields subjected to steam injection

Estudo do comportamento de pastas compósitas cimento/sílica/poliuretana para poços de petróleo HPHT

Os poços HPHT atravessam zonas anormalmente pressurizadas e com altos gradientes de temperatura. Esses poços apresentam elevadas concentrações de tensões produzidas pelas operações de perfuração e fraturamento hidráulico, flutuações da pressão e temperatura, forças dinâmicas geradas durante a perfuração, formações inconsolidadas, entre outros aspectos, podendo resultar em falhas mecânicas na bainha de cimento. Tais falhas comprometem a estabilidade mecânica do poço e o isolamento das zonas produtoras de óleos e/ou gás. Para que operações corretivas não se façam necessárias, é preciso adequar as pastas às condições de cada poço. Sistemas de pastas de cimento para poços HPHT requerem um bom controle de suas propriedades termo-mecânicas. Visto que a temperaturas superiores a 110 oC (230 oF) o cimento, após alcançar um valor máximo de resistência, inicia um processo de perda de resistência (retrogressão). Para prevenir esse efeito substitui-se parcialmente o cimento Portland por sílica com objetivo de incrementar a reação pozolânica. Esta reação modifica a trajetória do processo natural de hidratação do cimento, o gel de silicato de cálcio hidratado (C-S-H) se converte em várias outras fases com maior resistência. Polímeros também são adicionados para proporcionar maior flexibilidade e agir como barreira à propagação de trincas desenvolvidas sob tensão. O presente trabalho teve como objetivo estudar o comportamento do sistema cimento/sílica/polímero quando submetido às condições de alta temperatura e alta pressão. Foram formuladas pastas de cimento puro, pastas contendo 40 % BWOC de sílica flour e pastas com diferentes concentrações de poliuretana (5 % a 25 %) e 40 % BWOC de sílica flour. O peso específico das pastas foi fixado em 1,87 g/cm3 (15,6 lb/gal). Os resultados demonstram que as resistências da pasta contendo 40% de sílica e das com adição de polímero foram muito superiores a da pasta de cimento puro, não ocorrendo o efeito da retrogressão. As pastas com polímero apresentaram um crescente aumento da tenacidade com o aumento da concentração da mesma, sendo assim capaz de suportar as tensões. Além de se manterem estáveis termicamente acima de 180 ºC. O sistema também apresentou excelentes resultados de filtrado, reologia, água livre, estabilidade e permeabilidade. Sendo assim, o mesmo mostrou ser aplicável a poços HPHT