BR 
EN The objective of the current work is to present the development of a Particle Tracking Velocimetry (PTV) algorithm for the analysis of oil drops behaviour in two-phase oil–water dispersions within a centrifugal pump impeller. The drop tracking was realized through high-speed camera images in a transparent pump prototype, which enabled the visualization of oil drops dispersed in water in all the impeller channels. The PTV algorithm is based on deep-learning techniques for image processing. The drops are detected by a combined U-Net and Convolutional Neural Network (CNN) method, with the former generating a binary image and the latter detecting valid oil drop contours. After detection, the Labelled Object Velocimetry (LOV) is adopted to calculate the instantaneous oil drop velocity. A synthetic image generator based on a Generative Adversarial Network (GAN) is then developed to assess the results from the U-Net, CNN, and LOV models. Additional validation studies are performed using the results from Perissinotto et al. (2019a). The results reveal that the presented deep-learning PTV algorithm is robust and provides consistent and reliable data for the dispersed oil phase in two-phase oil–water flows.
Mês: outubro 2023
Utilizing integrated artificial intelligence for characterizing mineralogy and facies in a pre-salt carbonate reservoir, Santos Basin, Brazil, using cores, wireline logs, and multi-mineral petrophysical evaluation
In complex carbonate reservoirs, it is crucial to understand the connections between reservoir compositions (minerals, facies, and properties). Conventionally, core samples have been used to measure reservoir parameters and identify minerals and facies. However, core samples are limited to certain wells. Therefore, additional techniques are necessary to overcome this limitation comprehensively. This study aims to identify key mineralogical and facies components of the Barra Velha Formation (BVR) and their relation to reservoir parameters. Dolomite, calcite, quartz, and clay minerals were commonly found using X-ray Diffraction (XRD). By employing multi-mineral (MM) petrophysical evaluations, we accurately recreated mineral quantities from XRD and petrophysical properties from core analysis to ensure reliability. Replications of inputs well logs and the mineralogical volume from spectroscopic (ECS) were used as reliability techniques for validating the MM. A total of 47 wells were analyzed using those methods. In this study, the classification of facies was accomplished through the selection of three prominent supervised artificial intelligence techniques, among which SOM, a widely employed method for facies estimation, was included. Additionally, the ensemble methods of Random Forest and XGBoost were adopted due to their recognized efficacy in handling tabular data and their track record of success in machine learning and artificial intelligence competitions. Remarkably, the performance evaluation revealed that Random Forest and XGBoost algorithms outperformed SOM, yielding the most favorable outcomes in this context. An integrated analysis of mineralogical and facies results was conducted, incorporating production data and special profiles such as nuclear magnetic resonance (NMR) and Wellbore Image (WBI) to identify vug-containing areas. The dolomitic facies exhibited favorable reservoir qualities, influenced by diagenetic processes represented by vuggy porosity, which enhanced permeability. Shrubstones, spherulites, and reworked facies showed superior petrophysical qualities and were connected with productive regions, leading to elevated dolomite concentrations, and vuggy abundance. The study highlights two major innovations: the use of mineralogical volume from multi-mineral assessments as inputs for AI-based property estimation to improve facies estimates, and the discovery of relationships between facies, minerals, and reservoir properties, compared to production data. This understanding allows for more accurate static model creation, optimal production interval selection, improved hydrocarbon recovery, and better specification of stimulation processes.
The Golem: A general data-driven model for oil & gas forecasting based on recurrent neural networks
Oil & gas forecasting is one of the most critical issues in reservoir management. Physics-based simulations are the most common models used for production forecasts in oilfields. Previous works based on Machine Learning (ML) developed models focused on the oil rate as the unique target variable, forecasting by one-day output, and just one class of reservoir (synthetic or actual). This work introduces a general data-driven model based on Recurrent Neural Networks to forecast an adaptive sequence of timestamps for the complete production rates (oil, gas, and water), and we also included the well-bore pressure as a target variable, for both classes of reservoirs as actual as synthetic. The first dataset was obtained from the synthetic benchmark UNISIM-II-H, which simulates a carbonate reservoir in the Brazilian pre-salt; the second dataset is from an actual reservoir, the Volve oilfield, a decommissioned reservoir in the Norwegian North Sea. The forecasting is calculated using an input sequence of daily values from the historical record of the production rates and the pressure; the output is also a set of the values to the next sequence of days for one selected production variable (oil, gas, water, or pressure). The size of both input and output sets is adaptive and its adjustment depends on the dataset size and the production time. We built the model and compared it between the Long Short-Term Memory (LSTM) and the Gated Recurrent Unit (GRU) implementations. We tuned the architectural parameters of the model, the input size of historical records, and the output forecasting days. We performed the training/testing procedures with several sizes for the training dataset from the target well-bore and tested with the remaining data to evaluate the model stability. We adopted the Symmetric Mean Absolute Percentage Error (SMAPE) and the coefficient of determination r-square (R2) metrics to compare our forecasting values to the production rates and the pressure, most of the results for both synthetic and actual oilfields exhibited that the model can follow an accurate trend of the production rates and the pressure, and the output values are approximated. Forecasting values from the designed model exhibited closer values when compared to the expected data from the well-bores in most of the experiments, some cases exhibited a SMAPE lower than 2 and R2 up to 0.99. The model can learn the behavior of each production variable in the training stage and the forecasting output can be adapted for a set of several timestamps.
Phase inversion identification in Electrical Submersible Pumps using mechanical vibrations
Electric Submersible Pumps (ESPs) are multistage centrifugal pumps used in the artificial lift and transport of multiphase fluid mixtures. The flow regime is a liquid–liquid flow when the fluids correspond to two non-miscible fluids. Liquid–liquid flow is a mixture with a continuous and dispersed phase. As the amount of fluid in the dispersed phase increases, the dispersed phase suddenly becomes continuous and vice-versa. This transition phenomenon is called phase inversion. The flow regimes in oil–water mixtures are oil-in-water (o/w) and water-in-oil (w/o) flow regimes. This work demonstrates a correlation between the flow regime and the flow-induced vibration (FIV) in ESP operating with an oil–water mixture. This research proposes a novelty method to flow regime identification based on the Root Mean Square (RMS) of the vibration acceleration of the Fast Fourier Transform (FFT) signal.
The experimental setup consists of an 8-stage Electrical Submersible Pump (ESP) and a vibration acquisition system with six accelerometers uniformly distributed along the ESP. The experimental procedure consists of changing the water cut (percentage of water) from the oil flow regime to the water flow regime, maintaining stable ESP rotational speed, the total flow rate, and the oil viscosity. For each water cut, mechanical vibration is collected. The operational conditions consider 30, 40, and 50 Hz rotational speeds and viscosities between 70 and 210 cP.
Frequency domain analysis involves studying FFT between 0 and 5000 Hz, considering different water cuts and frequency ranges. Statistical features – mean, variance, geometric mean harmonic mean, and RMS – were extracted from the FFT for each frequency range. Results showed a strong correlation between the RMS of FFT and the phase inversion phenomena considering the rotational speed. A logistic regression model was employed to establish a transition boundary between oil-in-water and water-in-oil using 10% of the data. The model successfully separated at least 95.67% of the remaining data in the least favorable scenario.
Paleokarst features in the Aptian carbonates of the Barra Velha Formation, Santos Basin, Brazil
Seismic data, borehole image logs, and conventional well logs were used to investigate the distribution and characteristics of paleokarst features in the Aptian carbonates of the Barra Velha Formation in a pilot area of the Santos Basin, Brazil. Multiple seismic attributes were used to enhance details on the seismic data and highlight key seismic parameters including strata deformation and geometry, continuity of seismic events, and fault patterns. The study found that karst structures are controlled by faults and fractures along structural highs, which served as a conduit for the flow of dynamic fluids that dissolved the carbonate materials. Several closed, circular depressions and bright spots identified in the northeastern portion of the study area represent possible sinkhole structures. Epigenic and hypogenic processes due to the action of meteoric water, hydrothermal activity, and intra-formation acidity along regional unconformities in the Barremian-Aptian may have been responsible for the dissolution. Limitations of this study are related to the dificulty of integrating multiple datasets with various scales. However, the higher confidence for the occurrence of the karst features is provided by borehole images at the sub-seismic scale. The findings of this study hold significant relevance for the strategic planning of energy development and carbon sequestration initiatives in the Brazilian continental margins, thereby aiding in informed decision-making.
Particle image velocimetry in a centrifugal pump: Details of the fluid flow at different operation conditions
Centrifugal pumps are present in the daily life of human beings. They are essential to several industrial processes that transport single- and multi-phase flows with the presence of water, gases, and emulsions, for example. When pumping low-viscous liquids, the flow behavior in impellers and diffusers may affect the centrifugal pump performance. For these flows, complex structures promote instabilities and inefficiencies that may represent a waste of energetic and financial resources. In this context, this paper aims at characterizing single-phase water flows in one complete stage of a centrifugal pump to improve our understanding of the relationship between flow behavior and pump performance. For that, a transparent pump prototype was designed, manufactured and installed in a test facility, and experiments using particle image velocimetry (PIV) were conducted at different conditions. The acquired images were then processed to obtain instantaneous flow fields, from which the flow characteristics were determined. Our results indicate that the flow morphology depends on the rotational speed of the impeller and water flow rate: (i) the flow is uniform when the pump works at the best efficiency point (BEP), with streamlines aligned with the blades, and low vorticity and turbulence in the impeller; (ii) the velocity field becomes complex as the pump begins to operate at off-design conditions, away from BEP. In this case, velocity fluctuations and energy losses due to turbulence increase to higher numbers. Those results bring new insights into the problem, helping validate numerical simulations, propose mathematical models, and improve the design of new impellers.
Optimization of design variables and control rules in field development under uncertainty: A case of intelligent wells and CO2 water alternating gas injection
This paper focuses on life-cycle optimization of oil field development plan under uncertainty. The optimization problem included a wide range of design variables and control rules related to wells and platform in a realistic benchmark case (UNISIM–II–D) with a known ground truth reservoir model, UNISIM–II–R, that resembles Brazilian pre-salt fractured carbonate reservoirs in their early development stage. The design variables were the number and location of wells, the fluid processing capacity of the platform, and the location of internal control valves (ICVs), whereas the control rules were the setting of ICVs, production and injection rates, and the duration of the water-alternating-gas (WAG-CO2) cycle. An iterative sequential optimization framework was developed to deal with the massive search space and complex parameterization. The optimization further took into consideration the subsurface, operational and economic uncertainties, and used iterative discrete Latin hypercube method as the search algorithm. The robust optimization was carried out on a subset of representative models derived from the reduction of a large ensemble of data-assimilated models. As a low-fidelity representation of the compositional fluid model, a black-oil model was used to reduce simulation runtime. To validate our optimization framework, we applied the optimal development strategy to the ensemble of compositional simulation models, as well as the ground truth model. The true model’s responses were within the ranges predicted by the compositional ensemble, confirming the optimization framework’s reliability. The general methodology developed in this study, as well as our findings, can be used to optimize other similar real-world complex and high-risk field development projects, and are especially useful in closed-loop field development and management practices.
Minicurso: Integrated Reservoir and Production Modeling
Nos dias 16,17 e 23 de novembro de 2023 será oferecido pelo EPIC o minicurso intitulado “Integrated Reservoir and Production Modeling“, que abordará diversos aspectos envolvidos na integração das atividades de engenheiros de reservatórios, elevação, escoamento e de processamento primário.
As aulas serão ministradas por professores do Programa de Pós-graduação em Ciência e Engenharia de Petróleo (CEP/Unicamp) e da Equinor Noruega. O minicurso será totalmente online e ministrado em língua inglesa.
Esta será uma ótima oportunidade para mergulhar em um tema-chave e multidisciplinar e aprender mais sobre o eCalc™, uma ferramenta de software de código aberto para cálculo da demanda de energia e emissões de gases de efeito estufa (GEE) da produção e processamento de petróleo e gás.
Interessados deverão realizar sua pré-inscrição, até o dia 03 de novembro de 2023, pelo seguinte link:
Para mais informações, consulte o programa do minicurso, disponível em: