Browsing by Autor "Francklin Rivas"

Now showing 1 - 11 of 11

Application of Linear and Partial Correlation Techniques to Enhance the Waterflooding Surveillance Process
(2013) M.. Villamizar; Francklin Rivas; G. A. Carvajal; F.. Md Adnan; A.. Kheterpal; S. Knabe; José Antonio Rodríguez García; A.. Al-Jasmi; Bader Al-Saad; H. K. Goel
Abstract Linear correlation techniques (LCTs) and partial correlation techniques (PCTs) are well known statistical techniques useful in generating smart workflows for real-time surveillance and monitoring processes, such as waterflooding. In real-time environments, which require short-term analysis (30-day cycling), traditional simulation techniques are less effective and take a considerable amount of CPU time. As an alternative and considering LCTs have been widely applied in the oil industry, to understand relationships between producer and injector wells, LCTs can provide rapid results and even predict expected water breakthrough in producer wells. This paper describes the use of the Pearson correlation coefficient (PCC), a statistical measurement that is very sensitive to linear relationships between water injection and producing wells, including correlations where one parameter is a nonlinear function of the other. While this technique can show high correlation between some variables that are unrelated and only small correlations between highly related variables, the use of PCC, in many cases, returns measurements concerning the joint behavior of two variables that are important to the decision-making process. This paper describes how PCC was used to clean noisy data generated in LCTs. This paper also describes the use of the PCT to detect the influence of other variables on the LCT-based results. The study was conducted on a mature, carbonate black-oil reservoir in the Middle East under waterflood. The LCT/PCT results were compared with streamline simulation, and some similarities were found between the streamline simulation well allocation factors and the LCT/PCT results. Regardless of local reservoir conditions, the results showed that LCTs/PCTs are powerful tools that can be used to quickly assess inter-dependencies among producing wells and associated injectors. Use of these tools can enable engineers to make prompt decisions to help prevent water breakthrough and adjust water injection rates.
Applying Analytics to Production Workflows: Transforming Integrated Operations into Intelligent Operations
(2014) César Bravo; José Antonio Rodríguez García; Luigi Saputelli; Francklin Rivas
Abstract Several industry technologies support integrated operations, such as intelligent completions, real-time systems, surface-sub- surface models, workflow automation systems, etc. Each of these technologies provides relevant data pertaining to one specific part of the asset. The integration, correlation, and analysis of this data (current and historic) help the operator to understand the current state of the asset, as well as make inferences about future behavior. Such capabilities are provided by a set of tools and techniques known within the industry as analytics. Operating and service companies are using new and improved analytics to support oil and gas operations and management processes. Additionally, several analytics commonly used in the foreign market are being applied to industry operations and management workflows. This has led to more robust and effective solutions for oil and gas production operations. However, the analytics value added is limited if implemented in an isolated fashion; the real value is obtained when analytics are immersed within comprehensive production workflows, which aid in analysis, processing, and modeling of the production process. Workflows enhanced using analytics can transform integrated operations into intelligent operations. This paper presents an analysis of the primary analytics techniques and how they have been applied to support intelligent operations. To support this analysis, several application examples of analytics in oil and gas intelligent operations are described, and several case studies of real applications of analytics are referenced.
ARQUITECTURA DE REFERENCIA PARA INTEGRACIÓN EN EMPRESAS DE PRODUCCIÓN INDUSTRIAL BASADA EN LA INTELIGENCIA ARTIFICIAL DISTRIBUIDA
(Springer Nature, 2010) Cristina Bravo Bravo; José Aguilar; Addison Ríos Bolívar; Joseph Aguilar Martín; Francklin Rivas
The inability to repair the damaged membrane may be one of the key mechanisms underlying the severe neuronal degeneration and overall functional loss seen in in vivo spinal cord injury and traumatic axonal injury in blunt head trauma. Promoting membrane resealing following damage may therefore constitute a potential effective therapeutic intervention in treating head trauma and spinal cord injuries. In our previous studies, we have shown that the axolemma failed to reseal following transection in clinically related situations, such as low extracellular calcium and low temperature. Our current studies indicate that DMSO is capable of rendering significant improvement in guinea pig axonal membrane resealing following transection in both 0.5 mM [Ca(2+)](0) and 25 degrees C situations. This was demonstrated physiologically by monitoring membrane potential recovery and anatomically by conducting HRP-exclusion assays 60 minutes after injury. Further, we have shown that the addition of DMSO in normal Krebs' solution (2 mM [Ca(2+)](0) and 37 degrees C) resulted in a decrease in membrane repair following injury. This indicates that DMSO-mediated membrane repair is sensitive to temperature and calcium. This study suggests the role of DMSO in axonal membrane resealing in clinically relevant conditions and raises the possibility of using DMSO in combination with other more established therapies in spinal cord injury treatment.
Automation of the Oilfield Asset via an Artificial Intelligence (AI)-Based Integrated Production Management Architecture (IPMA)
(2011) César Bravo; Luigi Saputelli; José Aguilar; Addison Ríos; Francklin Rivas; Joseph Aguilar-Martín
Abstract Integrated Asset Management (IAM) is highly complex and requires the combined effort of several disciplines and technological tools. The orchestration of disciplines, workflow tools, and available data are paramount issues in the oil and gas industry today. Resource negotiation, communication language, and decision-making protocols are minor issues that exacerbate the problem, resulting in poor and delayed decision making. This study approaches these challenges through the implementation of innovative, distributed artificial intelligence (AI)-based architecture, designed for automated production management. This architecture, known as the Integrated Production Management Architecture (IPMA), has three layers: a connectivity layer, which allows access to the process information sources; a semantic layer, which establishes an ontological framework to guarantee the process-information integrity during the data interchange process developed between the applications that belong to the Enterprise Technology Information Platform; and a management layer, which automates the production process workflows using oilfield multi-agent systems and electronic institutions. A virtual oilfield, based on a commercial-integrated production model (IPM) and history-matched data, was used to show the benefits of the proposed approach. The IPM had the following configuration: Three reservoirs, eight oil wells, one flow station, and several gathering pipelines. The IPMA's objective was to maximize asset revenue under different constraint scenarios and changing operational events. The reactive capacity of the architecture, the effective communication between the agents, and the proposed oilfield ontology were tested successfully. In this sense, the well function of the three layers of IPMA was demonstrated. This study also outlines the use of ontologies and AI techniques that are important factors in future developments of IT solutions for the oil production industry.
DESIGN OF AN INDUSTRIAL AUTOMATION ARCHITECTURE BASED ON MULTI-AGENTS SYSTEMS
(Elsevier BV, 2005) César Bravo; José Aguilar; Mariela Cerrada; Francklin Rivas
Methodological mark for technologic prospective
(2008) José Aguilar; Oswaldo Terán; Addison Ríos; Leandro León; Domingo Hernández; Francklin Rivas; Nelson Pérez; J. M. Gonzalez
"This work is aimed at presenting and exemplifying a methodology for performing exercises of technologic prospective. Such a methodology was developed in a practical application for conceptualizing the automation technological platform of a Venezuelan public organization. The paper focuses on describing the sequence of steps necessary for such an exercise. Additionally, the goal, activities and recommended tools for each step are specified. Aspects of the application on industrial automation are shown."
Short-Term Production Prediction in Real Time Using Intelligent Techniques
(2013) A.. Al-Jasmi; H. K. Goel; Hatem N. Nasr; M.. Querales; Jordani Rebeschini; M.. Villamizar; G. A. Carvajal; S. Knabe; Francklin Rivas; Luigi Saputelli
Abstract Intelligent digital oilfield operations collect real-time data from an operating asset and transform that raw data into information through intelligent, automated work processes, which assist engineers with key well operations and monitoring, improving their productivity and decision-making. A major oil and gas operator in the Middle East is developing a set of intelligent workflows for key activities and processes for its production operations, with the ultimate goal of improved asset performance. Real-time surveillance and monitoring of production operation processes have proven to be operationally and economically important for managing complex, high-cost reservoirs. However, predicting short-term production and production interruptions—for example, related to pump settings—has posed a tremendous challenge. While operators routinely forecast production for the next 60 to 90 days, sophisticated tools such as full-field numerical simulation models are of limited use in predicting short-term production of 30 days. Similarly, while nodal analysis can estimate current operating conditions, it cannot be used for prediction. Because of its simplicity, rapid training, and demonstrated results, a prediction technique using neural networks (NN) has emerged as a solution that can predict short-term well production behavior with acceptable accuracy. This paper presents a case study using NNs to predict liquid rate and water cut performance in a mature reservoir with more than 20% water cut. The NN was trained using available surface and down-hole, real-time production data, time-dependent data, and completion design data. The time-dependent data are included as time series configured to let users generate scenarios by changing well operations. This approach not only provides a base-case prediction but also simulates results after making adjustments in control variables, such as tubing head pressure (THP) and pump frequency. Changing THP and frequency lets users model production to predict and circumvent negative well pump events. This project was implemented in a mature carbonate oil reservoir under waterflood in the Middle East. Despite limited reservoir data, the results show that the NN is a powerful and rapid tool that predicts liquid rate and water cut with acceptable accuracy, helping engineers make prompt decisions to prevent and reduce downtime.
Sistema Inteligente para la Generación Automática de Contratos en el marco de la Ley de Contrataciones Públicas
(National Polytechnic School, 2019) Francklin Rivas; Marilena Asprino; Juan Sarache; Francisco León
Resumen: En este artículo se presenta el diseño de un sistema inteligente para la creación automática de contratos en el marco de la Ley de Contrataciones Públicas de Venezuela. El sistema está ajustado a la normativa vigente y considera elementos tales como el objeto del contrato, las partes otorgantes, los montos, los aportes sociales requeridos y las cláusulas que debe obligatoriamente contener cada contrato. Como aplicación se desarrolló un sistema web para su utilización en la Universidad de Los Andes, en Venezuela.  Palabras clave: Sistemas Inteligentes, Derecho Administrativo, Ley de Contrataciones Públicas, Gobierno Electrónico.
Sistemas multiagentes para la planificación y manejo de los factores de producción en automatización
(Universidad Autónoma del Estado de México, 2010) José Aguilar; Francklin Rivas; Mariela Cerrada Lozada; Jorge Chacal; César Bravo
"En este trabajo se propone un marco de referencia para tareas de planificación y manejo de los factores de producción en automatización. Después, dicho marco es modelado usando agentes, para lo cual se usa la metodología de especificación de agentes MASINA. Dicho modelo basado en agentes tiene características propias de estos sistemas, tales como auto- nomía y capacidades inteligentes en sus componentes, distribución de funciones y emergencia, entre otras."
State of the Art of Artificial Intelligence and Predictive Analytics in the E&P Industry: A Technology Survey
(2012) César Bravo; Luigi Saputelli; Francklin Rivas; Anna Gabriela Pérez; Michael Nikolaou; Georg Zangl; Neil de Guzmán; S. Mohaghegh; Gustavo Núñez
Abstract Artificial intelligence (AI) has been used for more than two decades as a development tool for solutions in several areas of the E&P industry: virtual sensing, production control and optimization, forecasting, and simulation, among many others. Nevertheless, AI applications have not been consolidated as standard solutions in the industry, and most common applications of AI still are case studies and pilot projects. In this work, an analysis of a survey conducted on a broad group of professionals related to several E&P operations and service companies is presented. This survey captures the level of AI knowledge in the industry, the most common application areas, and the expectations of the users from AI-based solutions. It also includes a literature review of technical papers related to AI applications and trends in the market and R&D. The survey helped to verify that (a) data mining and neural networks are by far the most popular AI technologies used in the industry; (b) approximately 50% of respondents declared they were somehow engaged in applying workflow automation, automatic process control, rule-based case reasoning, data mining, proxy models, and virtual environments; (c) production is the area most impacted by the applications of AI technologies; (d) the perceived level of available literature and public knowledge of AI technologies is generally low; and (e) although availability of information is generally low, it is not perceived equally among different roles. This work aims to be a guide for personnel responsible for production and asset management on how AI-based applications can add more value and improve their decision making. The results of the survey offer a guideline on which tools to consider for each particular oil and gas challenge. It also illustrates how AI techniques will play an important role in future developments of IT solutions in the E&P industry.
State of the Art of Artificial Intelligence and Predictive Analytics in the E&P Industry: A Technology Survey
(Society of Petroleum Engineers, 2013) César Bravo; Luigi Saputelli; Francklin Rivas; Anna Gabriela Pérez; Michael Nikolaou; Georg Zangl; Neil de Guzmán; S. Mohaghegh; Gustavo Núñez
Summary Artificial intelligence (AI) has been used for more than 2 decades as a development tool for solutions in several areas of the exploration and production (E&P) industry: virtual sensing, production control and optimization, forecasting, and simulation, among many others. Nevertheless, AI applications have not been consolidated as standard solutions in the industry, and most common applications of AI still are case studies and pilot projects. In this work, an analysis of a survey conducted on a broad group of professionals related to several E&P operations and service companies is presented. This survey captures the level of AI knowledge in the industry, the most common application areas, and the expectations of the users from AI-based solutions. It also includes a literature review of technical papers related to AI applications and trends in the market and in research and development. The survey helped to verify that (a) data mining and neural networks are by far the most popular AI technologies used in the industry; (b) approximately 50% of respondents declared they were somehow engaged in applying workflow automation, automatic process control, rule-based case reasoning, data mining, proxy models, and virtual environments; (c) production is the area most affected by the applications of AI technologies; (d) the perceived level of available literature and public knowledge of AI technologies is generally low; and (e) although availability of information is generally low, it is not perceived equally among different roles. This work aims to be a guide for personnel responsible for production and asset management on how AI-based applications can add more value and improve their decision making. The results of the survey offer a guideline on which tools to consider for each particular oil and gas challenge. It also illustrates how AI techniques will play an important role in future developments of information-technology (IT) solutions in the E&P industry.