Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Results
Integrating Data Mining and Expert Knowledge for an Artificial Lift Advisory System
Vega, E. De (PEMEX AIB) | Sandoval, G.. (PEMEX AIB) | Garcia, M.. (PEMEX AIB) | Nunez, G.. (Schlumberger) | Al-Kinani, A.. (Schlumberger) | Holy, R. W. (Schlumberger) | Escalona, H.. (Schlumberger) | Mota, M.. (Schlumberger)
Abstract This paper describes a new workflow to accelerate and improve decisions regarding where and when to apply an artificial lift system in fields with a considerable number of active wells. The workflow deploys a hybrid combination of a user-driven expert system and a data-driven knowledge-capturing system calibrated with historic data. Both systems interact to determine the right point in time to support a particular well with an artificial lift system. In the case presented, the mature gas field has a large number of operating wells, with predominantly manual operating data entry and a long processing time for newly acquired data. Due to the rapid decline rate in many wells, however, quick decisions are needed to improve productivity and hence the economics of each individual well. During the first two phases of the project, the asset team focused on data collection and workflow automation to speed up well production surveillance operations (e.g., gas rate calculation, estimation of critical velocity, etc.) (Mota, 2007). This paper documents the third phase, which addresses the knowledge-capturing and advisory components of the solution. Mature fields typically have significant field and asset expertise and a huge amount of historic data. Both information sources—the expert documentation and historic data—can be integrated to investigate past decisions and identify an optimum approach to field interventions. This paper describes the setup and implementation of a hybrid model that combines expert knowledge from asset engineers with the new knowledge discovered through the latest data-mining technology. The resulting system is then implemented in a fully automated workflow that identifies which wells require artificial lift. The results from a case study in a North Mexico gas field are presented. The reservoir is highly compartmentalized and requires fracturing as a way to increment well productivity. The data-mining approach used in this study is a special visualization technique, the self-organizing map (SOM), and a clustering algorithm (Zangl, 2003). The model was trained with historic production data, well test data, and information about historic well intervention decisions. In addition, expert knowledge from the asset engineers was introduced. The combination of data and expert knowledge enabled fast and reliable identification of the optimal time to install an artificial lift system to increase production while also effectively managing costs. This system reduces the typical decision time from several days to a matter of hours. The automated workflow runs immediately after the data is acquired and provides a continuous, up-to-date, and ranked list of proposed wells for artificial lift analysis. When new decisions are taken, the model can be updated for future use. The rapid analysis and decision cycle reduces lost production and improves overall field and asset value.
- North America > Mexico (0.48)
- North America > United States > Texas > Coleman County (0.24)
- Information Technology > Data Science > Data Mining (1.00)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Rule-Based Reasoning (0.97)
- Information Technology > Artificial Intelligence > Machine Learning > Learning Graphical Models > Directed Networks > Bayesian Learning (0.69)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty > Bayesian Inference (0.47)
Abstract As organisations transition from concept and design to the deployment and operational phases of a Production Optimisation solution, they anticipate new levels of performance and possibilities. They plan for increased production from the ‘right’ wells, with production engineers and operators able to easily access information, share near-real-time views of the same issues, and make informed production decisions on a daily basis. The organisation may have accurately estimated the cost of the project design, build, deployment and implementation. But they may have assumed ongoing maintenance costs will primarily be the IT support needed for defect fixing and software release management. That narrow definition of support can lead to problems and ultimately, decreased confidence in the solution and jeopardise its sustainability and evolution. With a new solution, new roles must be defined to reinforce the relationship between day-to-day activities and their impact on performance metrics and business targets. Continuous improvement and solution enhancements should be sponsored by appropriate decision-makers, and management must recognise and champion the contributions of these new roles. Data quality issues may require diagnosis and follow-up, with different skill-sets mobilised to address them. Engineers must own the integrity of certain information - alarm levels, valid ranges, thresholds, and calculations. End users and support team must adopt a diagnostic process for identifying the type of follow-up needed to address issues. Simple and focused support metrics need to be devised and reviewed to insure that the support model returns the anticipated benefits.
- Information Technology > Communications > Collaboration (0.94)
- Information Technology > Architecture > Real Time Systems (0.88)
- Information Technology > Data Science > Data Quality (0.68)
Abstract The business of reliability management is to keep equipment up and running or available to run while managing the costs to operate and maintain it. Companies have made significant investments in condition-monitoring instrumentation and information infrastructure, but each firm will have a unique point of diminishing returns. Some companies have established centralized collaboration centers and have re-engineered their work processes in order to break through this diminishing- returns barrier. Others that are not yet ready to make the full change can apply five critical success factors observed in established collaboration centers that have demonstrated reliability-performance improvements: Putting equipment operating condition into context. Dynamic equipment requires views of mechanical condition in the context of the overall process. This applies both to rotating equipment and to processing equipment. Managing data by exception. The blizzard of data now available requires machine learning and management by exception to reduce data into usable information. Using both predictive analytics and deep diagnostics as complementary technologies that operate in different timeframes. Deep diagnostics include vibration signature analysis and cylinder performance analysis, while predictive analytics employs pattern recognition algorithms to detect minor events and anomalies. Communicating observations, diagnoses, recommendations, and learnings through collaboration tools. Such tools add value on multiple fronts that include knowledge transfer and equipment-specific learning such as Root Cause Analysis. Managing the findings in an asset-management system or collaboration system. This provides feedback for further improvement. A case-study example that uses predictive analytics will demonstrate these concepts, beginning at event detection and extending through diagnostics, collaboration, field action, and information consolidation. The direct deliverable is time: time for engineers to focus where they add most value, time to plan equipment outages that might otherwise have been unplanned, and time to produce oil and gas that might be lost to unplanned downtime.
Production Processes Integration for Large Gas Basin – Burgos Asset
Sandoval, G.. (PEMEX-AIB) | Martínez, F.. (PEMEX-AIB) | Cadena, A.. (PEMEX-AIB) | Bernal, H.. (PEMEX-AIB) | Vega, E. De (PEMEX-AIB) | Navarro, M.. (PEMEX-AIB) | García, M.. (PEMEX-AIB) | Leal, I.. (PEMEX-AIB) | Figón, L.. (PEMEX-AIB) | Zambrano, A.. (PEMEX-AIB) | Duran, J.. (PEMEX-AIB) | Rangel, M deL. (PEMEX-AIB) | Garza, E.. (PEMEX-AIB) | Corbellini, F.. (Schlumberger.) | Mota, M.. (Schlumberger.) | Escalona, H.. (Schlumberger.) | Aguilar, Y.. (Schlumberger.) | Corona, A.. (Schlumberger.) | Oca, A. Montes (Schlumberger.) | Tortolero, M.. (Schlumberger.) | Díaz, T.. (Schlumberger.) | Álvarez, N.. (Schlumberger.) | Montes, E.. (Schlumberger.) | Romero, E.. (Schlumberger.) | Suárez, A.. (Schlumberger.) | Romay, J.. (Schlumberger.) | Fuehrer, F.. (Schlumberger.) | Kinani, A. Al (Schlumberger.) | Holy, R.. (Schlumberger.) | Núñez, G.. (Schlumberger.) | Vernus, J.. (Schlumberger.)
Abstract This paper presents the advances in Production System Optimization for the largest gas field in Mexico. The Burgos Asset is a large gas brown field with reservoir characteristics like gas-loading backpressure, reduced permeability and tight gas formations where production declines rapidly. Due to the large number of wells (more than 3500 active wells) and the fact that 95% of the measured parameters are obtained by field operators, it is difficult to continuously monitor and to plan the usage of operational resources. To help solve this situation, PEMEX and the service company (Schlumberger) implemented a production surveillance system that gathers all operational information providing storage, quality control, and developed engineering processes to estimate gas rates and liquid loading, monitors KPI and detects anomalies in operational events. Implementation of this operational surveillance environment started in 2007, with a functionality that has been focused on monitoring KPI calculation and event analysis at well level. Due to the large number of wells and activities carried out by the Asset, the need arose to generate additional workflows that contribute to the production optimization process, candidate selection workflow for workover and artificial lift installation, allowing upscaling of the current solution to a level that supports the technical and economical decisions of the Asset. As part of this requirement the team took the initiative to incorporate workflows of candidate recognition for workover, de-bottlenecking and optimization of a particular set of facilities, allowing the Asset to take corrective action in these areas and to plan the recommendations accordingly. Additionally, as proof of concept, an intelligent candidate selection system was implemented for artificial lift installation opportunities, using artificial intelligence tools such as data mining, improving decisions and results. The initiatives mentioned above help to increase, validate and rank the Asset's diverse candidate basket and to integrate the economic constraints into the decision making process. The positive results that have been obtained in these focalized areas show a significant opportunity to be up scaled for the whole Asset.
- Energy > Oil & Gas > Upstream (1.00)
- Government > Regional Government > North America Government > Mexico Government (0.55)
- North America > Mexico > Tamaulipas > Burgos Basin > Burgos Field (0.98)
- North America > Mexico > Nuevo Leon > Burgos Basin > Burgos Field (0.98)
- North America > Mexico > Coahuila > Burgos Basin > Burgos Field (0.98)
- Production and Well Operations > Well Operations and Optimization (1.00)
- Production and Well Operations > Well & Reservoir Surveillance and Monitoring (1.00)
- Production and Well Operations > Artificial Lift Systems (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Artificial intelligence (1.00)
Abstract The petroleum industry is facing volatile energy prices, increasing government regulation and taxation, difficult operating environments, strict environmental, health, and safety demands and escalating competition. But the Digital Oilfield — a composite of people, processes and technologies — is enhancing the productivity and reducing the costs for exploration and production (E&P) workers and oilfield managers across the globe in leading companies. The essence of the Digital Oilfield is managing the entire process from exploration to production to facilities operations in an optimized, real-time way with the integration of all business partners – the operators, service companies, logistics providers, software & technology providers, and various governmental regulatory agencies. A key driver of the Digital Oilfield is the explosion of digital information that is created by real-time data gathering systems, new modeling and simulation tools, and information created by collaborating employees. Most E&P companies struggle with the management of this increasing volume of enterprise information. This information base includes data, information, and knowledge from the domains of finance, exploration, drilling, reservoir management, operations and maintenance. The management of this information is critical as it represents a huge investment in expensive oilfield equipment and skilled human resources. Effective operational decisionmaking requires information about current and past operations along with data stored in E&P and ERP systems. This paper describes the evolution of a new tool to access and integrate these diverse sources of information in the context of the work that field managers and engineers do every day. This paper is copyrighted by the Society of Petroleum Engineers.
- Management > Asset and Portfolio Management > Integrated asset modeling (1.00)
- Management > Asset and Portfolio Management > Field development optimization and planning (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Knowledge management (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Data integration (0.89)
Abstract BP has deployed early warning systems that monitor heavy machinery, markedly increasing the reliability, operational integrity, and performance of equipment in BP's operations. Early warning allows BP to more effectively schedule maintenance (with costs of planned maintenance typically being a fraction of the costs of emergency repairs) and plan to minimize any production loss during the work through reconfiguration and feed rerouting. The company's initial trial generated value of $2 million during the trial alone, at a cost of only $50,000. Additional trials provided further savings of almost $3 million through detections such as pump seal problems, failing instrumentation, control problems, and turbine fouling. These striking benefits led BP to plan a significant deployment across the company. In just over a year, BP has made significant implementations at more than half of its facilities in one business segment and online pilots in all other business areas. Millions of dollars have already been saved; BP's goal of significantly reducing unplanned maintenance is well on its way to being realized. Far fewer experts are required to spot developing problems than with traditional data monitoring methods, this can now be done by a skilled technician; so more problems are caught. Quick- win maintenance savings more than paid for the technologies in the first year, and the safety benefits in a potentially hazardous environment are priceless. BP's aggressive adoption of wired and novel wireless technology to capture more measurements has significantly increased the volume of data available. This wealth of data put BP in an even better position to leverage predictive analytics technology. The technologies’ data-driven approach has many advantages over the traditional trending or first principles models used in the past. It's generally faster to implement, easier to maintain, does not require sophisticated engineering knowledge, and makes use of a wealth of existing but unused data, representing a breakthrough in the area of equipment health.
- Production and Well Operations (1.00)
- Data Science & Engineering Analytics > Information Management and Systems > Data mining (0.74)
- Facilities Design, Construction and Operation > Processing Systems and Design > Compressors, engines and turbines (0.69)
- Facilities Design, Construction and Operation > Measurement and Control > Process control and automation (0.47)
- Information Technology > Data Science > Data Mining (1.00)
- Information Technology > Artificial Intelligence > Machine Learning (1.00)
- Information Technology > Communications > Networks (0.87)