Data Driven Gas Well Performance Model Hands Back Control to Engineers

2021 ◽  
Author(s):  
Cornelis Veeken
Keyword(s):  
Real Time ◽  
Performance Model ◽  
Data Driven ◽  
Production Data ◽  
Performance Parameters ◽  
Well Performance ◽  
Gas Well ◽  
Reservoir Performance ◽  
Fit For Purpose ◽  
Over Time

Abstract This paper presents a fit-for-purpose gas well performance model that utilizes a minimum set of inflow and outflow performance parameters, and demonstrates the use of this model to describe real-time well performance, to compare well performance over time and between wells, and to generate production forecasts in support of well interventions. The inflow and outflow parameters are directly related to well-known reservoir and well properties, and can be calibrated against common well surveillance and production data. By adopting this approach, engineers develop a better appreciation of the magnitude and uncertainty of gas well and reservoir performance parameters.

scholarly journals Data-Driven Dispatching Rules Mining and Real-Time Decision-Making Methodology in Intelligent Manufacturing Shop Floor with Uncertainty

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4836
Author(s):  
Liping Zhang ◽  
Yifan Hu ◽  
Qiuhua Tang ◽  
Jie Li ◽  
Zhixiong Li
Keyword(s):  
Decision Making ◽  
Data Base ◽  
Real Time ◽  
Manufacturing Industry ◽  
Job Shop ◽  
Data Driven ◽  
Dispatching Rules ◽  
Shop Floor ◽  
Production Data ◽  
Online Decision Making

In modern manufacturing industry, the methods supporting real-time decision-making are the urgent requirement to response the uncertainty and complexity in intelligent production process. In this paper, a novel closed-loop scheduling framework is proposed to achieve real-time decision making by calling the appropriate data-driven dispatching rules at each rescheduling point. This framework contains four parts: offline training, online decision-making, data base and rules base. In the offline training part, the potential and appropriate dispatching rules with managers’ expectations are explored successfully by an improved gene expression program (IGEP) from the historical production data, not just the available or predictable information of the shop floor. In the online decision-making part, the intelligent shop floor will implement the scheduling scheme which is scheduled by the appropriate dispatching rules from rules base and store the production data into the data base. This approach is evaluated in a scenario of the intelligent job shop with random jobs arrival. Numerical experiments demonstrate that the proposed method outperformed the existing well-known single and combination dispatching rules or the discovered dispatching rules via metaheuristic algorithm in term of makespan, total flow time and tardiness.

Integrated Automation and Data-Driven Workflow for CO2 Project Management – Case Study from a Smart Oil Field in the Middle-East

2021 ◽  
Author(s):  
Erismar Rubio ◽  
Mohamed Yousef Alklih ◽  
Nagaraju Reddicharla ◽  
Abobaker Albelazi ◽  
Melike Dilsiz ◽  
...  
Keyword(s):  
Project Management ◽  
Real Time ◽  
Reservoir Management ◽  
Oil Field ◽  
Data Driven ◽  
Co2 Injection ◽  
Well Performance ◽  
Potential Cost ◽  
Integrated Automation ◽  
Well Pattern

Abstract Automation and data-driven models have been proven to yield commercial success in several oil fields worldwide with reported technical advantages related to improved reservoir management. This paper demonstrates the implementation of an integrated workflow to enhance CO2 injection project performance in a giant onshore smart oil field in Abu Dhabi. Since commissioning, proactive evaluation of the reservoir management strategy is enabled via smart-exception-based surveillance routines that facilitate reservoir/pattern/well performance review and supporting the decision making process. Prolonging the production sustainability of each well is a key pillar of this work, which has been made more quantifiable using live-tracking of the produced CO2 content and corrosion indicators. The intensive computing technical tasks and data aggregation from different sources; such as well testing and real time production/injection measurements; are integrated in an automatic workflow in a single platform. Accordingly, real-time visualizations and dashboards are also generated automatically; to orchestrate information, models and multidisciplinary knowledge in a systematic and efficient manner; allowing engineers to focus on problematic wells and giving attention to opportunity generation in a timely manner. Complemented with numerical techniques and other decision support tools, the intelligent system data-driven model assist to obtain a reliable short-term forecast in a shorter time and help making quick decisions on day-to-day operational optimization aspects. These dashboards have allowed measuring the true well/pattern performance towards operational objectives and production targets. A complete set of KPI's has helped to identify well health-status, potential risks and thus mitigate them for short/long term recovery to obtain an optimum reservoir energy balance in daily bases. In case of unexpected well performance behaviors, the dashboards have provided data insights on the root causes of different well issues and thus remedial actions were proposed accordingly. Maintaining CO2 miscibility is also ensured by having the right pressure support around producers, taking proactive actions from continues evaluation of producer-injector connectivity/interdependency, improving injection/production schedule, validating/tuning streamline model based on surveillance insights, avoiding CO2 recycling, optimizing data acquisition plan with potential cost saving while taking preventive measures to minimize well/facility corrosion impact. In this work, best reservoir management practices have been implemented to create a value of 12% incremental oil recovery from the field. The applied methodology uses an integrated automation and data-driven modeling approach to tackle CO2 injection project management challenges in real-time.

Gas-Production-Data Analysis of Variable-Pressure-Drawdown/Variable-Rate Systems: A Density-Based Approach

2014 ◽  
Vol 17 (04) ◽  
pp. 520-529 ◽  
Author(s):  
Miao Zhang ◽  
Luis F. Ayala H.
Keyword(s):  
Data Analysis ◽  
Material Balance ◽  
Gas Production ◽  
Variable Pressure ◽  
Production Data ◽  
Variable Rate ◽  
Well Performance ◽  
Gas Well ◽  
Type Curves ◽  
Performance Forecasting

Summary This study demonstrates that production-data analysis of variable-bottomhole-flowing-pressure/variable-rate gas wells under boundary-dominated flow (BDF) is possible by use of a density-based approach. In this approach, governing equations are expressed in terms of density variables and dimensionless viscosity/compressibility ratios. Previously, the methodology was successfully used to derive rescaled exponential models for gas-rate-decline analysis of wells primarily producing at constant bottomhole pressure (Ayala and Ye 2013a, b; Ayala and Zhang 2013; Ye and Ayala 2013; Zhang and Ayala 2014). For the case of natural-gas systems experiencing BDF, gas-well-performance analysis has been made largely possible by invoking the concepts of pseudotime, normalized pseudotime, or material-balance pseudotime. The density-based methodology rigorously derived in this study, however, does not use any type of pseudotime calculations, even for variable-rate/variable-pressure-drawdown cases. The methodology enables straightforward original-gas-in-place calculations and gas-well-performance forecasting by means of type curves or straight-line analysis. A number of field and numerical case studies are presented to showcase the capabilities of the proposed approach.

scholarly journals Classification of Ventricular Arrhythmias Based on a Data Driven Approach

2021 ◽  
Author(s):  
Matthew Hotradat
Keyword(s):  
Real Time ◽  
Ventricular Arrhythmias ◽  
Data Driven ◽  
Term Therapy ◽  
Computationally Efficient ◽  
Therapy Options ◽  
Data Driven Approach ◽  
Efficient Data ◽  
Long Term Therapy ◽  
Over Time

Ventricular arrhythmias (VA) are dangerous pathophysiological conditions affecting the heart which evolve over time resulting in different manifestations such as ventricular tachycardia (VT), organized VF (OVF), and disorganized VF (DVF). Success of resuscitation for patients is greatly impacted by the type of VA and swift administration of appropriate therapy options. This thesis attempts to arrive at computationally efficient, data driven approaches for classifying and tracking VAs over time for two purposes: (1) ‘in-hospital’ scenarios for planning long-term therapy options, and (2) ‘out-of-hospital’ scenarios for tracking progression/segregation of VAs in near real-time. Using a database of 61 60-s ECG VA segments, maximum classification accuracies of 96.7% (AUC=0.993) and 87% (AUC=0.968) were achieved for VT vs. VF and OVF vs. DVF classification for ‘in-hospital’/offline analysis. Two near real-time approaches were also developed for ‘out-of-hospital’ VA incidents with results demonstrating the high potential to track VA progression and segregation over time.

Looking Glass

2012 ◽  
Vol 4 (1) ◽  
pp. 17-28
Author(s):  
Anni R. Coden ◽  
John R. Harrald ◽  
Michael Tanenblatt ◽  
Theresa Jefferson ◽  
Pamela Murray-Tuite
Keyword(s):  
Ad Hoc ◽  
Data Driven ◽  
Performance Parameters ◽  
Human In The Loop ◽  
Preparedness Planning ◽  
Financial Costs ◽  
Decision Support Framework ◽  
Driven System ◽  
Looking Glass ◽  
Over Time

Looking Glass enables the discovery of a city’s vulnerabilities in a scenario along with the exploration of alternative resolutions and their accompanying side effects. It is a tool for enabling city officials to bridge the silos defined by people, processes, and organizations; the decision support framework can be used to discover interdependencies between a city’s infrastructure elements, its protocols (procedures) and its people’s actions over time. It is a tool for preparedness planning for natural and man-made threats, providing visualization of scenarios as they unfold, allowing observation and measurement of the effects of ad-hoc decisions. Looking Glass is a dynamic data driven system where the data can be interactively manipulated with the human-in-the-loop module during simulation. In general, the key performance parameters are the time, resources, and cost of resolving an incident, both financial costs and the costs associated with the health, safety, and happiness of the population. A prototype was demonstrated to city and county officials who were excited about the benefits of Looking Glass for their organizations.

Sign in / Sign up

Export Citation Format

Share Document