Real-Time Reservoir Surveillance Utilizing Permanent Downhole Pressures - An
Operator's Experience

Chorneyko, David

doi:10.2523/103213-ms

Cited by 9 publications

(9 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To address the noise issue, Ouyang and Kikani (2002) used wavelet analysis to determine the noise level and handle outliers. And companies have been developing new data processing and management strategies to deal with the challenges brought by the volume of PDG data (Chorneyko, 2006).…”

Section: Previous Workmentioning

confidence: 99%

Applying Machine Learning Techniques to Interpret Flow Rate, Pressure and Temperature Data From Permanent Downhole Gauges

Tian

Horne

2015

SPE Western Regional Meeting

View full text Add to dashboard Cite

Permanent downhole gauges (PDGs) provide a continuous record of pressure, temperature, and sometimes flow rate during well production. The continuous record provides us rich information about the reservoir and makes PDG data a valuable source for reservoir analysis. It has been shown in previous work that the convolution kernel based data mining approach is a promising tool to interpret flow rate and pressure data from PDGs. The convolution kernel method denoises and deconvolves the pressure signal successfully without explicit breakpoint detection. However, the bottlenecks of computational efficiency and incomplete recovery of reservoir behaviors limit the application of the method to interpret real PDG data.In this paper, three different machine learning techniques were applied to flow rate -pressure interpretation. We formulated the problem into a linear regression on parameters that connect the nonlinear flow rate features with pressure targets. The linear process leads to a closed form solution, which speeds up the computation dramatically. Linear regression was shown to have the same learning quality as the convolution kernel method, and outperforms it with much less computational effort.Kernel ridge regression was applied to address the issue of incomplete recovery of reservoir behaviors. Kernel ridge regression utilizes the expanded features given by the kernel function to capture the more detailed reservoir behaviors, while controlling the prediction error using ridge regression. It was shown that kernel ridge regression recovers the full reservoir behaviors successfully, e.g. wellbore storage effect, skin effect, infinite-acting radial flow and boundary effect.Some potential uses of temperature data from PDGs are also discussed in this paper. Machine learning was shown to be able to model temperature and pressure data recorded by PDGs, even if the actual physical model is complex. This originates from the fact that by using features as an approximation, machine learning does not require perfect knowledge of the physical model. The modeling of pressure using temperature data was extended to two promising applications: pressure history reconstruction using temperature data, and the cointerpretation of temperature and pressure data when flow rate data are not available.

show abstract

Section: Previous Workmentioning

confidence: 99%

Applying Machine Learning Techniques to Interpret Flow Rate, Pressure and Temperature Data From Permanent Downhole Gauges

Tian

Horne

2015

SPE Western Regional Meeting

View full text Add to dashboard Cite

show abstract

“…The accelerating performance of digital devices (e.g., processors, storage, and bandwidth) is leading to waves of technological innovation that promise significant new capabilities for E&P firms. As a result, the industry is standing on the crest of the digital oil field of the future (DOFF), which will enable petro-professionals and field workers to benefit from total asset awareness on the ability to monitor and manage all Additionally, real-time drilling technology is leading to reductions in drilling costs by 5 to 15%, as drilling engineers are able to react to problems in a more informed and timely manner (Chorneyko, 2006).…”

Section: Digital Oil Field Of the Futurementioning

confidence: 99%

Pressure Transient Analysis Of Data From Permanent Downhole Gauges

et al. 2013

View full text Add to dashboard Cite

In recent years there has been a significant growth in the number of Permanent Downhole Measurement System (PDHMS) installations in oil and gas fields around the world, as PDHMS prices have been falling steadily and their reliability has also been increasing. However, the full benefits of this investment can only be realized when it is taken from simple surveillance and monitoring to a source for reservoir characterization. This study assesses the systems and workflows that have been put in place to transform the massive amounts of data, including pressure, flow rate and temperature, into actionable information to improve field development and performance. This study presents a dynamic real-time well testing workflow for utilizing data from from intelligent fields. It discusses the applicability of pressure transient analysis using I-Field data from Permanent Downhole Gauges to characterize reservoir and well performance. While seeking to develop an efficient workflow for the utilization of the real-time data for pressure transient analysis, the study also seeks to assess the effects of producing time, flow rate simplification, and data interruptions on the reliability of the analysis methods and results. Actual real-time pressure data from PDHMS, and flow rate data Multi-Phase Flow Meters (MPFM) were used in the analyses, to determine reservoir parameters and evaluate well performance. This study highlights some of the challenges in using real-time data from PDHMS and MPFM. A commercially available software product was used to filter, and manage the real-time data, as well as the modeling and analysis of the test data.

show abstract

“…Real-time use of Permanent Downhole Gauge Data -In-house tools and customized vendor products to improve transient analysis for high-frequency real-time data 5,6 .…”

Section: Retr -Reservoir Evaluation Time Reduction Is Proprietary Tecmentioning

confidence: 99%

An Enterprise-Wide Approach to Implementing ‘Digital Oilfield'

et al. 2008

View full text Add to dashboard Cite

Within ExxonMobil * , optimal "Digital Oilfield" opportunities are viewed as the application of digital technologies to improve and enhance existing, proven asset management processes, resulting in improved asset performance. This paper describes ExxonMobil's strategies, approaches, and examples of a consistent, systematic, global approach to applying advanced digital technology driven by the value added to established asset management processes.Advances in information technology have created unique opportunities to further improve asset performance, specifically complementing ExxonMobil core execution strategies emphasizing technology leadership, functional excellence, and globally-standard asset management processes. By standardizing desktop hardware and software, creating data systems including globally-standard datastores and tools to broadly access data and maintain data quality, and developing and applying new technology to integrate and automate work, digital technology now allows ExxonMobil to further leverage its global functional organization to more-seamlessly integrate and automate its standard asset management processes.

show abstract

Real-Time Reservoir Surveillance Utilizing Permanent Downhole Pressures - An Operator's Experience

Cited by 9 publications

References 12 publications

Applying Machine Learning Techniques to Interpret Flow Rate, Pressure and Temperature Data From Permanent Downhole Gauges

Applying Machine Learning Techniques to Interpret Flow Rate, Pressure and Temperature Data From Permanent Downhole Gauges

Pressure Transient Analysis Of Data From Permanent Downhole Gauges

An Enterprise-Wide Approach to Implementing ‘Digital Oilfield'

Contact Info

Product

Resources

About