Estimated ultimate recovery prediction of fractured horizontal wells in tight oil reservoirs based on deep neural networks

Luo, Shangui; Ding, Chao; Cheng, Huhu; Zhang, Boning; Zhao, Yulong; Liu, Lingfu

doi:10.46690/ager.2022.02.04

Cited by 26 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The misuses of the production rate distribution and horizontal well length would result in erroneous well and reservoir parameter interpretations. (2) The second radial-flow regime, which occurs before the traditional horizontal radial-flow regime behaves as the pressure-derivative with the value of 0.5/N*, is seldom observed in the actual well interpretation.…”

Section: Introductionmentioning

confidence: 99%

“…Horizontal wells have proved to be an effective approach to improve well production due to its advantage of increasing the contact area with reservoir. , Because of the reservoir heterogeneity, nonuniform formation damage after production, selective completion, etc., the water injection or oil production rate changes dramatically along horizontal wellbore. The liquid production and water injection profile loggings are the important means to understand the formation characteristics of the production interval, which is a key work in oilfield development.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Evaluation of Liquid Production and Water Injection Profiles of Horizontal Well by Pressure-Transient Analysis: Field Cases

Wang,

Xie,

Gao

et al. 2023

Energy Fuels

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Evaluation of Liquid Production and Water Injection Profiles of Horizontal Well by Pressure-Transient Analysis: Field Cases

Wang,

Xie,

Gao

et al. 2023

Energy Fuels

View full text Add to dashboard Cite

“…With the rapid development of Deep Neural Networks (DNN), it not only facilitates life, but also affects people's thinking [1]. As one of the representative algorithms of DNN, CNN has unique characteristics of local data extraction and weight sharing, which makes it have unique scientific and technological advantages in image recognition.…”

Section: Introductionmentioning

confidence: 99%

An improved CNN algorithm for accelerating structural optimization with pulsating array

Xiao

2023

Second Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum (AIBDF 2022)

View full text Add to dashboard Cite

The rapid development of artificial intelligence has prompted the convolutional neural network (CNN) to process huge amount of data, which has caused a great burden on convolution operations. Therefore, according to the characteristics of the systolic array architecture, the acceleration structure of CNN is constructed by fusing it with CNN. Besides, it is optimized in practical application, and its effectiveness is verified. The experimental results show that in the broadcast architecture, the time required by the CNN acceleration architecture is at least 0.005, while the maximum throughput is 16.83, which is far higher than the acceleration architecture under the systolic array architecture. In the case of small change in the maximum frequency, the error rate is the same as that of the systolic array, which is about 3.62%. In the comparison of various methods proposed on the systolic array, the accuracy rate of CNN acceleration architecture is 94.7%, and the utilization rate is 81.95%. The correctness and effectiveness of the algorithm are proved. To sum up, the improved CNN acceleration structure based on pulse array optimization reduces the response time and meets the requirements of terminal calculation force, which is of high significance in practical application.

show abstract

“…Tight oil reservoirs are characterized by their low permeability and complex pore network, which severely hampers the flow of hydrocarbons and impedes conventional production methods. − A combination of horizontal drilling and hydraulic fracturing is used to create multiple fractures and increase production. − Despite the benefits of hydraulic fracturing, there are challenges to maintaining production levels, such as rapid declines, instability, and low primary recovery rates of 5–10%, with a significant portion of the oil remaining trapped in the reservoir matrix. − …”

Section: Introductionmentioning

confidence: 99%

Investigating Recovery Potential through Depletion Development of Tight Oil Reservoirs via NMR Technology

He,

Shang,

et al. 2023

Energy Fuels

View full text Add to dashboard Cite

Tight oil reservoirs have emerged as a vital component of the global energy landscape, offering both promising prospects and intricate challenges in their exploitation. Overcoming challenges to maintain sustainable production levels, including rapid declines, instability, and low primary recovery rates, is imperative. However, understanding the mechanisms behind production declines during the depletion development of tight oil reservoirs remains elusive. In this study, we employ nuclear magnetic resonance (NMR) online monitoring technology to quantitatively assess oil recovery on the pore scale and investigate the impacts of depletion development on tight oil reservoirs. Our experimental findings reveal a bimodal pore distribution within the target reservoir, characterized by a significant proportion of micronano pore throats measuring less than 0.1 μm in radius. A noteworthy nonlinear relationship exists between the T 2 relaxation time and pore throat radius within the tight reservoir core, enabling the derivation of rock pore distribution from T 2 spectra. Within these tight reservoirs, the recovery rate achieved solely through the utilization of formation energy during depletion development ranges from 7 to 10%. This finding underscores the substantial untapped potential for future oil recovery, with a significant volume of oil remaining trapped within the matrix. Our analysis indicates that primary oil extraction primarily targets macropores during depletion development, leaving the crude oil within the micropores largely undisturbed.

show abstract

Estimated ultimate recovery prediction of fractured horizontal wells in tight oil reservoirs based on deep neural networks

Abstract: L. Estimated ultimate recovery prediction of fractured horizontal wells in tight oil reservoirs based on deep neural networks.

Cited by 26 publications

References 22 publications

Evaluation of Liquid Production and Water Injection Profiles of Horizontal Well by Pressure-Transient Analysis: Field Cases

Evaluation of Liquid Production and Water Injection Profiles of Horizontal Well by Pressure-Transient Analysis: Field Cases

An improved CNN algorithm for accelerating structural optimization with pulsating array

Investigating Recovery Potential through Depletion Development of Tight Oil Reservoirs via NMR Technology

Contact Info

Product

Resources

About