A Multistage Theoretical Model To Characterize the Liquid Level During Steam-Assisted-Gravity-Drainage Process

Yang, Yang; Huang, Shijun; Liu, Yang; Song, Qianlan; Wei, Shaolei; Xiong, Hao

doi:10.2118/183630-pa

Cited by 25 publications

(7 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reasons behind are that first ANN can analyze a bunch of data to uncover the hidden pattern and relationships [45]. Second, EOR methods are widely used in unconventional reservoirs to improve oil recovery [2,5,[46][47][48][49][50][51][52], changing their work conditions frequently and leading to a more complicated well production performance. TSA is a good method to handle this issue because the stock markets have used this technique to predict the stock price for a long time [53].…”

Section: Geofluidsmentioning

confidence: 99%

Well Performance from Numerical Methods to Machine Learning Approach: Applications in Multiple Fractured Shale Reservoirs

Liu

Kim

et al. 2021

Geofluids

View full text Add to dashboard Cite

Horizontal well fracturing technology is widely used in unconventional reservoirs such as tight or shale oil and gas reservoirs. Meanwhile, the potential of enhanced oil recovery (EOR) methods including huff-n-puff miscible gas injection are used to further increase oil recovery in unconventional reservoirs. The complexities of hydraulic fracture properties and multiphase flow make it difficult and time-consuming to understand the well performance (i.e., well production) in fractured shale reservoirs, especially when using conventional numerical methods. Therefore, in this paper, two methods are developed to bridge this gap by using the machine learning technique to forecast well production performance in unconventional reservoirs, especially on the EOR pilot projects. The first method is the artificial neural network, through which we can analyze the big data from unconventional reservoirs to understand the underlying patterns and relationships. A bunch of factors is contained such as hydraulic fracture parameters, well completion, and production data. Then, feature selection is performed to determine the key factors. Finally, the artificial neural network is used to determine the relationship between key factors and well production performance. The second is time series analysis. Since the properties of the unconventional reservoir are the function of time such as fluid properties and reservoir pressure, it is quite suitable to apply the time series analysis to understand the well production performance. Training and test data are from over 10000 wells in different fractured shale reservoirs, including Bakken, Eagle Ford, and Barnett. The results demonstrate that there is a good match between the available and predicated well performance data. The overall R values of the artificial neural network and time series analysis are both above 0.8, indicating that both methods can provide reliable results for the prediction of well performance in fractured shale reservoirs. Especially, when dealing with the EOR field cases, such as huff-n-puff miscible gas injection, Time series analysis can provide more accurate results than the artificial neural network. This paper presents a thorough analysis of the feasibility of machine learning in multiple fractured shale reservoirs. Instead of using the time-consuming numerical methods, it also provides a more robust way and meaningful reference for the evaluation of the well performance.

show abstract

Section: Geofluidsmentioning

confidence: 99%

Well Performance from Numerical Methods to Machine Learning Approach: Applications in Multiple Fractured Shale Reservoirs

Liu

Kim

et al. 2021

Geofluids

View full text Add to dashboard Cite

show abstract

“…The stable interlayer can divide the thick reservoir into several relatively independent flow units. At present, injection steam for thermal recovery is the main way to improve oil recovery in heavy oil reservoirs (Wang et al, 2006;Zhu et al, 2011;Liu et al, 2012;Ajay, 2012;Huang et al, 2013;Khansari et al, 2014;Liu, 2015;Liu et al, 2015;Sheikholeslami et al, 2016;Hou et al, 2016;Yang et al, 2016;Ma and Liu, 2018;Zhong et al, 2015;Xiong et al, 2017). Interlayer affects fluid seepage by affecting the development and expansion of steam chamber (Zhou et al, 2006;Wang et al, 2009), which has a vital impact on the thermal effect of thick heavy oil reservoirs.…”

Section: Introductionmentioning

confidence: 99%

Quantitative research on the influence of interlayer to thermal recovery horizontal wells in thick oil reservoir

Liu¹,

Liu²,

Zhang³

et al. 2019

J. Petroleum Gas Eng.

View full text Add to dashboard Cite

At present, the effect of different development patterns of interlayer like the length and the longitudinal position of interlayer on thermal recovery modes such as steam stimulation (CSS) and steam flooding (SF) is still a qualitative understanding, and there is no systematic study yet. Therefore, it is difficult to control the thermal production of thick oil reservoirs according to different interlayer patterns. In order to quantitatively analyze the influence of interlayer distribution pattern on steam huff and puff and steam flooding of horizontal wells in thick heavy oil reservoir, a numerical simulation model was established based on typical parameters of LD21 heavy oil reservoir in Bohai in China. Through comparison and research on the different modes of development longitudinal position, development length and development scale in non-permeable interlayer and semi-permeable interlayer. The influence of interlayer on the expansion law of steam chamber and ultimate oil recovery degree during steam huff and puff and steam flooding, and the main controlling factors of interlayer influencing oil recovery were obtained. The research results can be used for reference to optimize the location of thermal wells in thick heavy oil reservoir and reduce the influence of interlayer on thermal production effect of horizontal wells.

show abstract

“…Many processes of exploiting heavy oil have been developed and improved, such as water flooding, chemical flooding, thermal recovery, and microbial recovery (Sheikholeslami et al, 2016). Among a variety of enhanced oil recovery technologies, the thermal recovery technology has been widely used for heavy oil reservoirs (Khansari et al, 2014;Hou et al, 2016a, b), such as steam assisted gravity drainage(SAGD) (Yang et al, 2016), steam flooding (SF) (Zhao et al, 2013;Mahood et al, 2016) and cyclic steam stimulation (CSS) (Hou and Chen, 1997;Escobar et al, 2000;Bao et al, 2016), cyclic multi-thermal fluids stimulation (Hou et al, 2016c;Kuigian, 2018;Liu et al, 2018;Dong et al, 2014a, b;Dong et al, 2016). Nowadays, CSS and SF are known as the most widely used and mature technologies (Dong et al, 2012).…”

Section: Introductionmentioning

confidence: 99%

A statistical approach to investigate oil displacement efficiency in thermal recovery techniques for heavy oil based on one-dimensional core experiment

Dong¹,

Su²,

Ge³

et al. 2019

J. Petroleum Gas Eng.

View full text Add to dashboard Cite

Precise description of displacement efficiency (E d) is extremely important for evaluating the performance, economic effectiveness and final recovery of thermal recovery techniques. Current researches mainly focused on one-dimensional core displacement experiment, and it is difficult to obtain precise E d beyond the range of test points. In addition, there are two ways to improve the E d for thermal flooding: Increasing injection pore volume (PV) or raising injection temperature (T), it's hard to make decisions. In this study, the above two problems were solved by a statistical approach research. At the beginning, one dimensional core displacement experiment was carried out for hot water and steam, respectively. Then, dozens of curves and correlations about E d varied with injection PV number and injection temperature was regressed, respectively. Based on this, the formula of E d and PV, E d and T for injection hot water and steam was established respectively, which makes up for the shortage of the finite test data points. Next, chart of the E d between the PV and T was obtained. In addition, sensitivity analyses of injection rate and steam quality are discussed in this paper. Finally, the precise of the regression formula was verified by three steam flooding case of different heavy oil fields. The results indicated that, in order to get higher E d , higher injection PV and temperature are beneficial. With the E d chart, technicians can determine different schemes to improve oil displacement efficiency according to specific reservoir conditions. Besides, main production indexes such as oil recovery can be predicted quickly and precisely.

show abstract

A Multistage Theoretical Model To Characterize the Liquid Level During Steam-Assisted-Gravity-Drainage Process

Cited by 25 publications

References 9 publications

Well Performance from Numerical Methods to Machine Learning Approach: Applications in Multiple Fractured Shale Reservoirs

Well Performance from Numerical Methods to Machine Learning Approach: Applications in Multiple Fractured Shale Reservoirs

Quantitative research on the influence of interlayer to thermal recovery horizontal wells in thick oil reservoir

A statistical approach to investigate oil displacement efficiency in thermal recovery techniques for heavy oil based on one-dimensional core experiment

Contact Info

Product

Resources

About