Toward mechanistic understanding of Fast SAGD process in naturally fractured heavy oil reservoirs: Application of response surface methodology and genetic algorithm

Mohammadi, Kaveh; Ameli, Forough

doi:10.1016/j.fuel.2019.05.070

Cited by 26 publications

(12 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gong et al [25][26][27] studied the influence of the reservoir conditions, such as the rhythm, interlayer, thief formation, and fractures, on the development effect of fast SAGD using numerical simulations. Nguyen et al [24,[28][29][30][31] optimized the pattern shape of fast SAGD, the offset horizontal well pretreatment, start-up method, and production time.…”

Section: Introductionmentioning

confidence: 99%

Simulation and Production Optimization on Enhanced Oil Recovery during the Middle and Late Period for SAGD Development in Ultraheavy Oil Reservoirs with Interlayers

Zhang

Zhou

et al. 2022

Geofluids

View full text Add to dashboard Cite

Previous studies on the technique for using the remaining oil are incomplete and inaccurate according to the position of the interlayer of the Steam-Assisted Gravity Drainage (SAGD) technique, and comparative studies of infilled horizontal wells are lacking. In this study, the SAGD well pair in the superheavy oil reservoir in the Z block in the Xinjiang Oilfield, China, was taken as an example. According to the reservoir’s geological parameters and production parameters, a typical well group geological model was created for the first time. The model divided the well groups in block Z into three categories according to the position of the interlayer, the production degree of the horizontal section, the oil recovery ratio, and the available degree of reserve control. According to the geological classification results, different typical well groups without an interlayer, with an interlayer located above the steam injection well, and with an interlayer located between the well pairs were classified and analyzed using numerical simulations. This was the first time the infilled horizontal well technique was compared with the infilled vertical well-assisted SAGD technique. In addition, the steam chamber connection law of the infilled vertical well-assisted SAGD was clarified. The results show that for reservoirs without an interlayer, the use of infilled horizontal well-assisted SAGD could speed up the lateral connection of the steam chambers and reduce the residual oil saturation. For reservoirs with a low production degree in the horizontal section and that are affected by an interlayer, an infilled vertical injector could be used with the assisted SAGD technique to increase the oil recovery by 5%–13%. The results of this study provided strong guidance for the next step in using enhanced oil recovery techniques to achieve traditional SAGD production from superheavy oil reservoirs with an interlayer.

show abstract

Section: Introductionmentioning

confidence: 99%

Simulation and Production Optimization on Enhanced Oil Recovery during the Middle and Late Period for SAGD Development in Ultraheavy Oil Reservoirs with Interlayers

Zhang

Zhou

et al. 2022

Geofluids

View full text Add to dashboard Cite

show abstract

“…In addition, the global search ability of these algorithms is very strong, so compared with the approximate gradient algorithms, the probability of obtaining the global optimum of nonconvex problems is greatly enhanced. Therefore, intelligent optimization algorithms have been widely used in multiparameter optimization problems in the oil and gas industry in recent years [9,10].…”

Section: Introductionmentioning

confidence: 99%

Parameter Optimization Study of Gas Hydrate Reservoir Development Based on a Surrogate Model Assisted Particle Swarm Algorithm

Zhang

Xin

et al. 2022

Geofluids

View full text Add to dashboard Cite

Using surrogate model to assist parameter optimization of oil and gas reservoir development can greatly reduce the call times of numerical simulator and accelerate the optimization process. However, for serial simulators or parallel simulators with low speedup ratio, the conventional method is still time-consuming. Firstly, an improved surrogate model assisted particle swarm optimization (PSO) algorithm was proposed in this paper. Then, the performance of the algorithm was analyzed using the Rastrigin function. Finally, the key operation parameters of a gas hydrate reservoir by depressurization−to−hot−water−flooding method were optimized with the new method. The results show that the new method only affects the update of the global optimal particle without interfering with the calculation process of the local optimal particles at the early stage of optimization. It realizes the rapid addition of the particle samples through the good parallel features of the PSO algorithm, and therefore, improve the precision of surrogate model in a short time. At the late stage of optimization, it is transformed into a local surrogate model to achieve rapid convergence, when the training time of the surrogate model exceeds the calculation time of the simulator. Both the optimization of Rastrigin function and operation parameters of gas hydrate development reveal that the new algorithm greatly reduces the number of iterations under the same accuracy and thus successfully accelerates the optimization process.

show abstract

“…As long as a sufficient amount of good-quality data are available, numerical reservoir simulation, as a robust physics-based tool, has been an effective approach for predicting the performance of the SAGD process over its entire life cycle. 12 However, as the numerical reservoir model becomes more complex, the resources that are necessary become considerably high. As a result, computationally more efficient data-driven models become valuable and more practical.…”

Section: Introductionmentioning

confidence: 99%

Machine-Learning Approach for Forecasting Steam-Assisted Gravity-Drainage Performance in the Presence of Noncondensable Gases

Canbolat¹,

Artun

2022

ACS Omega

View full text Add to dashboard Cite

Steam-assisted gravity drainage (SAGD) is an effective enhanced oil recovery method for heavy oil reservoirs. The addition of certain amounts of noncondensable gases (NCG) may reduce the steam consumption, yet this requires new design-related decisions to be made. In this study, we aimed to develop a machine-learning-based forecasting model that can help in the design of SAGD applications with NCG. Experiments with or without carbon dioxide (CO 2 ) or n -butane ( n -C 4 H 10 ) mixed with steam were performed in a scaled physical model to explore SAGD mechanisms. The model was filled with crushed limestone that was premixed with heavy oil of 12.4° API gravity. Throughout the experiments, temperature, pressure, and production were continuously monitored. The experimental results were used to train neural-network models that can predict oil recovery (%) and cumulative steam–oil ratio (CSOR). The input parameters included injected gas composition, prior saturation with CO 2 or n -C 4 H 10 , separation between wells, and pore volume injected. Among different neural-network architectures tested, a 3-hidden-layer structure with 40, 30, and 20 neurons was chosen as the forecasting model. The model was able to predict oil recovery and CSOR with R 2 values of 0.98 and 0.95, respectively. Variable importance analysis indicated that pore volume injected, distance between wells, and prior CO 2 saturation are the most critical parameters that would affect the performance, in agreement with the experiments.

show abstract

Toward mechanistic understanding of Fast SAGD process in naturally fractured heavy oil reservoirs: Application of response surface methodology and genetic algorithm

Cited by 26 publications

References 37 publications

Simulation and Production Optimization on Enhanced Oil Recovery during the Middle and Late Period for SAGD Development in Ultraheavy Oil Reservoirs with Interlayers

Simulation and Production Optimization on Enhanced Oil Recovery during the Middle and Late Period for SAGD Development in Ultraheavy Oil Reservoirs with Interlayers

Parameter Optimization Study of Gas Hydrate Reservoir Development Based on a Surrogate Model Assisted Particle Swarm Algorithm

Machine-Learning Approach for Forecasting Steam-Assisted Gravity-Drainage Performance in the Presence of Noncondensable Gases

Contact Info

Product

Resources

About