Estimation of minimum miscibility pressure during CO₂ flooding in hydrocarbon reservoirs using an optimized neural network

Abstract

CO2 flooding recovery strongly depends on the minimum miscibility pressure (MMP). Conventional tests to determine gas–oil MMP such as rising bubble apparatus and slim tube displacement are either costly or time consuming. In order to propose a quick and accurate model to determine MMP, a back-propagation neural network is presented for MMP prediction during pure and impure CO2 injections. Five new variables were screened as input parameters to the network. Next, the network was optimized using five evolutionary algorithms, and this work highlights that three of these evolutionary algorithms (e.g. Mind Evolutionary, Artificial Bee Colony, and Dragonfly) are firstly used to predict MMP. Then, data from the literature were input to the optimized network to train it. Statistical evaluation and graphical analyses were used to evaluate the performance of the proposed models and for comparison with published MMP correlates to obtain the optimal model for predicting MMP. The back-propagation model optimized using the dragonfly algorithm exhibited the highest accuracy among all those considered and MMP correlates; its coefficient of determination, average absolute percent relative error, root mean square error, and standard deviation were 0.965, 5.79%, 206.1, and 0.08, respectively. In addition, reservoir temperature was determined as the strongest MMP predictor (Pearson correlation = 0.63) based on sensitivity analysis.

Research on Minimum Miscible Pressure Between Crude Oil and Supercritical Carbon Dioxide System in Ultra-Low Permeability Reservoir by the Long-Slim-Tube Experiment Method

“…In the phase behavior simulation calculation method, the effect of CO 2 gas injected into the reservoir on crude oil properties is investigated by the phase behavior simulation technology, then the parameters of equation of state are adjusted by fitting PVT experimental data to establish a phase state model that conforms to the real fluid, and finally the MMP of oil and gas system is calculated by simulating the multistage contact experiment process. Artificial intelligence algorithm is a new MMP predicting method in recent years, which mainly includes artificial neural network (ANN) method, genetic algorithm (GA), particle swarm optimization (PSO), ant colony algorithm (ACA), simulated annealing algorithm (SAA), least-squares support vector machine (LSSVM) (Shokrollahi et al, 2013;Alomair and Iqbal, 2014;Rostami et al, 2018), and gene expression programming (GEP) (Tatar et al, 2013;Kamari et al, 2015;Tian et al, 2020). Compared with other numerical methods, the artificial intelligence method has the unique ability to identify the implicit linear or nonlinear relationship between input variables and target output values and a large number of parallel operations; it has a high prediction accuracy and is capable of processing large amounts of data in parallel.…”

Integration of Domain Knowledge and Data-Driven Modeling Evaluation Process for Predicting Minimum Miscible Pressure of CO2–Oil Systems in CCUS

“…The pressure must reach the minimum miscible pressure (MMP) in order to produce a miscible CO 2 flooding. The MMP the pressure that causes the interface tension of crude oil and CO 2 to be zero or local flooding efficiency of nearly 100% . Physically, the MMP between CO 2 and crude oil is defined as the lowest pressure at which CO 2 and crude oil can reach miscibility via multiple contacts at reservoir temperature .…”

“…While Karkevandi-Talkhooncheh utilized a substantial data set to construct the ANFIS employing five optimization algorithms, they did not consider reservoir pressure as one of the influencing factors in their selection, and their evaluation model remained singular. Tian et al introduced a back-propagation neural network model for predicting MMP during pure and impure CO 2 injection processes. They employed the Pearson correlation coefficient method to select five variables as input parameters.…”

“…The MMP the pressure that causes the interface tension of crude oil and CO 2 to be zero or local flooding efficiency of nearly 100%. 4 Physically, the MMP between CO 2 and crude oil is defined as the lowest pressure at which CO 2 and crude oil can reach miscibility via multiple contacts at reservoir temperature. 5 Therefore, it is appropriately predicted that MMP will contribute to lower oil field costs, enhanced oil recovery, and screening CO 2 injection of the reservoir.…”

Key geological factors controlling oil displacement efficiency of CO2 injection in low-permeability reservoirs

“…It can reduce negative effect of capillary force and enhance oil displacement efficiency using miscible or semi miscible CO 2 flooding (Choubineh et al., 2016; Stephenson et al., 1993; Zhao and Liao, 2012). In addition, CO 2 can be permanently buried underground to reduce greenhouse gas emission (James et al., 2014; Kalra et al., 2018; Spigarelli and Kawatra, 2013; Tian et al., 2020). Therefore, using CO 2 injection to enhance oil recovery in low-permeability reservoir has attracted considerable attention from geologists and petroleum engineers (Saira et al., 2020; Sridhara et al., 2018; Wang et al, 2014).…”