Fuzzy modeling of volume reduction of oil due to dissolved gas runoff and pressure release

Abstract

Oil formation volume factor (FVF) refers to the change in oil volume between reservoir and standard conditions at surface. It is a crucial oil property which is governed by reservoir temperature, amount of dissolved gas in oil, and specific gravity of oil and dissolved gas. This parameter plays a trivial role in petroleum reservoir and production calculations. Accurate determination of oil FVF is restricted by limitations on reliable sampling and high cost and time-consumption associated with laboratory experiments. Furthermore, available empirical correlations do not have satisfying generalization and accuracy owing to being calibrated on specific oil samples. Therefore, this study offers a Takagi-Sugeno (TS) fuzzy logic model for estimating oil FVF for the purpose of developing a precise model calibrated on regional Iranian oil using 367 training samples. TS fuzzy model utilizes subtractive clustering approach for determining number of rules and clusters. Evaluation of constructed fuzzy logic using 108 unseen test data points indicated achievement of fuzzy logic in prediction of oil FVF.

Prediction performance of compressive strength of cementitious materials containing rubber aggregates and filler using fuzzy logic method

“…To achieve an optimal fuzzy model, different clustering radii were introduced to subtract clustering algorithm and the performance of the consequent fuzzy model was investigated. Subtractive clustering was generated by a design parameter, called clustering radii (Zargar et al , 2014). Each cluster may contain a variety of mass composition of cementitious materials.…”

Oil Formation Volume Factor Determination Through a Fused Intelligence

“…Table 4 provides an opportunity to compare MSE and R-square factors of different models. Results show that committee machine surpasses other methods and provides more reliable results relative to Zargar et al (2014), , and individual SVR and ACE models.…”

“…Graph evaluating the performance of committee machine model using concepts of correlation coefficient, relative error, and residual analysis of prediction. Zargar et al (2014) proposed a fuzzy logic model for estimating FVF from available PVT data. Performing an error distribution analysis, they concluded that the fuzzy model is an accurate model for FVF estimation.…”

“…FVF value has significance in calculating various parameters such as the depletion rate, oil in place, predicting the future of the reservoir, optimizing the rate of production, designing of production operation and facilities . Rigorous depiction of FVF through differential vaporization test on bottom-hole or recombined surface samples is very time, cost and labor intensive (Zargar et al 2014). Furthermore, sampling for experiments is limited to early producing life of reservoir which imposes a restraint to laboratory measurements (Dake 1988).…”