Prediction of Compressional, Shear, and Stoneley Wave Velocities from Conventional Well Log Data Using a Committee Machine with Intelligent Systems

Asoodeh, Mojtaba; Bagheripour, Parisa

doi:10.1007/s00603-011-0181-2

Cited by 102 publications

(33 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Neural networks are computational models which partially emulate the biological neural storage and analytical operations of the brain through non-linear processing elements (neurons) arranged in parallel structures called layers [17]. Back-propagation is the common supervised learning algorithm used for training of neural networks.…”

Section: Methodology: Ga-ps Optimized Neural Networkmentioning

confidence: 99%

“…For clarification of the hybrid GA-PS technique, refer to Asoodeh and Bagheripour [17,18,31] and Mohaghegh [32].…”

Section: Methodology: Ga-ps Optimized Neural Networkmentioning

confidence: 99%

“…]. Recent studies showed that intelligent systems, including neural network, fuzzy logic, neuro-fuzzy, and etc have more generalization capability compared with empirical correlations [17,18]. Hitherto, several researchers have utilized intelligent systems for solving their complicated problems in petroleum engineering [?…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Oil formation volume factor modeling: Traditional vs. Stochastically optimized neural networks

2013

Self Cite

View full text Add to dashboard Cite

Abstract:Oil formation volume factor (FVF) is considered as relative change in oil volume between reservoir condition and standard surface condition. FVF, always greater than one, is dominated by reservoir temperature, amount of dissolved gas in oil, and specific gravity of oil and dissolved gas. In addition to limitations on reliable sampling, experimental determination of FVF is associated with high costs and time-consumption. Therefore, this study proposes a novel approach based on hybrid genetic algorithm-pattern search (GA-PS) optimized neural network (NN) for fast, accurate, and cheap determination of oil FVF from available measured pressure-volumetemperature (PVT) data. Contrasting to traditional neural network which is in danger of sticking in local minima, GA-PS optimized NN is in charge of escaping from local minima and converging to global minimum. A group of 342 data points were used for model construction and a group of 219 data points were employed for model assessment. Results indicated superiority of GA-PS optimized NN to traditional NN. Oil FVF values, determined by GA-PS optimized NN were in good agreement with reality.

show abstract

Section: Methodology: Ga-ps Optimized Neural Networkmentioning

confidence: 99%

“…For clarification of the hybrid GA-PS technique, refer to Asoodeh and Bagheripour [17,18,31] and Mohaghegh [32].…”

Section: Methodology: Ga-ps Optimized Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Oil formation volume factor modeling: Traditional vs. Stochastically optimized neural networks

2013

Self Cite

View full text Add to dashboard Cite

show abstract

“…A fuzzy inference system (FIS) is the method of formulating from a given input to an output using fuzzy logic (MATLAB user's guide 2011). A FIS consists of five major steps: fuzzification of input variables, application of fuzzy operators (AND, OR, and NOT) in the rule's antecedent, implication from the antecedent to the consequent, aggregation of consequent across the rules, and defuzzification (Asoodeh and Bagheripour 2012a). Defining appropriate membership functions (fuzzy sets) which best fit the data set is an important task that is done by subtractive clustering algorithm in Takagi and Sugeno (1985) FIS.…”

Section: Fuzzy Logicmentioning

confidence: 99%

“…These empirical correlations do not have flexible structure and consequently do not serve satisfying generalization. Recent years have been witnessing the growing tendency to utilize intelligent systems for solving complicated petroleum and chemistry problems (Asoodeh and Bagheripour 2012a, Asoodeh and Bagheripour 2012b, Asoodeh and Bagheripour 2012bAsoodeh 2013a, b). These works proved that intelligent systems have more generalization capability and produce more reliable results.…”

Section: Introductionmentioning

confidence: 99%

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

Zargar

Bagheripour

Asoodeh

2014

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Oil‐CO₂ minimum miscible pressure (MMP) determination using a stimulated smart approach

et al. 2015

Self Cite

View full text Add to dashboard Cite

Multi‐contact miscible displacement of reservoir petroleum by injection of the relatively inexpensive carbon dioxide (CO2) gas represents one of the most efficient currently available techniques of enhanced oil recovery. Experimental determination of optimal injection pressure, known as minimum miscible pressure (MMP), is very costly, laborious, and time‐intensive. Therefore, the quest for a quick, cost‐effective, and accurate way of determining MMP is inevitable. In this study an improved approach was followed to predict oil‐CO2 MMP. First, input/output data are transformed to a higher correlated data space using an alternative condition expectation (ACE) algorithm to reduce complexity of the problem for a generalized regression neural network (GRNN). Then, transformed data are introduced to the GRNN to construct a model for estimation of MMP. Eventually, a hybrid genetic algorithm‐pattern search technique is employed for optimizing the GRNN and producing more accurate estimations. This model was constructed using worldwide experimental data from open literature. The performance of the constructed model was assessed by introducing experimental data from Iran Oils as test data. A comparison between the current study and previous models, including outstanding correlations and intelligent systems, demonstrated the superiority of the proposed model.

show abstract

Prediction of Compressional, Shear, and Stoneley Wave Velocities from Conventional Well Log Data Using a Committee Machine with Intelligent Systems

Cited by 102 publications

References 43 publications

Oil formation volume factor modeling: Traditional vs. Stochastically optimized neural networks

Oil formation volume factor modeling: Traditional vs. Stochastically optimized neural networks

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

Oil‐CO₂ minimum miscible pressure (MMP) determination using a stimulated smart approach

Contact Info

Product

Resources

About

Prediction of Compressional, Shear, and Stoneley Wave Velocities from Conventional Well Log Data Using a Committee Machine with Intelligent Systems

Cited by 102 publications

References 43 publications

Oil formation volume factor modeling: Traditional vs. Stochastically optimized neural networks

Oil formation volume factor modeling: Traditional vs. Stochastically optimized neural networks

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

Oil‐CO2 minimum miscible pressure (MMP) determination using a stimulated smart approach

Contact Info

Product

Resources

About

Oil‐CO₂ minimum miscible pressure (MMP) determination using a stimulated smart approach