A novel approach for modeling and optimization of surfactant/polymer flooding based on Genetic Programming evolutionary algorithm

Bahrami, Peyman; Kazemi, Pezhman; Mahdavi, Sedigheh; Ghobadi, Hossein

doi:10.1016/j.fuel.2016.03.095

Cited by 31 publications

(18 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It was first introduced by Koza [34]. In this method, the mathematical expressions are generated using input-output data by a biologically inspired algorithm, where the population continuously evolves towards the best-fitted model [35]. GP and the genetic algorithm (GA) have some similarities, while the most important difference is the output format.…”

Section: Genetic Programming (Gp)mentioning

confidence: 99%

“…The output of GA is a value, whereas the output of GP is a computer program. The complicated structures of computer programs, mathematical expressions, and process system models in GP are represented with trees [35,36].…”

Section: Genetic Programming (Gp)mentioning

confidence: 99%

“…The new generation is built based on the models, having a lower fitness error. The next generation of models is reproduced by using genetic operators, such as the reproduction, crossover and mutation operators [34,35]. In the crossover operator, two models exchange the sub-trees to generate two new models, while in the mutation operator, the new model is formed from the previously generated model by substituting a randomly selected sub-tree with a newly generated one.…”

Section: Genetic Programming (Gp)mentioning

confidence: 99%

“…The fitness evaluation step is repeated for the newly generated population, and the whole procedure continues until an acceptable fitness value is achieved or the algorithm reaches its generation limit. By using this iterative procedure, the accuracy of each model improves in each iteration and finally the best one is considered as the output of the GP algorithm [34,35]. Figure 3 shows a flow chart of the GP computation procedure:…”

Section: Genetic Programming (Gp)mentioning

confidence: 99%

See 3 more Smart Citations

Robust Data-Driven Soft Sensors for Online Monitoring of Volatile Fatty Acids in Anaerobic Digestion Processes

et al. 2020

Self Cite

View full text Add to dashboard Cite

The concentration of volatile fatty acids (VFAs) is one of the most important measurements for evaluating the performance of anaerobic digestion (AD) processes. In real-time applications, VFAs can be measured by dedicated sensors, which are still currently expensive and very sensitive to harsh environmental conditions. Moreover, sensors usually have a delay that is undesirable for real-time monitoring. Due to these problems, data-driven soft sensors are very attractive alternatives. This study proposes different data-driven methods for estimating reliable VFA values. We evaluated random forest (RF), artificial neural network (ANN), extreme learning machine (ELM), support vector machine (SVM) and genetic programming (GP) based on synthetic data obtained from the international water association (IWA) Benchmark Simulation Model No. 2 (BSM2). The organic load to the AD in BSM2 was modified to simulate the behavior of an anaerobic co-digestion process. The prediction and generalization performances of the different models were also compared. This comparison showed that the GP soft sensor is more precise than the other soft sensors. In addition, the model robustness was assessed to determine the performance of each model under different process states. It is also shown that, in addition to their robustness, GP soft sensors are easy to implement and provide useful insights into the process by providing explicit equations.

show abstract

Section: Genetic Programming (Gp)mentioning

confidence: 99%

Section: Genetic Programming (Gp)mentioning

confidence: 99%

Section: Genetic Programming (Gp)mentioning

confidence: 99%

Section: Genetic Programming (Gp)mentioning

confidence: 99%

See 2 more Smart Citations

Robust Data-Driven Soft Sensors for Online Monitoring of Volatile Fatty Acids in Anaerobic Digestion Processes

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“… The economic cost of the chemical injection reduced the NPV of all scenarios in the Lula IFS, despite increasing the oil recovery factor. Therefore, the associated costs of CEOR program play a fundamental role in its applicability, a behavior observed previously by Bahrami et al (2016) and Kamari et al (2016) researches.…”

Section: Discussionmentioning

confidence: 80%

Optimization and comparison between polymer, surfactant-polymer and water flooding recoveries in a pre-salt carbonate reservoir considering uncertainties.

García¹,

Sebastian²

View full text Add to dashboard Cite

A successful Chemical Enhanced Oil Recovery (CEOR) program starts with a proper process selection for a given field, followed by a formulation of the batch components and a representative simulation step. Also, lab studies, field data, pilot testing, and economic analyses are required before project implementation. This work discusses the state of the art of the Surfactant-Polymer flood (SP) EOR technique, specifically for carbonate reservoirs, and states a methodology mixing laboratory, literature and reservoir simulation, to assess its applicability under economic and geological uncertainties. First, it is explained concepts related to the research, such as polymer, surfactant, microemulsion, functionalities of each chemical injected, advantages, and disadvantages. Second, a state of the art is developed about recent SP advances. Third, it is described the laboratory method being used to evaluate some properties of the chemicals injected for the Polymer flooding (PF) and SP flooding. Later, the simulation study step being conducted is explained, which will define the volume recovered and Net Present Value (NVP) obtained for the PF, SP injections and water flooding, in different economic and geological scenarios for two models resembling carbonate Brazilian reservoirs. Finally, it is discussed the results obtained, future researches that could be performed, and the respective bibliography. As part of this research, it was verified the Xanthan gum shows adequate results at different concentrations; that a surfactant specifically selected for a carbonate rock with low Interfacial tension and low adsorption is required; also that for the Lula based model although the polymer flooding and Surfactant-Polymer simulation brought some benefits, when compared with the waterflooding, on different economic scenarios and geological models, the high cost associated to the chemical handling facilities and volume spent do not make favorable its application in any scenario. On the contrary for the Cerena I field model, it was found the SP and Polymer flooding on all cases brought better results when compared with the water injection. Concluding that the performance and success of a CEOR program require finding the correct slug characteristics for the unique conditions of each reservoir. In this research the reservoir with higher production rates made possible the use of Chemical EOR presenting better results than a water injection however in the smaller model they were not economically viable due to the additional associated prices.

show abstract

An experimental method to control pore structure in artificial conglomerate based on grain size distribution design

Gao

Luan³

et al. 2020

Preprint

View full text Add to dashboard Cite

A novel approach for modeling and optimization of surfactant/polymer flooding based on Genetic Programming evolutionary algorithm

Cited by 31 publications

References 23 publications

Robust Data-Driven Soft Sensors for Online Monitoring of Volatile Fatty Acids in Anaerobic Digestion Processes

Robust Data-Driven Soft Sensors for Online Monitoring of Volatile Fatty Acids in Anaerobic Digestion Processes

Optimization and comparison between polymer, surfactant-polymer and water flooding recoveries in a pre-salt carbonate reservoir considering uncertainties.

An experimental method to control pore structure in artificial conglomerate based on grain size distribution design

Contact Info

Product

Resources

About