Estimating hydrogen sulfide solubility in ionic liquids using a machine learning approach

Shafiei, Ali; Ahmadi, Mohammad Ali; Zaheri, Seyed Hayan; Baghban, Alireza Akbarzadeh; Amirfakhrian, Ali; Soleimani, Reza

doi:10.1016/j.supflu.2014.08.011

Cited by 107 publications

(49 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, intelligence schemes have widely applied in different fields in order to modeling nonlinear relationships between concerned variables (Shafiei et al, 2014;Ahmadi and Baghban, 2015;Baghban et al, 2015a;Baghban et al, 2015b;Amedi et al, 2016;Baghban et al, 2016;Bahadori et al, 2016). Artificial neural network, fuzzy logic system, adaptive network-based fuzzy inference system, and support vector machine are for popular and widely used embranchments of intelligence schemes.…”

Section: Introductionmentioning

confidence: 99%

Modeling of true vapor pressure of petroleum products using ANFIS algorithm

Baghban

Bahadori

Ahmad

et al. 2016

Petroleum Science and Technology

Self Cite

View full text Add to dashboard Cite

The aim of this contribution was to develop a simple tool based on fuzzy logic concepts to predict true vapor pressure of volatile petroleum products. In this regard, the adaptive neuro fuzzy inference system was evolved to estimate the true vapor pressure of volatile petroleum products as function of temperature and Reid vapor pressure. In addition, to determine optimal membership function parameters, the particle swarm optimization as an amazing evolutionary algorithm was applied. This predictive tool is suggested as a precise technique to measure the true vapor pressures of typical liquefied petroleum gases, natural gasoline, and motor fuel components at broad ranges of temperatures. This technique was trained and tested by 156 set of data points collected from the reference. The temperature range is 253-373 K and the range of Reid vapor pressure is 35-250 KPa. Results obtained from the present tool found to be in acceptable agreement with the actual reported data in the literature. The values of root mean square error and regression coefficient obtained 5.34 and 0.9975, respectively.

show abstract

Section: Introductionmentioning

confidence: 99%

Modeling of true vapor pressure of petroleum products using ANFIS algorithm

Baghban

Bahadori

Ahmad

et al. 2016

Petroleum Science and Technology

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, intelligence schemes have widely applied in different fields to model nonlinear relationships between concerned variables (Ahmadi and Baghban, 2015;Amedi et al, 2016;Baghban et al, 2015a;Baghban et al, 2015;Baghban et al, 2015c;Shafiei et al, 2014;Bahadori et al, 2016). Artificial neural network, fuzzy logic system, adaptive network-based fuzzy inference system (ANFIS), and support vector machine are for popular and widely used embranchments of intelligence schemes.…”

Section: Introductionmentioning

confidence: 99%

Estimation of natural gases water content using adaptive neuro-fuzzy inference system

Baghban

Kashiwao

Bahadori

et al. 2016

Petroleum Science and Technology

Self Cite

View full text Add to dashboard Cite

To appropriate design and satisfactory performance of utilities in the gas processing and transmission plants, a crucial factor that should be taken in consideration is the natural gas water content. The present research aimed to develop a precise strategy for estimating sour gas/sweet gas water content ratio. This developed predictive tool is based on adaptive neuro-fuzzy inference system (ANFIS). In this regard, a comprehensive data bank that contains 1,126 data points was collected. This model predicts ratio of sour gas to sweet gas as function of pressure, temperature, and equilibrium H 2 S mole fraction. The ranges of pressure and temperature were 200-70000 KPa and 10-150°C, respectively. In addition, the equilibrium H2S mole fraction ranges between 0.076 and 0.492. Results obtained from the ANFIS model confirmed acceptable and reasonable predictive capability of this model. This tool is simple to use and can be help petroleum engineers to predict water content of natural gas at broad ranges of conditions.

show abstract

“…Different mathematical optimization methods such as Back Propagation (BP) [38], Genetic Algorithm [39], Particle Swarm Optimization (PSO) [40][41][42], Hybrid Particle Swarm Optimization and Genetic Algorithm (HPSOGA) [43], Unified Particle Swarm Optimization (UPSO) [44], Imperialist Competitive Algorithm (ICA) [45] can be coupled with above mentioned computational intelligence paradigms to optimize configuration of them. Moreover, the aforementioned optimization approaches can be coupled with least square SVM [46][47][48][49][50][51][52][53][54][55][56][57][58].…”

Section: Introductionmentioning

confidence: 99%