Evolving a prediction model based on machine learning approach for hydrogen sulfide removal from sour condensate of south pars natural gas processing plant

Adib, Hooman; Sabet, Askar; Naderifar, Abbas; Adib, Marjan; Ebrahimzadeh, M.

doi:10.1016/j.jngse.2015.08.012

Cited by 15 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Support Vector Machine training procedure converges to optimum output results faster and it is not need to control model parameters (Cortes and Vapnik, 1995;Pelckmans et al, 2002;Suykens et al, 2002;Curilem et al, 2011). For detailed information about the SVM refer to our Adib et al, 2013Adib et al, , 2015Moradi et al, 2016). Pattern recognition or classification can be performed by SVM in a data set consisting of N data point x k ; y k f gk ¼ 1; 2; .…”

Section: Support Vector Machinementioning

confidence: 99%

“…The main advantage of such models over existing approaches is the capability of learning and generalizing data, fault tolerance and inherent contextual information processing in addition to fast computation potential (Raynal et al, 2016). Such characteristics make them perfect candidates for applications where the complexity of the data or task demands high computational costs (Haghbakhsh et al, 2012;Adib et al, 2013Adib et al, , 2015Moradi et al, 2016).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Prediction of sulfur content in propane and butane after gas purification on a treatment unit

Adib

Kazerooni

Falsafi

et al. 2018

Oil Gas Sci. Technol. – Rev. IFP Energies nouvelles

Self Cite

View full text Add to dashboard Cite

The acidic compounds such as Mercaptans, H2S and COS are commonly present in the liquid LPG streams in the south Pars gas processing plant. Sulfur contaminants not only lead to odor problems but can form objectionable oxides on combustion and cause environmental pollution. In present study, Support Vector Machine (SVM) is employed to develop an intelligent model to predict the sulfur content of propane and butane products of Liquefied Petroleum Gas (LPG) treatment unit of south Pars gas processing plant of Assaluyeh/Iran. A set of seven input/output plant data each consisting of 365 data has been used to train, optimize, and test the model. Model development that consists of training, optimization and test was performed using randomly selected 70%, 15%, and 15% of available data respectively. Test results from the SVM developed model showed good compliance with operating plant data. Squared correlation coefficients for developed models are 0.97 and 0.99 for propane and butane sulfur content, respectively. According to the results of the present case study, SVM could be regarded as a reliable accurate approach for modeling the sulfur content of LPG treatment unit of a natural gas processing plant.

show abstract

Section: Support Vector Machinementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Prediction of sulfur content in propane and butane after gas purification on a treatment unit

Adib

Kazerooni

Falsafi

et al. 2018

Oil Gas Sci. Technol. – Rev. IFP Energies nouvelles

Self Cite

View full text Add to dashboard Cite

show abstract

“…Wei Jiang 1,2 Jinjin Li 1,2 Guanshan Chen 1,2 Renjiang Luo 3 Yan Chen 4 Xu Ji 5 Zhuoxiang Li 5 Ge He For instance, Mowbray [12] employed feedforward neural networks and support vector machines (SVMs) to accurately estimate the monoethanolamine (MEA) circulation rate in amine treatment units. Adib et al [13,14] used SVM models to estimate the process output variables of the stabilizer column in industrial natural gas sweetening units. Keshavarz et al [15] implemented the imperialist competitive algorithm (ICA) to optimize the weights, biases, and neuron numbers of the ANN model, establishing an ANN-ICA process model to predict the concentration of acidic gases at the desulfurization tower outlet.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Data‐Driven Modeling Strategy Based on Feature Selection for an Industrial Natural Gas Sweetening Process

Jiang,

Li,

Chen

et al. 2023

Chem Eng & Technol

View full text Add to dashboard Cite

As the core process of natural gas purification plant, natural gas sweetening directly affects the production efficiency and product quality of the purification plant. However, process modeling based on sulfur content prediction presents challenges in adaptability and accuracy. To tackle this, a machine learning‐based modeling approach is proposed that integrates an adaptive immune genetic algorithm with random forest (RF) to intelligently select process features as input variables for RF modeling. The industrial result indicates that the proposed method is able to remove interfering variables and adaptively achieve optimal model precision for different scenarios. It offers a novel research instrument for product quality monitoring in natural gas sweetening plants.

show abstract

“…Related research in this field includes the following contributions. Adib et al (2015) constructed an SVMbased predictive model to gauge hydrogen sulfide pressure during the removal process, utilizing input data such as top stabilizer column pressure, temperature, seal pressure, and volumetric flow rate of the condition [9]. Zhou et al (2020) employed diverse machine learning models, including ANN, Random Forest, AdaBoost, and XGBoost (Extreme Gradient Boosting), to anticipate the heat transfer coefficient of a capacitor, a component possessing a function contrary to that of a vaporizer [10].…”

Section: Introductionmentioning

confidence: 99%

Development of a DNN Predictive Model for the Optimal Operation of an Ambient Air Vaporizer of LNG

Shin,

Lim,

Kim

et al. 2023

Processes

View full text Add to dashboard Cite

In this study, we conducted preliminary research with the objective of leveraging artificial intelligence to optimize the efficiency and safety of the entire Ambient Air Vaporizer (AAV) system for LNG (Liquid Natural Gas). By analyzing a year-long dataset of real operational data, we identified key variables that significantly influence the outlet temperature of Natural Gas (NG). Based on these insights, a Deep Neural Network (DNN) prediction model was developed to forecast the NG outlet temperature. The endeavor to create an effective prediction model faced specific challenges, primarily due to the narrow operational range of fan speeds and safety-focused guidelines. To surmount these obstacles, various learning algorithms were evaluated under multiple conditions. Ultimately, a DNN model exhibiting lower values of both absolute mean error (MAE) and mean square error (MSE) was successfully established.

show abstract

Evolving a prediction model based on machine learning approach for hydrogen sulfide removal from sour condensate of south pars natural gas processing plant

Cited by 15 publications

References 34 publications

Prediction of sulfur content in propane and butane after gas purification on a treatment unit

Prediction of sulfur content in propane and butane after gas purification on a treatment unit

Adaptive Data‐Driven Modeling Strategy Based on Feature Selection for an Industrial Natural Gas Sweetening Process

Development of a DNN Predictive Model for the Optimal Operation of an Ambient Air Vaporizer of LNG

Contact Info

Product

Resources

About