Artificial Intelligence Based Methods for Asphaltenes Adsorption by Nanocomposites: Application of Group Method of Data Handling, Least Squares Support Vector Machine, and Artificial Neural Networks

Abstract

Asphaltenes deposition is considered a serious production problem. The literature does not include enough comprehensive studies on adsorption phenomenon involved in asphaltenes deposition utilizing inhibitors. In addition, effective protocols on handling asphaltenes deposition are still lacking. In this study, three efficient artificial intelligent models including group method of data handling (GMDH), least squares support vector machine (LSSVM), and artificial neural network (ANN) are proposed for estimating asphaltenes adsorption onto NiO/SAPO-5, NiO/ZSM-5, and NiO/AlPO-5 nanocomposites based on a databank of 252 points. Variables influencing asphaltenes adsorption include pH, temperature, amount of nanocomposites over asphaltenes initial concentration (D/C0), and nanocomposites characteristics such as BET surface area and volume of micropores. The models are also optimized using nine optimization techniques, namely coupled simulated annealing (CSA), genetic algorithm (GA), Bayesian regularization (BR), scaled conjugate gradient (SCG), ant colony optimization (ACO), Levenberg–Marquardt (LM), imperialistic competitive algorithm (ICA), conjugate gradient with Fletcher-Reeves updates (CGF), and particle swarm optimization (PSO). According to the statistical analysis, the proposed RBF-ACO and LSSVM-CSA are the most accurate approaches that can predict asphaltenes adsorption with average absolute percent relative errors of 0.892% and 0.94%, respectively. The sensitivity analysis shows that temperature has the most impact on asphaltenes adsorption from model oil solutions.

Insights into the estimation of hydroxyl radical rate constant of water contaminants in AOP using new smart QSPR models

“…To distiguish how each one of the inputs affects the hydroxyl radical rate constants, a sensitivity analyis was done. To this end, relevancy factor was determined as below to find out the impact of each input (Mazloom et al ., 2020):…”

“…In the LSSVM algorithm, two optimization parameters of γ and σ 2 should be determined. More details and equations of LSSVM algorithm can be found in the following references (Bemani et al ., 2020b; Ershadnia et al ., 2020; Mazloom et al ., 2020).…”

Toward estimating standard enthalpy of combustion of pure chemical compounds: extreme learning machine approach

“…The artificial intelligence methods have extensive applications in other issues such as determination of higher heating values based on proximate (Keybondorian et al 2017) and ultimate systems (Darvishan, BakhDarvishan et al 2018), asphaltene adsorption (Mazloom et al 2020), hydrocarbon and carbon dioxide interfacial tension (Suleymani and Bemani 2018), and sulfur deposition (Bemani, Baghban, and Mohammadi 2020). Due to extensive applications of machine learning methods in chemical engineering (Ershadnia et al 2020), in the present work, a novel very accurate machine learning method is proposed for the estimation of combustion enthalpy of pure chemical compounds based on group contributions.…”

Comparative Analysis of Machine Learning Models for Nanofluids Viscosity Assessment

“…Recently, artificial intelligent models, such as an artificial neural network (ANN), radial basis function neural network (RBF-NN), etc., which have powerful nonlinear regression ability and can theoretically model complex relations, have been widely utilized to model thermo-physical properties of nanofluids. These strong data-driven modeling tools can determine the complex nonlinear dependency of an output parameter to its input variables with high speed and low computational cost [6,18]. Karimi et al [19] firstly proposed an artificial neural network based on a genetic algorithm (GA).…”