Estimation of carbon dioxide equilibrium adsorption isotherms using adaptive neuro‐fuzzy inference systems (ANFIS) and regression models

Abstract

Removal of CO 2 from industrial facilities such as refineries and power plants for emission reduction has attracted considerable interest. Among currently used CO 2 capturing processes, the use of microporous solids is considered to be one of the most promising approaches. A description of the CO 2 adsorption on microporous material focuses on some captivating problems of present adsorption studies. In present study, robust and accurate methods are designed for the estimation of CO 2 adsorption onto microporous solids as a function of CO 2 partial pressure and temperature. The performance and accuracy of the developed models were tested and validated by their ability to predict the literature data. It was concluded that the designed adaptive neurofuzzy inference systems (ANFIS) models and mathematical equations demonstrated a superior predictive performance on estimation of CO 2 adsorption data over well-known classic adsorption isotherms. Findings of present study indicate that the neuro-fuzzy modeling approach is a practicable method for analysis and design of CO 2 separation and purification technology.

Application of ANFIS, ANN and fuzzy time series models to CO2 emission from the energy sector and global temperature increase

“…Environmental factors such as average temperature and CO 2 and oxygen levels were calculated using an ANFIS, which was proven to perform well. Similarly, Saghafi and Arabloo (2017) proposed an account of CO 2 immersion on a microporous material emphasized some of the captivating problems of the present adsorption studies and observed that ANFIS performed better than conventional adsorption isotherms. ANFIS, multiple linear regression models and other statistical indices have also been used to model temperature data against crop yield (Cobaner et al , 2014).…”

Developing an adaptive neuro‐fuzzy inference system based on particle swarm optimization model for forecasting Cr(VI) removal by NiO nanoparticles

“…These substances are considered as removal pollutant sorbent because of the large specific area and lack of internal diffusion resistance. 7,8 In recent years, machine-learning approaches such as artificial neural network (ANN), adaptive neuro-fuzzy inference system (ANFIS), and least square support vector machine have researchers' attention for the prediction of different processes in industries [9][10][11][12][13][14][15] that can be applied to an extra range of systems to predict the behavior of experimental systems. 9,[11][12][13][14] Tahani et al proposed an ANN model to estimate the thermal conductivity of nanofluid.…”

A new empirical scaling equation for accurate prediction of gaseous species equilibrium adsorption on activated carbon

“…As it can be seen in Table , the correlation factors and error parameters are in an acceptable range, which demonstrates the fact that the proposed model well match the experimental data of equilibrium adsorption for different NGs on activated carbon. To draw a comparison between the proposed model and other novel methods to predict adsorption at different temperature, the average absolute error of the proposed model for CO 2 is less than 1%, which is comparable with that of a new framework, recently proposed by Saghafi and Arabloo for prediction of carbon dioxide adsorption. The main advantages of the proposed model are its simplicity and applicability at different temperatures.…”

“…Even though the model is accurate, it has more than 12 coefficients to be calculated. Rostami et al and Saghafi and Arabloo used soft computing schemes to predict CO 2 adsorption amount on activated carbon in nonisothermal condition. The developed networks predict the adsorption amount at different temperatures with an acceptable range of error, but no tangible framework was built to be used by other researchers.…”