Predicting thermal conductivity of carbon dioxide using group of data-driven models

Menad Nait Amar,Ashkan Jahanbani Ghahfarokhi,Noureddine Zeraibi

doi:10.1016/j.jtice.2020.08.001

Abstract

Thermal conductivity of carbon dioxide (CO2) is a vital thermophysical parameter that significantly affects the heat transfer modeling related to CO2 transportation, pipelines design and associated process industries. The current study lays emphasis on implementing powerful soft computing approaches to develop novel paradigms for estimation of CO2 thermal conductivity. To achieve this, a massive database including 5893 experimental datapoints was acquired from the experimental investigations. The collected data, covering pressure values from 0.097 to 209.763 MPa and temperature between 217.931 and 961.05 K, were employed for establishing various models based on multilayer perceptron (MLP) optimized by different back-propagation algorithms, and radial basis function neural network (RBFNN) coupled with particle swarm optimization (PSO). Then, the two best found models were linked under two committee machine intelligent systems (CMIS) using weighted averaging and group method of data handling (GMDH). The obtained results showed that CMIS-GMDH is the most accurate paradigm with an overall AARD% and R2 values of 0.8379% and 0.9997, respectively. In addition, CMIS-GMDH outperforms the best prior explicit models. Finally, the leverage technique confirmed the validity of the model and more than 96% of the data are within its applicability realm.

Highlights

The increased level of CO2 emissions in the atmosphere is regarded as the primary issue of climate change [1À3]
During the training phase of different soft computing methods, mean square error (MSE) was the considered fitness function to assess the reliability of the approaches
Where λi denotes CO2 thermal conductivity, N is the number of training datapoints and the subscripts pre and exp refer to the predicted values and the experimental measurements, respectively

Summary

Introduction

The increased level of CO2 emissions in the atmosphere is regarded as the primary issue of climate change [1À3]. With the intention of reducing greenhouse gas emissions, enormous efforts have been made to adequately establish proper techniques for Carbon Capture and Sequestration (CCS) in geological formations [5À9]. Post-combustion capture; pre-combustion capture and oxy-fuel combustion capture; CO2 transport and storage [10À12]. These classes include various industrial units, land transportation using pipeline, maritime transport by ship, and lastly injection or storage in geological formations [13,14]. In the context of injecting CO2 in geological formations, enhanced oil recovery (EOR) techniques by injecting miscible CO2 (with oil) have shown increased ultimate recovery factors in various oil reservoirs. The CO2-oil system can reach the miscibility condition during CO2 injection, leading to the improvement of the microscopic displacement efficiency [15À20]

Objectives

Results

Conclusion