Publications Scientifiques

Permanent URI for this communityhttps://dspace.univ-boumerdes.dz/handle/123456789/10

Browse

Author: search.filters.author.Ben Seghier, Mohamed El AmineSubject: search.filters.subject.Data-driven

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Predicting solubility of nitrous oxide in ionic liquids using machine learning techniques and gene expression programming
    (Elsevier, 2021) Nait Amar, Menad; Ghriga, MMohammed Abdelfetah; Ben Seghier, Mohamed El Amine; Ouaer, Hocine
    Background: - Nitrous oxide (N2O), as a potent greenhouse gas, is increasingly becoming a major multidisciplinary concern in recent years. Therefore, the removal of N2O using powerful green solvents such as ionic liquids (ILs) has turned into an attractive way to reduce the amount of N2O in the atmosphere. Methods: -The aim of this study was to establish rigorous models that can predict the solubility of N2O in various ILs. To achieve this, three advanced soft-computing methods, viz. cascaded forward neural network (CFNN), radial basis function neural network (RBFNN), and gene expression programming (GEP) were trained and tested using comprehensive experimental measurements. Significant Findings: - The obtained results demonstrated that the newly implemented models can predict the solubility of N2O in ILs with high accuracy. Besides, it was found that the CFNN model optimized using Levenberg-Marquardt (LM) algorithm was the best predictive paradigm (R2=0.9994 and RMSE=0.0047). Lastly, the Leverage technique was carried out, and the statistical validity of the newly implemented model was documented as more than 96% of data were located in the applicability realm of this paradigm. © 2021 Taiwan Institute of Chemical Engineers
  • No Thumbnail Available
    Item
    Modeling viscosity of CO 2 at high temperature and pressure conditions
    (Elsevier, 2020) Nait Amar, Menad; Ghriga, Mohammed Abdelfetah; Ouaer, Hocine; Ben Seghier, Mohamed El Amine; Thai Pham, Binh
    The present work aims at applying Machine Learning approaches to predict CO2 viscosity at different thermodynamical conditions. Various data-driven techniques including multilayer perceptron (MLP), gene expression programming (GEP) and group method of data handling (GMDH) were implemented using 1124 experimental points covering temperature from 220 to 673 K and pressure from 0.1 to 7960 MPa. Viscosity was modelled as function of temperature and density measured at the stated conditions. Four backpropagation-based techniques were considered in the MLP training phase; Levenberg-Marquardt (LM), bayesian regularization (BR), scaled conjugate gradient (SCG) and resilient backpropagation (RB). MLP-LM was the most fit of the proposed models with an overall root mean square error (RMSE) of 0.0012 mPa s and coefficient of determination (R2) of 0.9999. A comparison showed that our MLP-LM model outperformed the best preexisting Machine Learning CO2 viscosity models, and that our GEP correlation was superior to preexisting explicit correlations.