Publications Scientifiques

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

Browse

Subject: search.filters.subject.GEP

Search Results

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Prediction of Wax Appearance Temperature Using Artificial Intelligent Techniques
    (Springer, 2020) Benamara, Chahrazed; Gharb, Kheira; Nait Amar, Menad; Hamada, Boudjema
    The paraffin particles can promote and be involved in the formation of deposits which can lead to plugging of oil production facilities. In this work, an experimental prediction of wax appearance temperature (WAT) has been performed on 59 Algerian crude oil samples using a pour point tester. In addition, a modeling investigation was done to create reliable WAT paradigms. To do so, gene expression programming and multilayers perceptron optimized with Levenberg–Marquardt algorithm (MLP-LMA) and Bayesian regularization algorithm were implemented. To generate these models, some parameters, namely density, viscosity, pour point, freezing point and wax content in crude oils, have been used as input parameters. The results reveal that the developed models provide satisfactory results. Furthermore, the comparison between these models in terms of accuracy indicates that MLP-LMA has the best performances with an overall average absolute relative error of 0.23% and a correlation coefficient of 0.9475.
  • 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.
  • No Thumbnail Available
    Item
    Hybrid soft computational approaches for modeling the maximum ultimate bond strength between the corroded steel reinforcement and surrounding concrete
    (Springer, 2020) Ben Seghier, Mohamed El Amine; Ouaer, Hocine; Ghriga, Mohammed Abdelfetah; Nait Amar, Menad; Duc-Kien, Thai
    The capacity efficiency of load carrying with the accurate serviceability performances of reinforced concrete (RC) structure is an important aspect, which is mainly dependent on the values of the ultimate bond strength between the corroded steel reinforcements and the surrounding concrete. Therefore, the precise determination of the ultimate bond strength degradation is of paramount importance for maintaining the safety levels of RC structures affected by corrosion. In this regard, hybrid intelligence and machine learning techniques are proposed to build a new framework to predict the ultimate bond strength in between the corroded steel reinforcements and the surrounding concrete. The proposed computational techniques include the multilayer perceptron (MLP), the radial basis function neural network and the genetic expression programming methods. In addition to that, the Levenberg–Marquardt (LM) deterministic approach and two meta-heuristic optimization approaches, namely the artificial bee colony algorithm and the particle swarm optimization algorithm, are employed in order to guarantee an optimum selection of the hyper-parameters of the proposed techniques. The latter were implemented based on an experimental published database consisted of 218 experimental tests, which cover various factors related to the ultimate bond strength, such as compressive strength of the concrete, concrete cover, the type steel, steel bar diameter, length of the bond and the level of corrosion. Based on their performance evaluation through several statistical assessment tools, the proposed models were shown to predict the ultimate bond strength accurately; outperforming the existing hybrid artificial intelligence models developed based on the same collected database. More precisely, the MLP-LM model was, by far, the best model with a determination coefficient (R2) as high as 0.97 and 0.96 for the training and the overall data, respectively.