Browsing by Author "Ben Seghier, Mohamed El Amine"

Now showing 1 - 13 of 13

Etude de la fiabilité et de l’intégrité des canalisations de transport des hydrocarbures aux défauts de corrosion actifs en évolution
(2019) Ben Seghier, Mohamed El Amine
Les canalisations de transport des hydrocarbures sont considérées comme des installations pétrolières principales occupant une place particulière dans l’industrie pétrolière et gazière, vue la quantité importante transportée par ces structures. Actuellement, les canalisations souvent nommées les pipelines, sont généralement enfuies dans des différents types de sols, soumises aux conditions naturelles très sévères et aux sollicitations différentes telles que celles provoquées par la pression interne. Ce type de conditions favorise le développement du phénomène de corrosion, ce qui engendre les vieillissements et les dégradations de ces constructions. Les défaillances des pipelines corrodés peuvent avoir des graves conséquences sur la vie humaine, l’environnement et sur l’économique. Afin de prédire la durée de vie résiduelle, le niveau de dégradation dû aux défauts de corrosion, la pression interne convenable aux régimes de fonctionnement, de nouveaux modèles probabilistes et méthodes numériques ont été développés dans ce travail. Ces derniers sont basés sur la fiabilité structurale et des méthodes statistiques approfondies, dans le but d’évaluer la probabilité de défaillance relative à plusieurs cas d’étude des pipelines corrodés et leurs sensibilités aux variables aléatoires introduites dans les calculs. Deux méthodes de simulation reposant sur la méthode de Monte Carlo Direct (CMC) sont proposées pour évaluer les probabilités de ruptures en fonction du temps d’exploitation des canalisations contenant de multiples défauts de corrosion où en tient compte de l’effet de corrélation des variables de base sur la fiabilité structurale des pipelines corrodés. De plus, une étude comparative des modèles de pression d’éclatement existants, des pipelines corrodés a été faite sur la base des indices statistiques et sur la base de données réelles des tests expérimentaux d’éclatement des tubes de différents grades contenant des défauts de corrosion réels ou artificiels. En outre, trois nouveaux modèles probabilistes de pression d’éclatement des canalisations corrodées ont été proposés pour les canalisations de basse, moyenne et haute résistances afin de réduire l’erreur de prédiction. Une nouvelle approche est également développée pour améliorer l'efficacité de la méthode de fiabilité de premier ordre (FORM) pour l'analyse de la fiabilité structurale des canalisations corrodées. Toutefois, nos modèles développés sont intégrés dans cette approche pour l’analyse fiabiliste de différents cas d’études ainsi que l’influence de plusieurs variables a été illustrée
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.
Machine learning-based Shapley additive explanations approach for corroded pipeline failure mode identification
(Elsevier Ltd, 2024) Ben Seghier, Mohamed El Amine; Mohamed, Osama Ahmed; Ouaer, Hocine
Rapid failure mode identification of oil and gas pipelines can prevent catastrophic consequences, improve fast intervention and enhance the design safety of these critical systems. This paper proposes explainable-based machine learning models using to determine the failure mode of corroded pipelines as a function of geometric configurations, material properties, and corrosion defect details. To determine the best identification model, this study examined eight machine learning models, including Nave Bayes, K-Nearest Neighbors, Decision Tree, Random Forest, Adaptive Boosting, Extreme Gradient Boosting, Light Gradient Boosting Machine, and Category Boosting, based on a comprehensive experimental database for steel pipelines with various corrosion/crack defect configurations. Furthermore, the Shapley additive explanations approach is utilized to rank the input variables for failure mode identification and explains the machine learning model predicting a specific failure mode for a given sample. In identifying the failure mode of corroded pipelines, the proposed Extreme Gradient Boosting model indicated the highest accuracy in term of performance evaluation compared to all other proposed models. In addition, the model-explanation findings show that the important parameter influencing the failure mechanism of corroded pipelines is the depth of corrosion defects followed by the pipeline wall thickness. The proposed framework is adaptable enough to allow further use of experimental results for having new insights.
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.
Modified response surface method basis harmony search to predict the burst pressure of corroded pipelines
(Elsevier, 2017) Keshtegar, Behrooz; Ben Seghier, Mohamed El Amine
Modified response surface method basis harmony search to predict the burst pressure of corroded pipelines
(Elsevier Ltd, 2018) Ben Seghier, Mohamed El Amine; Behrooz, Keshtegar
The accurate burst pressure prediction of pipelines with corrosion defects is important to provide a suitable design of water, oil, and gas pipes networks. Generally, the empirical burst pressure models for corroded pipelines have the narrow limitation for large-verity of steel grades. In this paper, a modified response surface model is proposed based on the novel learning procedure using harmony search algorithm to predict the burst pressure of corroded pipelines with different steel grades named as HS-MRSM. The nonlinear relation as a power and high-order polynomial functions is calibrated using improved harmony search for large experimental corroded pipes >572 in HS-MRSM model. The performances for both accuracy and agreement predictions of the HS-MRSM are compared with modified response surface method (MRSM) and existing empirical models using comparative statistics as root mean square error (RMSE), mean absolute error (MAE), the Nash-Sutcliffe Efficiency (NSE), and the Willmott index of agreement (d). The results demonstrated that the proposed HS-MRSM is significantly improved The burst pressure predictions of corroded pipelines compared to best empirical model and MRSM. Generally, the empirical models – based PCORRC format are performed the best predictions among other empirical models
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
Prediction of Lattice Constant of A 2 XY 6 Cubic Crystals Using Gene Expression Programming
(2020) Nait Amar, Menad; Ghriga, Mohammed Abdelfetah; Ben Seghier, Mohamed El Amine; Ouaer, Hocine
Lattice constant is one of the paramount parameters that mark the quality of thin film fabrication. Numerous research efforts have been made to calculate and measure lattice constant, including experimental and empirical approaches. Not withstanding these efforts, a reliable and simple-to-use model is still needed to predict accurately this vital parameter. In this study, gene expression programming (GEP) approach was implemented to establish trustworthy model for prediction of the lattice constant of A2XY6 (A = K, Cs, Rb, TI; X = tetravalent cation; and Y = F, Cl, Br, I) cubic crystals based on a comprehensive experimental database. The obtained results showed that the proposed GEP correlation provides excellent prediction performance with an overall average absolute relative deviation (AARD%) of 0.3596% and a coefficient of determination (R2) of 0.9965. Moreover, the comparison of the performance between the newly proposed correlation and the best pre-existing paradigms demonstrated that the established GEP correlation is more robust, reliable, and efficient than the prior models for prediction of lattice constant of A2XY6 cubic crystals
Probabilistic investigation on the reliability assessment of mid- and high-strength pipelines under corrosion and fracture conditions
(Elsevier, 2020) Guillal, Abdelkader; Ben Seghier, Mohamed El Amine; Abdelbaki, Noureddine; Correia, José A.F.O.; Zahiraniza, Mustaffa; Nguyen-Thoi, Trung
In order to reduce the economic costs of pipeline construction projects and for offering a good combination of strength and toughness for efficient transportation of large quantities of hydrocarbon products under high pressure, High Strength Steels (HSS) such as API 5L X70 to X120 are used recently in the construction of pipeline systems for the large oil and gas projects. The commonly utilized models for the reliability evaluation of the HSS pipelines may lead to some conservatism regarding the used data. This paper aims to evaluate the system reliability of HSS pipelines with combined corrosion and cracks defects. Therefore, two failure modes as the plastic collapse and fracture are considered. The effect of different correlations under the term of the strain-hardening exponent that depends on the yield to ultimate tensile strength (Y/T) ratio is investigated. The reliability index of HSS pipelines is evaluated separately for each failure mode using the subset simulation technique. Herein, the tensile strength proprieties of the HSS pipelines are taken into consideration, while the applied methodology utilizes novel probabilistic models to predict the burst pressure for the plastic collapse failure mode. The steels toughness is taken as equal to the minimum requirement for both the ductile and the brittle fracture arrest applied in the HSS pipelines. Moreover, the reliability of the system with multiple failure modes is evaluated to show the mutual existence effect of crack and corrosion defects on pipeline safety
Reliability analysis based on hybrid algorithm of M5 model tree and Monte Carlo simulation for corroded pipelines : case of study X60 Steel grade pipes
(Elsevier, 2019) Ben Seghier, Mohamed El Amine; Keshtegar, Behrooz; Correia, José A.F.O.; Lesiuk, Grzegorz; De Jesus, Abilio M.P.
Reliability analysis of low, mid and high-grade strength corroded pipes based on plastic flow theory using adaptive nonlinear conjugate map
(Elsevier, 2018) Ben Seghier, Mohamed El Amine; Keshtegar, Behrooz; Elahmoune, Bouali
Rigorous connectionist models to predict carbon dioxide solubility in various ionic liquids
(MDPI AG, 2020) Ouaer, Hocine; hossein hosseini, amir; Nait Amar, Menad; Ben Seghier, Mohamed El Amine; Ghriga, Mohammed Abdelfetah; Nabipour, Narjes; Pål Østebø, Andersen; Mosavi, Amir; Shamshirband, Shahaboddin
Estimating the solubility of carbon dioxide in ionic liquids, using reliable models, is ofparamount importance from both environmental and economic points of view. In this regard,the current research aims at evaluating the performance of two data-driven techniques, namelymultilayer perceptron (MLP) and gene expression programming (GEP), for predicting the solubilityof carbon dioxide (CO2) in ionic liquids (ILs) as the function of pressure, temperature, and fourthermodynamical parameters of the ionic liquid. To develop the above techniques, 744 experimentaldata points derived from the literature including 13 ILs were used (80% of the points for training and20% for validation). Two backpropagation-based methods, namely Levenberg–Marquardt (LM) andBayesian Regularization (BR), were applied to optimize the MLP algorithm. Various statistical andgraphical assessments were applied to check the credibility of the developed techniques. The resultswere then compared with those calculated using Peng–Robinson (PR) or Soave–Redlich–Kwong(SRK) equations of state (EoS). The highest coefficient of determination (R2=0.9965) and the lowestroot mean square error (RMSE=0.0116) were recorded for the MLP-LMA model on the full dataset(with a negligible difference to the MLP-BR model). The comparison of results from this model with
Structural reliability of corroded pipeline using the so-called Separable Monte Carlo method
(Sage journals, 2018) Ben Seghier, Mohamed El Amine; Bettayeb, Mourad; Correia, José; De Jesus, Abílio
The evaluation of the failure probability of corroded pipelines is an important calculation to quantify the risk assessment and integrity of pipelines. Traditional Monte Carlo simulation method has been widely used to solve this type of problems, where it generates a very large number of simulations and takes longer time in computing. In this study, enhanced computational method called Separable Monte Carlo is employed to evaluate the time-dependent reliability of pipeline segments containing active corrosion defects, where a practical example was used. The results show that the Separable Monte Carlo simulation method not only minimizes the computational cost strongly but also improves the calculation precision.