Search

The aim of this study is to develop a new framework for the prediction of stress intensity factor (SIF) using newly developed hybrid artificial intelligence (AI) models. To do so, an adaptive neuro‐fuzzy inference system optimized by two meta‐heuristic algorithms as genetic algorithm (ANFIS‐GA) and particle swarm optimization (ANFIS‐PSO) is proposed. Moreover, a database composed of 150 SIF values obtained using the finite element method (FEM) calculations is used for training and validating the two proposed AI models. The efficiency and accuracy of the proposed AI models were investigated through several assessment criteria. Results showed the outperformance of the ANFIS‐PSO model for accurate prediction of SIF values with R2= 0.9913, root mean square error (RMSE) = 23.6 and mean absolute error (MAE) = 18.07, whereas both AI models indicate a robust performance in the presence of input variability. Overall, the performed study provides a hybrid AI framework that can serve as an efficient numerical tool for SIF prediction and analysis. [ABSTRACT FROM AUTHOR]

• Experimental and modeling investigations were performed and combined to establish trustworthy paradigms to predict the crude oil viscosity. • Measurements are done at wide variety of conditions (pressure from 0.1 to 69.4 MPa, temperature from 322 to 415 K, and heavy to light oils). • Advanced computational modeling approaches are applied for modeling based on crude oil composition, pressure and temperature. In the present study, experimental and modeling investigations were performed and combined to implement trustworthy paradigms to predict the viscosity value under different circumstances and a wide variety of conditions. The experimental approach was conducted on a considerable number of Iranian crude samples using a Rolling Ball viscometer. Accordingly, more than 1000 experimental points were gained. These latter were utilized as a databank in the modeling approach which included many advanced soft computing techniques, namely radial basis function (RBF) neural network, multilayer perceptron (MLP), support vector regression (SVR), adaptive neuro-fuzzy inference system (ANFIS), decision trees (DTs) and random forest (RF). When performing the modeling tasks using these techniques, two distinct cases were considered: the first includes all available parameters as inputs such as pressure, temperature, API°, Mw of C 12+ and the mole fractions till C11; whereas in the second case, a grouping scheme was considered to reduce the number of fractions. The obtained results revealed that DTs for the first case is the best implemented model with an overall average absolute relative deviation (AARD) of 3.379%. In addition, the comparison results with the preexisting approaches showed the superiority of the newly proposed model. [ABSTRACT FROM AUTHOR]

This paper proposes a practical implementation of robust ensemble learning models for accurate prediction of the internal corrosion rate in oil and gas pipelines. A correct assessment of the corrosion rate in fluid flowed oil and gas pipelines has a significant influence on the system's safety and the ability to control operation. The developed predictive data driven models include four ensemble learning approaches, namely random forest, adoptive boosting, gradient boosting regression tree, and extreme gradient boosting. The implementation procedure of these predictive models integrates a comprehensive database of eight system descriptors, extracted from the literature, while k -fold cross validation is employed to guarantee high performance and generalization. In addition, the obtained results of the internal corrosion rate are subjected to rigorous statistical and graphical analysis to evaluate the models performance and compare their abilities. The extreme gradient boosting model indicate the highest performance in the prediction of the internal corrosion rate in oil and gas pipelines based on the calculated single and global metrics, with a mathematical RMSE value of internal corrosion rate 0.031 mm/y and performance index, PI = 0.61. Besides, the significance of the input variables is determined through a sensitivity analyses by using feature importance criteria, whereas for the applied dataset strongest corrosion rate dependency to temperature and the pressure was shown beside the CO 2 contribution. In overall, the ensemble learning models show a significant performance in the internal corrosion rate predictions, while the extreme gradient boosting model is beneficial to model the internal corrosion rate in oil and gas pipelines due to its high performance. • A novel framework for the internal corrosion rate prediction in oil and gas pipelines is proposed using Ensemble Learning techniques. • Single and global criteria are used to evaluate and compare the performance of the proposed EL-models. • The proposed EL-models show superior accuracy compared to the single ML-models and empirical correlation. • The extreme gradient boosting model provide the highest performance with RMSE = 0.031 mm/y and R2 = 0.99. [ABSTRACT FROM AUTHOR]