Prediction of maximum pitting corrosion depth in oil and gas pipelines

Seghier, Mohamed El Amine Ben; Keshtegar, Behrooz; Tee, Kong Fah; Zayed, Tarek; Abbassi, Rouzbeh; Nguyen-Thoi, T.

doi:10.1016/j.engfailanal.2020.104505

Cited by 90 publications

(26 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These indicators include the mean bias error ( MBE ), the root mean square error ( RMSE ), the mean absolute error ( MAE ), the Nash–Sutcliffe efficiency ( NSE ), the Willmott index of agreement ( d ), confidence index ( CI ) and the coefficient of determination ( R 2 ). Equations 17–23 express the formulas of those indicators as follows 52,53 :

italicMBE = \frac{1}{n} \sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true^}{{SIF}_{i}})}^{2},

italicRMSE = \sqrt{\frac{1}{n} \sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true^}{{SIF}_{i}})}^{2},}

italicMAE = \frac{1}{n} \sum_{i = 1}^{n} (||, {SIF}_{i} - \overset{{italicSIF}_{i}}{true}),

italicNSE = 1 - \frac{\sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true^}{{SIF}_{i}})}^{2}}{\sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true¯}{{SIF}_{i}})}^{2}} - \infty \leq italicNSE \leq 1,

d = 1 - \frac{\sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true^}{{SIF}_{i}})}^{2}}{\sum_{i = 1}^{n} (||)}

…”

Section: Methodsmentioning

confidence: 99%

Novel hybridized adaptive neuro‐fuzzy inference system models based particle swarm optimization and genetic algorithms for accurate prediction of stress intensity factor

Seghier

Carvalho

Keshtegar

et al. 2020

Fatigue Fract Eng Mat Struct

Self Cite

View full text Add to dashboard Cite

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 R 2 = 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.

show abstract

italicMBE = \frac{1}{n} \sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true^}{{SIF}_{i}})}^{2},

italicRMSE = \sqrt{\frac{1}{n} \sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true^}{{SIF}_{i}})}^{2},}

italicMAE = \frac{1}{n} \sum_{i = 1}^{n} (||, {SIF}_{i} - \overset{{italicSIF}_{i}}{true}),

italicNSE = 1 - \frac{\sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true^}{{SIF}_{i}})}^{2}}{\sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true¯}{{SIF}_{i}})}^{2}} - \infty \leq italicNSE \leq 1,

d = 1 - \frac{\sum_{i = 1}^{n} {({italicSIF}_{i} - \overset{true^}{{SIF}_{i}})}^{2}}{\sum_{i = 1}^{n} (||)}

…”

Section: Methodsmentioning

confidence: 99%

Novel hybridized adaptive neuro‐fuzzy inference system models based particle swarm optimization and genetic algorithms for accurate prediction of stress intensity factor

Seghier

Carvalho

Keshtegar

et al. 2020

Fatigue Fract Eng Mat Struct

Self Cite

View full text Add to dashboard Cite

show abstract

“…In past studies, this diagram has been used to compare estimating methods. 108,109 This type of diagram combines several indices in order to present how the predicted values are matched against the real measurements. Using three error criteria, standard deviation, correlation coefficient, and RMSE, Taylor diagram was plotted for the total specimens as displayed in Figure 6.…”

Section: Taylor Diagrammentioning

confidence: 99%

Estimating the compressive strength of rectangular fiber reinforced polymer–confined columns using multilayer perceptron, radial basis function, and support vector regression methods

Moodi

Ghasemi

Mousavi

2021

Journal of Reinforced Plastics and Composites

View full text Add to dashboard Cite

Recently, there has been a tendency to use machine learning (ML)–based methods, such as artificial neural networks (ANNs), for more accurate estimates. This paper investigates the effectiveness of three different machine learning methods including radial basis function neural network (RBNN), multi-layer perceptron (MLP), and support vector regression (SVR), for predicting the ultimate strength of square and rectangular columns confined by various FRP sheets. So far, in the previous study, several experiments have been conducted on concrete columns confined by fiber reinforced polymer (FRP) sheets with the results suggesting that the use of FRP sheets enhances the compressive strength of concrete columns effectively. Also, a wide range of experimental data (including 463 specimens) has been collected in this study for square and rectangular columns, confined by various FRP sheets. The comparison of ML-derived results with the experimental findings, which were in a very good agreement, demonstrated the ability of ML to estimate the compressive strength of concrete confined by FRP; the correlation coefficient (R2) for MLP, RBFNN, and SVR methods was equal to 0.97, 0.97, and 0.90, respectively. Similar accuracy was obtained by MLP and RBFNN, and they provided better estimates for determining the compressive strength of concrete confined by FRP. Also, the results showed that the difference between statistical indicators for training and testing specimens in the RBFNN method was greater than the MLP method, and this difference indicated the poor performance of RBFNN.

show abstract

“…Therefore, it is of paramount importance to quantify the service life and reliability of RC beams that are subjected to aggressive environmental conditions which could lead to corrosion of the reinforcing steel. Corrosion is one of the main issues for structures made of steel that can have a high risk of failure according to several studies [12][13][14][15][16][17]. The development of an appropriate formulation to capture the behavior Materials 2021, 14, 1820 2 of 15 of RC beams subjected to different corrosion forms with an accurate structural reliability framework will enable owners and field engineers to make more risk-informed decisions to increase the service life of the structure by performing the required maintenance actions.…”

Section: Introductionmentioning

confidence: 99%

Time-Dependent Reliability Analysis of Reinforced Concrete Beams Subjected to Uniform and Pitting Corrosion and Brittle Fracture

2021

Self Cite

View full text Add to dashboard Cite

Reinforced concrete (RC) beams are basic elements used in the construction of various structures and infrastructural systems. When exposed to harsh environmental conditions, the integrity of RC beams could be compromised as a result of various deterioration mechanisms. One of the most common deterioration mechanisms is the formation of different types of corrosion in the steel reinforcements of the beams, which could impact the overall reliability of the beam. Existing classical reliability analysis methods have shown unstable results when used for the assessment of highly nonlinear problems, such as corroded RC beams. To that end, the main purpose of this paper is to explore the use of a structural reliability method for the multi-state assessment of corroded RC beams. To do so, an improved reliability method, namely the three-term conjugate map (TCM) based on the first order reliability method (FORM), is used. The application of the TCM method to identify the multi-state failure of RC beams is validated against various well-known structural reliability-based FORM formulations. The limit state function (LSF) for corroded RC beams is formulated in accordance with two corrosion types, namely uniform and pitting corrosion, and with consideration of brittle fracture due to the pit-to-crack transition probability. The time-dependent reliability analyses conducted in this study are also used to assess the influence of various parameters on the resulting failure probability of the corroded beams. The results show that the nominal bar diameter, corrosion initiation rate, and the external loads have an important influence on the safety of these structures. In addition, the proposed method is shown to outperform other reliability-based FORM formulations in predicting the level of reliability in RC beams.

show abstract

Prediction of maximum pitting corrosion depth in oil and gas pipelines

Cited by 90 publications

References 40 publications

Novel hybridized adaptive neuro‐fuzzy inference system models based particle swarm optimization and genetic algorithms for accurate prediction of stress intensity factor

Novel hybridized adaptive neuro‐fuzzy inference system models based particle swarm optimization and genetic algorithms for accurate prediction of stress intensity factor

Estimating the compressive strength of rectangular fiber reinforced polymer–confined columns using multilayer perceptron, radial basis function, and support vector regression methods

Time-Dependent Reliability Analysis of Reinforced Concrete Beams Subjected to Uniform and Pitting Corrosion and Brittle Fracture

Contact Info

Product

Resources

About