Sensitivity of reliability-based fatigue analysis to crack shape development in cracked pipeline

Guillal, Abdelkader; Abdelbaki, Nourdine; Seghier, Mohamed El Amine Ben; Correia, José A.F.O.; Jesus, Abílio M.P. De; Zhu, Shun‐Peng

doi:10.1016/j.prostr.2020.01.026

Cited by 4 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Ensuring correct estimation of the failure probability for structures that contain crack defects resulted from the surrounded environment loads is the major critical task 6,7 . Remaining fatigue life assessment (RFLA) is usually employed to evaluate the reliability analysis of structures with crack defect propagation.…”

Section: Introductionmentioning

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

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

Section: Introductionmentioning

confidence: 99%