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.
Increasing traffic demands (ie, load intensity and operational life) on ancient riveted metallic bridges and the fact that these bridges were not explicitly designed against fatigue make the fatigue performance assessment and fatigue life prediction of riveted bridges a concern. This paper proposes a global‐local fatigue analysis method that integrates beam‐to‐solid submodeling, elastoplastic of material in local region, and local fatigue life prediction approach. The proposed beam‐to‐solid submodeling can recognize accuracy local stress/strain information accompanying with the global structural effect on the fatigue response of local riveted joints. The fatigue life is predicted based on cumulative damage rule, local strains, and number of cycles with consideration of traffic data, where the relation between the fatigue life and local strain is derived according to the Basquin and Manson‐Coffin law. Besides, the elastoplastic of material is considered. The proposed methodology for fatigue life prediction based on local strain parameter and the Palmgren‐Miner linear damage hypothesis is implemented in a case study of an ancient riveted bridge.
The fatigue design of offshore structures normally uses wave and wind fatigue loading. Currently, fatigue analyses for fatigue damage accumulation assessments of this type of structure are based on signal–noise (S–N) curves for welded structural components, the hot-spot stress approach and the Palmgren–Miner law – according to design codes. Fatigue analyses in design codes and/or recommended practices are supported by global structural analysis. In this paper, a global–local fatigue methodology applied to an offshore jacket-type platform using a local approach through the notch strain damage parameter is proposed. The local approach is based on Neuber's rule combined with the Ramberg–Osgood description. Then, the Coffin–Manson strain–life relation together with the Palmgren–Miner linear damage rule are used to evaluate the fatigue damage accumulation for the critical tubular welded joint. For application of Neuber's rule, the stress concentration factor values are calculated, according to Efthymiou's analytical equations, for the connection under consideration. The proposed methodology is compared with the simplified fatigue analysis presented in the Det Norske Veritas (Norway) and Germanischer Lloyd (Germany) DNVGL-RP-C203 recommendations. These analyses were performed using wave loads from the scatter diagram collected in the North Sea, which were computed through the fifth-order Stokes wave theory and the Morrison formula.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.