Approximation of the maximum dynamic stress range in steel catenary risers using artificial neural networks. (1st June 2015)

• Record Type: Journal Article
• Authors: Quéau, Lucile M.; Kimiaei, Mehrdad; Randolph, Mark F.
• Is Part Of: Engineering structures. Volume 92(2015:Jun. 01)
• Page Start: 172
• Page End: 185
• Publication Date: 2015-06-01
• Subjects: Steel catenary risers -- Fatigue -- Sensitivity analyses -- Design of experiment -- Artificial neural network; Structural engineering -- Periodicals; Structural analysis (Engineering) -- Periodicals; Construction, Technique de la -- Périodiques; Génie parasismique -- Périodiques; Pression du vent -- Périodiques; Earthquake engineering; Structural engineering; Wind-pressure; Periodicals; 624.105
• DOI: 10.1016/j.engstruct.2015.02.025
• Languages: English
• ISSNs: 0141-0296

Abstract

Highlights: The sensitivity of SCR fatigue damage in the TDZ is investigated. A large database is generated using automation subroutine. The response surface method is applied with a series of ANNs. An approximation of the maximum dynamic stress range in the TDZ is defined. The approximation predicts well the fatigue life of selected example SCRs. Abstract: Adequate assessment of fatigue damage in steel catenary risers (SCRs) is essential, and usually evaluated with time consuming numerical analyses. Simplified design strategies would improve the efficiency of the screening tasks in the early design stages. As part of on-going research aiming to define a simplified fatigue design procedure for SCRs in the touchdown zone (TDZ), the sensitivity of fatigue damage to various parameters is explored using a large database (>40, 000 cases). An approximation of the maximum stress range in the TDZ is established using several artificial neural networks and predicts well the fatigue life of selected example SCRs.