Abstract
Ice loads are major environmental loads that are encountered during navigation in the polar regions and can affect the structural safety of a ship, thereby leading to severe structural or fatigue damage to the ship structure. To identify full-scale ice loads, an ice load measurement on XueLong was performed during an Arctic voyage in August 2017. The least square support vector machine (LS_SVM) algorithm was utilised in the ice load identification model, and an experimental application was performed to validate the feasibility of the identification model. Two typical ship–ice interaction cases were analysed via time–procedure analysis. During the trials, 306 cases were analysed, and 16,178 extreme values of ice loads were extracted via the extreme selection procedure. Three commonly used fitting models—the Weibull, exponential, and lognormal models—were adopted for analysing the distribution of extreme values, and the Weibull distribution model was selected via a goodness-of-fit test. Considering the main parameters that influence ice loads, a grey relational analysis was performed to determine the input variables of the parametric model of extremes. The parametric statistics can aid in the development of an early warning system for detecting ice loads.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
