This study proposes an optimal design of a dolphin structure under offshore load conditions such as berthing, mooring, wind, wave, and current loads. The design objective is to reduce the total weight of the pile structure by determining its diameter, thickness, and arraying direction with constraints of axial compressive pressure-bending moment ratio and total displacement. As design requirements, the stress has to be satisfied under the allowable compressive pressure-bending moment, and the total displacement of the steel piles should be less than 0.1 m on the upper deck. The structural analysis data are generated using Box–Behnken design based on the design of experiments. In the meta-model-based approximate optimization process, the pressure-bending moment ratio and total displacement are expressed using a backpropagation neural network, and the structural weight of the pile is approximated via a second-order polynomial-based response surface model. Compared with the initial design, the optimal solution of the total weight of the steel piles reduces by 27.37% under the satisfied constraint conditions. For the post-optimization study, the optimal sensitivity analysis with respect to the seabed level is conducted.
Article history:Presently, rapidly changing and unstable global economic environments demand engineers. Products should be designed to increase profits by lowering costs and provide distinguished performance compared with competitors. This study aims to optimize the design of the power-transmission drive shaft. The mass is reduced as an objective function, and the stress is constrained under a constant value. To reduce the number of experiments, CCD (central composite design) and D-Optimal are used for the experimental design. RSM (response surface methodology) is employed to construct a regression model for the objective functions and constraint function. In this problem, there is only one objective function for the mass. The other objective function gives 1; thus, NSGA-II is used.
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.