Genetic optimization method of ship strong frame based on sequential surrogate model

Abstract

Objectives The optimization design of a ship strong frame structure under the requirements of common structural rules (CSR) is a complex and time-consuming problem, moreover, it has tremendous constraints so that the feasibility of a design scheme is hard to identify. When adopting the static surrogate assisted evolutionary algorithm to solve this problem, since the approach aims at global accuracy, the prediction of key area will be distorted in the case of small size samples. However, the active-learning surrogate-based approach can solve this bottleneck since it can improve the accuracy of key area sequentially by adding samples to refine the surrogate model purposely. Therefore, this method can obtain better optimization scheme and save computational burden compared with the former one. Methods Aiming at the problem, an optimization method for strong frame based on sequential surrogate assisted genetic algorithm is proposed. Firstly, the constraints on strong frame structure based on CSR are analyzed, and all 675 constraints are reduced to 2 positive constraints according to the type of constraints. Then surrogates for objective function and constraints functions are constructed. Next, feasibility principle based genetic algorithm is adopted to solve it. After optimized solution is obtained, its true response is calculated and surrogates will be updated. In addition, expected feasibility function criterion is applied to update constraints surrogates, the purpose of which is to refine the prediction accuracy at the constraints boundary. Iterate the above procedures for several times, the optimized global feasible solution will be obtained finally. Results It is found that the proposed method is able to get better solution than static surrogate based algorithm with less computation resource and the weight of design area is reduced by 15.55% finally. Conclusions Proposed sequential surrogate based algorithm is superior to static surrogate based algorithm and has good application value in the optimization of ship structure under complex constraints.