Due to the high specific stiffness and strength, composite shells have been widelyused in fuel tanks of launch vehicles. The buckling analysis of composite shells withcutouts based on the finite element (FE) method is too time-consuming. From thepoint-of-view of model size reduction, a novel Proper Orthogonal Decomposition(POD)-based buckling method is proposed in this paper, which can significantlyincrease the computational efficiency of buckling analysis. In order to improve theefficiency and effectiveness of prediction and optimization of composite shells withmultiple cutouts, the POD method is integrated into an optimization framework thatuses Gaussian process (GP) machine learning method. First, the training set used forthe machine learning training is generated efficiently by means of the POD method.Then, the obtained set is trained and tested based on the Gaussian process method. Theinputs are ply angles of the composite shell and the output is the buckling load of thecomposite shell containing cutouts. In order to maximize the buckling load of thecomposite shell against cutouts, the Genetic Algorithm is combined with the trainedGaussian process method to search for the optimal ply angles. Finally, an illustrativeexample is carried out to demonstrate the effectiveness of the proposed prediction andoptimization framework.
展开▼
