Topology optimization analysis of VLCC transverse web based on UNet deep learning

Objectives In order to apply it to the optimization design of complex ship structures, this paper proposes a hull transverse web topology optimization method based on UNet.

Methods Taking a VLCC transverse web as the research object, the UNet topology optimization surrogate model is first created according to the optimization mathematical principles; then the finite element grid physical quantity is mapped to the tensor to obtain the dataset for model training; finally, the intersection over union (IoU) method is used to evaluate the training results, and the method is compared with the SIMP method in terms of topology configuration.

Results The results show that this topology optimization method can quickly output the material layout of the design domain, and compared with SIMP topology optimization, it can obtain the topology configuration more efficiently.

Conclusions The proposed topology optimization method can provide a new design method for ship transverse web structures.