Research on Multi-Objective Optimization Method of eVTOL Connection Structure Based on Convolutional Neural Network and Dwarf Mongoose Optimization Algorithm

Abstract

This paper studied the fallable structure of the seat and floor connection of the 500kg multi-rotor manned electric vertical take-off and landing (eVTOL) aircraft. In view of the lack of research on fallable structures, especially for seat connection structures, this paper proposes a multi-objective optimization method based on neural network and pygmy mongoose algorithm. By constructing the finite element model and conducting simulation analysis, combined with the CNN surrogate model and DMOA, the optimization of the crashworthiness of the structure was realized. The results show that the proposed optimization method can improve the crashworthiness while ensuring the lightweight of the structure, and provides a new solution for the design of eVTOL seat connection structure