导航

ACTA AERONAUTICAET ASTRONAUTICA SINICA ›› 2022, Vol. 43 ›› Issue (5): 225363.doi: 10.7527/S1000-6893.2021.25363

• Solid Mechanics and Vehicle Conceptual Design • Previous Articles     Next Articles

Hybrid optimization method for structural layout and size of flight vehicles

HU Jiaxin1, RUI Shu2, GAO Ruichao2, GOU Jianjun1, GONG Chunlin1   

  1. 1. Shaanxi Aerospace Flight Vehicle Design Key Laboratory, School of Astronautics, Northwestern Polytechnical University, Xi'an 710072, China;
    2. Beijing Aerospace Technology Institute, Beijing 100074, China
  • Received:2021-02-04 Revised:2021-03-18 Published:2021-04-29
  • Supported by:
    National Natural Science Foundation of China (51806175); Fundamental Research Funds for the Central Universities (3102019HTXM004)

Abstract: An efficient hybrid optimization method is proposed to solve the problem of layout and size optimization in lightweight structural design of aircraft. A layout-size hybrid optimization model is constructed by introducing size variables into the traditional ground structure method. The Genetic Algorithm (GA) is used as the basic search method, and the chromosome is designed to uniformly describe the 0-1 type discrete layout variables and continuous size variables, and the solution process of the hybrid layout-size optimization of the structure is established. The neural network agent model is introduced in the solution process because of the large size of the population. By predicting the individual population, the number of individuals that need to be accurately calculated in each generation is reduced. A wing structure optimization design with 55 layout variables and 55 size variables is taken as an example, and the results verify the feasibility of the method. Compared with the traditional ground structure method, the new method can further reduce the weight by 13%. Furthermore, the introduction of the agent model reduces the computational cost by about 50%.

Key words: flight vehicle structure design, hybrid optimization, layout optimization, size optimization, genetic algorithm (GA), agent model

CLC Number: