Airship comprehensive optimization method based on neural network

The invention discloses an airship comprehensive optimization method based on a neural network. The method comprises the following steps: 1) constructing an airship body aerodynamic characteristic data set; 2) according to the airship body aerodynamic characteristic data set, establishing an airship body resistance coefficient rapid prediction model; 3) establishing a precise calculation model for the output characteristics of the solar cells on the surface of the boat body; 4) establishing a multidisciplinary optimization framework through the boat body resistance coefficient rapid prediction model and the boat body surface solar cell output characteristic accurate calculation model; and 5) optimizing the established multidisciplinary optimization framework. According to the method, a pneumatic calculation model and a solar cell calculation model are integrated by adopting a parallel subspace method, and a comprehensive optimal result of airship appearance and solar cell laying is obtained through global opt