Wind tunnel tests involve many links and the test results are affected by many factors. Among them, the elastic deformation of the non-rigid aircraft model is one of the important reasons that significantly affects the wind tunnel test data. Therefore, wind tunnel test data cannot be directly used in aircraft design and related engineering applications, and static aeroelastic correction is required to obtain aerodynamic test data without deformation effects. In this paper, we mainly focus on the application of deep learning in static aeroelastic correction, taking the transport aircraft scale-model configuration CHN-T1 as the research object, building an aerodynamic data model for static aeroelastic correction through data augmentation, data fusion, neural network and other techniques based on the existing conventional wind tunnel test data and CFD calculation data, and then constructing a neural network-based static aeroelastic correction method. The results show that the correction results of the neural network-based hydrostatic aeroelastic correction method proposed in this paper are less than 5% error compared with the correction results of the incremental method based on CFD, and the correction efficiency is improved by more than 10 times.