Search

Two-dimensional inlet is usually used in the wide-speed-range aircraft which has a higher flying velocity region. It is difficult to meet more requirements under both low-speed and high-speed flow conditions. Although the inlet perfor-mance could be improved by using jets to control shock waves on compression ramps, the existing jet excitation only push the shock wave toward the cowl, which may not achieve optimal performance. The optimization of jet control parameters is a significant problem. The effects of different optimization variables on inlet performance were investigated at Ma=6 based on Isight with the Hooke-Jeeves optimization method, in which different jet parameters were selected as optimization variables, flow coefficient was selected as constraint condition and maximum total pressure recovery coefficient was selected as objective function for optimization. The result show that the Hooke-Jeeves optimization method is able to optimize inlet with jet control. The optimized inlet can meet the requirements of flow coefficients. The total pressure recovery coefficient after optimizing the jet angle is increased by 18% compared to the inlet without jet, and the total pressure recovery coefficient after combination optimization is increased by 2.82% compared to only optimizing the jet angle.

Recommender systems are widely used in e-commerce, movies, music, social media, and other fields because of their personalized recommendation functions. The recommendation algorithm is used to capture user preferences, item characteristics, and the items that users are interested in are recommended to users. Matrix factorization is widely used in collaborative filtering algorithms because of its simplicity and efficiency. However, the simple dot-product method cannot establish a nonlinear relationship between user latent features and item latent features or make full use of their personalized information. The model of a neural network combined with an attention mechanism can effectively establish a nonlinear relationship between the potential features of users and items and improve the recommendation accuracy of the model. However, it is difficult for the general attention mechanism algorithm to solve the problem of attention interaction when the number of features between the users and items is not the same. To solve the above problems, this paper proposes an attention interaction matrix factorization (AIMF) model. The AIMF model adopts a symmetric structure using MLP calculation. This structure can simultaneously extract the nonlinear features of user latent features and item latent features, thus reducing the computation time of the model. In addition, an improved attention algorithm named slide-attention is included in the model. The algorithm uses the sliding query method to obtain the user’s attention to the latent features of the item and solves the interaction problem among different dimensions of the user, and the latent features of the item.