Correct evaluation of the blades' surface temperature field is crucial to the structural design and operational safety of aero-engine turbine blades. Current high-temperature measurement technology can only measure the limited discrete points temperature of the hot-end turbine blades. If the boundary conditions are completely unknown, it is still difficult to solve equations through traditional computational fluid dynamics methods. It is an inverse problem to predict the temperature field of the turbine engine blade with unknown boundary conditions. This paper proposes a two-dimensional temperature field inversion of turbine blades based on physics-informed neural networks (PINN) and finite discrete temperature measurement points. The PINN is used to model the nonlinear mapping of input variables and output variables. Only a small amount of data is used to train the neural network. It can be found that adding the loss term of the physical governing equation during training can make the neural network better predict the temperature field of the turbine blade, which can also avoid anomalies such as large temperature errors in some areas that may occur when training with only a small amount of data. When the boundary conditions are completely unknown, the average relative error of PINN trained with only 62 points of temperature data on the test set is below 2%, and the R2−Score is above 0.95. When the training data reaches 122 points of temperature data, the average relative error of PINN on the test set is less than 1%, and the R2−Score reaches 0.99.

The traditional optimization of airfoils relies on, and is limited by, the knowledge and experience of the designer. As a method of intelligent decision-making, reinforcement learning can be used for such optimization through self-directed learning. In this paper, we use the lift–drag ratio as the objective of optimization to propose a method for the aerodynamic optimization of airfoils based on a combination of deep learning and reinforcement learning. A deep neural network (DNN) is first constructed as a surrogate model to quickly predict the lift–drag ratio of the airfoil, and a double deep Q-network (double DQN) algorithm is then designed based on deep reinforcement learning to train the optimization policy. During the training phase, the agent uses geometric parameters of the airfoil to represent its state, adopts a stochastic policy to generate optimization experience, and uses a deterministic policy to modify the geometry of the airfoil. The DNN calculates changes in the lift–drag ratio of the airfoil as a reward, and the environment constantly feeds the states, actions, and rewards back to the agent, which dynamically updates the policy to retain positive optimization experience. The results of simulations show that the double DQN can learn the general policy for optimizing the airfoil to improve its lift–drag ratio to 71.46%. The optimization policy can be generalized to a variety of computational conditions. Therefore, the proposed method can rapidly predict the aerodynamic parameters of the airfoil and autonomously learn the optimization policy to render the entire process intelligent.

Shock wave/boundary layer interaction (SWBLI) is a widespread phenomenon in supersonic flows and has received extensive attention. The boundary layer is generated due to viscous stress, which is a kind of macroscopic manifestation of molecular nonequilibrium motion, namely, nonequilibrium effects. In this paper, an investigation is conducted on SWBLI from the perspective of nonequilibrium effects. A method is proposed for studying nonequilibrium effects based on the Navier–Stokes (NS) equations and the Reynolds-averaged NS (RANS) equations. The SWBLI at Mach 2 and Mach 6 is concerned. The results show that nonequilibrium effects associated with the incident shock wave are weaker than that in the boundary layer for a Mach 2 incoming flow. Neither the separation shock wave nor the incident shock wave has an obvious interaction with nonequilibrium effects in the boundary layer. However, the nonequilibrium effects of the incident shock wave are stronger for a Mach 6 incoming flow, and it has an obvious interaction with the nonequilibrium effect in the boundary layer. We also discuss the relation between nonequilibrium effects and energy conversion in the boundary layer. The analysis reveals that changes in the gradients of total energy-related nonequilibrium effects contribute to the change in total energy by influencing the gradient of the heat flux and the power of viscous stress. Thus, this work provides the flow characteristics of boundary layer separation and energy conversion mechanism of SWBLI from the perspective of nonequilibrium effects, as well as the interaction of nonequilibrium effects between the shock wave and boundary layer.

This paper investigates the effect of curvature on curved detonation and its reflections. Specifically, the study focuses on two aspects: the effect of curvature on the postwave parameters and their gradients, and the stabilization of Mach reflection. Relationships are established between the curvature and the gradients of the postwave parameters, thus providing a basis for examining detonation reflections and obtaining a comprehensive understanding of curved detonation. In particular, these relationships offer a valuable analytical tool to predict the postwave gradients, as well as providing a fresh perspective to understand the transformation from Mach reflection to regular reflection in curved detonation. The validity of these relationships is confirmed by comparison with simulation results. Two mechanisms by which curvature influences the stationarity of Mach reflection are identified. An increase in wave angle and interference between wave systems leading to the generation and integration of subsonic zones are the reasons for the non-stationarity of the Mach reflection in curved detonation. Besides, the effect mechanisms of choked flow which is considered to be the root cause are analysed in detail. On the basis of a theoretical model, the development of a quantitative criterion for the stability of detonation reflection is proposed, and its validity is confirmed by simulations. This criterion is used in a comprehensive investigation of the primary factors affecting the stability of detonation wave reflections, providing insights that will be of great value for the further development of detonation engines.

The physical characteristics inside shock waves with nonequilibrium molecular motion are difficult to describe using conventional macroscopic methods. In this paper, nonequilibrium hydrodynamic and thermodynamic effects caused by the strong nonequilibrium molecular velocity distribution at a shock wave are studied using a mesoscopic kinetic approach. This approach is based on a lattice Boltzmann method and a kinetic nonequilibrium method. The former adopts a compressible double-distribution-function model with separated density and total energy distribution functions. The latter represents the nonequilibrium effects through nonequilibrium kinetic moments based on the nonequilibrium molecular velocity distribution. The nonequilibrium effects in the steady state and the process of the formation of a regular reflection shock wave are presented. Nonequilibrium effects inside the shock wave are further investigated. First, the curvature pattern during the formation of a regular reflection shock wave is addressed. The curvature characteristic leads to distinct features of nonequilibrium effects compared with the linear pattern. A vector-based approach for visualizing nonequilibrium effects is proposed to study the curvature pattern. Second, the influence of viscosity on nonequilibrium effects, which is related to the average collision time among molecules at the shock wave, is explored. The results obtained in this paper provide mesoscopic physical insight into the flow mechanisms occurring in shock waves.

Combined-cycle engine is a potential propulsion system for hypersonic aircraft. To ensure long-term, normal operation of combined-cycle engine under the harsh environment of high thermal load, it is of great significance to study the thermal protection and management of the propulsion system. In this study, the objective and development status of thermal protection and thermal management systems for the combined-cycle propulsion system were described. The latest research progresses of thermal protection, thermal barrier coating, and thermal management system of the combined-cycle propulsion system were summarized. Moreover, the problems and shortcoming in current researches were summarized. In addition, a prospect for the future development of thermal protection and management of the combined-cycle propulsion system was presented, pointing out a direction of great value and vital research significance to thermal protection and management of the combined-cycle propulsion system.