An onboard three-dimensional (3D) trajectory generation approach based on the reinforcement learning (RL) algorithm and deep neural network (DNN) is proposed for hypersonic vehicles in glide phase. Multiple trajectory samples are generated offline through the convex optimisation method. The deep learning (DL) is employed to pre-train the DNN for initialising the actor network and accelerating the RL process. Based on the offline deep policy deterministic actor-critic algorithm, a flight target-oriented reward function with path constraints is designed. The actor network is optimised by the end-to-end RL and policy gradients of the critic network until the reward function converges to the maximum. The actor network is considered as the onboard trajectory generator to compute optimal control values online based on the real-time motion states. The simulation results show that the single-step online planning time meets the real-time requirements of onboard trajectory generation. The significant improvement in terminal accuracy of the online trajectory and the better generalisation under biased initial states for hypersonic vehicles in glide phase is observed.

As an effective drag reduction and thermal protection technology, the opposing jet can guarantee the flight safety of the hypersonic vehicle. In this paper, the jet mode transition is realised by controlling the total jet pressure ratio value (PR) with a function. The jet mode transition from the long penetration mode (LPM) to the short penetration mode (SPM) uses an increasing function. However, the jet mode transition from SPM to LPM uses a decreasing function. The flow field reconstruction process of a two-dimensional axisymmetric blunt body model in the hypersonic flow is studied when the jet mode transition between SPM and LPM changes into each other. The flow field structures and wall parameters of the LPM and SPM transition processes are obtained. The results indicate that the drag and Stanton number both decrease in the transition stage from LPM to SPM, and this is beneficial for the improvement of the drag reduction and thermal protection effect. The peak values of drag and Stanton number fall by 36.39% and 46.40%, respectively. When the jet mode transforms from SPM to LPM, the Stanton number increases, and the drag force first increases and then decreases. However, the final drag reduction effect is not obvious. With the increase in the change rate of the total pressure ratio of the two jet transformation modes, the jet mode transition time is advanced, and the flow field changes more violently.

A distributed UAV (unmanned aerial vehicle) flocking control method based on vision geometry is proposed, in which only monocular RGB (red, green, blue) images are used to estimate the relative positions and velocities between drones. It does not rely on special visual markers and external infrastructure, nor does it require inter-UAV communication or prior knowledge of UAV size. This method combines the advantages of deep learning and classical geometry. It adopts a deep optical flow network to estimate dense matching points between two consecutive images, uses segmentation technology to classify these matching points into background and specific UAV, and then maps the classified matching points to Euclidean space based on the depth map information. In 3D matching points, also known as 3D feature point pairs, each of their classifications is used to estimate the rotation matrix, translation vector, velocity of the corresponding UAV, as well as the relative position between drones, based on RANSAC and least squares method. On this basis, a flocking control model is constructed. Experimental results in the Microsoft Airsim simulation environment show that in all evaluation metrics, our method achieves almost the same performance as the UAV flocking algorithm based on ground truth cluster state.

Although a coaxial compound helicopter can takeoff without propeller in the normal condition, the distance should be as short as possible for obstacle avoidance when the vehicle operates in a confined area with heavy loads. Therefore, a suitable propeller control is required to improve the takeoff performance while the total power consumption is no more than the available power. The path is predicted by applying trajectory optimisation. Several varying takeoff parameters, including attitude, liftoff speed and obstacle height, are considered for optimum global performance. Three path indicators are proposed. Apart from typical distance and pilot workload, path sensitivity is quantified based on deviation from takeoff parameter variation. Results indicated that low propeller thrust at hover and moderate allocation on the propeller through flight is recommended. The aircraft achieves significantly improved takeoff performance compared to flight with pure rotors while maintaining the maximum takeoff weight. The distance is shortened by 12.6%, and the longitudinal pilot workload is alleviated by 9.8% and 7.3% from mean and maximum power frequency aspects. Besides, the path is less sensitive to takeoff parameter variations, such as speed, altitude and height.

Lamb waves are a growing method for the Non-Destructive Testing and Evaluation (NDT&E) and structural health monitoring (SHM) of aerospace vehicles. These guided waves can propagate over large distances and have a strong tendency to interact with damage. Whilst several methods exist for the modelling of Lamb wave propagation, this paper is the first to introduce a first principles numerical model that can efficiently and accurately predict the behaviour of Lamb waves. The numerical model is easier to understand and implement compared with analytical solutions and significantly faster than discretised numerical methods. The numerical model is presented in detail for an isotropic and homogenous plate, along with validation against the industry accepted, WaveForm Revealer 3 (WFR3) software. The results show a mean correlation across all assessed parameters of 90.4% and 96.6% for the symmetric and antisymmetric modes, respectively. Further discussion is provided on future developments to the model, including on the topic of high temperature effects, anisotropic materials and edge reflections.

A fleet of aircraft can be seen as a set of degrading systems that undergo variable loads as they fly missions and require maintenance throughout their lifetime. Optimal fleet management aims to maximise fleet availability while minimising overall maintenance costs. To achieve this goal, individual aircraft, with variable age and degradation paths, need to operate cooperatively to maintain high fleet availability while avoiding mechanical failure by scheduling preventive maintenance actions. In recent years, reinforcement learning (RL) has emerged as an effective method to optimise complex sequential decision-making problems. In this paper, an RL framework to optimise the operation and maintenance of a fleet of aircraft is developed. Three cases studies, with varying number of aircraft in the fleet, are used to demonstrate the ability of the RL policies to outperform traditional operation/maintenance strategies. As more aircraft are added to the fleet, the combinatorial explosion of the number of possible actions is identified as a main computational limitation. We conclude that the RL policy has potential to support fleet management operators and call for greater research on the application of multi-agent RL for fleet availability optimisation.