This paper constructs a reinforcement learning framework based on the PPO algorithm for drone air combat to solve 1v1 pursuit-evasion in 2D beyond-visual-range air combat. Firstly, the mission scenario is modeled, defining key roles of ATA and AA. Then, state transition models of pursuer and evader are built based on flight kinematics. To handle reward sparsity in policy network training, a dense reward function combining distance and angle rewards is designed to guide the agent in learning tail-chasing and interception strategies. Using the Actor-Critic architecture, deep neural networks implement the decision-making and evaluation modules. The PPO algorithm trains the pursuing drone in a simulation. Results show that after ~5 million steps, the agent learns a stable strategy, completing tasks promptly and generalizing well in unseen scenarios. This research offers ideas for drone combat and guidance, and supports autonomous decision-making in complex air battles.

Yu, Kangjie, Gong, Zheng, Hu, Runchang, Liu, Huixiang

Load Analysis of Flap and Slat Actuators in Aircraft High-Lift Systems

2026-99-1802

To be published on 07/17/2026

This study develops an end-to-end load analysis scheme for flap and slat actuators, which comprise the aircraft’s high-lift system, and the analysis results are directly integrated into hardware optimization. Because they shoulder heavy responsibilities during the takeoff and landing phases, whether they can remain rock-solid under complex aerodynamic conditions or even remain unmoved in emergencies is directly related to their overall safety performance. This work process is closely linked and includes three major links. First of all, according to the CCAR-25.301 standard, the load envelope under normal working conditions is sorted out, and the limit cases of abnormal faults are exhausted. Subsequently, ANSYS Workbench pulled silk and peeled off the cocoons to capture the peak stress at the engagement between the output shaft and the gear. In the end, the closed-loop verification of the customized test bench made the theoretical calculations and the hardware-measured data exactly the

Xu, Yuanze

Aerodynamic Optimization Method Based on a Hierarchical Adaptive Activation Function Neural Network

2026-99-1823

To be published on 07/17/2026

Efficient optimization of aerodynamic shapes is a critical challenge in aircraft design. Traditional CFD-based optimization workflows suffer from high computational costs and low efficiency, which severely restricts their practical engineering application. In this paper, a novel aerodynamic optimization method based on a hierarchical neural network with adaptive activation functions is proposed. The network adopts learnable B-spline activation functions and is hierarchically constructed in accordance with the sharing status of B-spline control points. After being trained to achieve fast and accurate prediction of aerodynamic performance, the network can effectively replace the traditional CFD module in the optimization loop. The primary advantage of the proposed method is that it significantly reduces the computational cost during the optimization process while ensuring that the prediction accuracy is not compromised. This work thereby presents a novel strategy and technical framework

Liu, Di, Wang, Yongfeng, Wen, Hong, Wei, Yuanhang, Ma, Hengwei, Zhao, Runhui

A Mode Code Configuration Method for Remote Terminals in 1553B Bus Systems

2026-99-1826

To be published on 07/17/2026

Requirements of Interface for Aircraft/Store Electrical Interconnection System (GJB 1188A-99) is the current standard followed by all types of carrier aircraft and stores. This paper designed a 1553B bus remote terminal mode code configuration method that met the requirements of GJB1188A standard, completing the interrupt initialization and data initialization of compulsory mode codes. These comprehensive test results confirm that the proposed mode code configuration method is both reliable and effective, and provides strong portability, which can be used as a reference for the GJB1188A interface software design of other components

Han, Bin, Zhang, Kun, Liu, Xuhan, Ye, Jinhan, Li, Zhengmao

Study on Resistance and Surface Pressure Characteristics of UUVs Navigating in the Pycnocline

2026-99-1807

To be published on 07/17/2026

kε

Zhang, Yin, Xue, Leilei, Guo, Liqiang, Fu, Xiao, Zhang, Xiaofang, Liu, Zhihao, Han, Guoxin

On-orbit Computing Framework for LEO Satellites Based on MADDPG and Lyapunov Optimization

2026-99-1811

To be published on 07/17/2026

This paper solves the problem of resource and energy constraints on orbit computing for LEO satellites. By combining MADDPG reinforcement learning and Lyapunov optimization, the paper proposes a computing framework and implements an adaptive task offloading model for space flight using a multi-agent deep actor critic algorithm, MADDPG. The joint optimization mechanism is implemented by multi-agent dynamic task offloading. Through the transformation from the state with long-term constraints into optimization of the status of queue stability, the load scheduling under threshold energy in accordance with the characteristics of energy constraints was realized by introducing Lyapunov virtual queues into the process of policy evaluation of deep reinforcement learning. The experimental results show that the proposed framework enables a lightweight preliminary calculation, balanced energy consumption to reduce resource allocation, and realizes the stable queues through adaptability of tasks

Yan, Ming, Zhao, Liang, Xu, Lexi, Zhou, Xiaofei, Hawbani, Ammar, Sun, Yunhe

Key Technologies of Aircraft Flight Test Based on Structural Control

2026-99-1825

To be published on 07/17/2026

A comprehensive solution integrating advanced sensor technology, structural dynamics models, and intelligent control algorithms is proposed to address the shortcomings of traditional flight testing techniques in monitoring and controlling aircraft structures under complex flight conditions. By establishing precise aircraft structural dynamic equations through fiber optic sensors, an accurate description of the dynamic characteristics of the aircraft structure can be achieved. A distributed structural monitoring system is constructed through FBG to monitor the physical quantities, such as strain and temperature, of key parts of the aircraft in real time during flight testing. Based on the real-time monitoring data, the structural state of the aircraft can be predicted, and the structural response can be actively adjusted by controlling the actuator. The experimental results show that this technology system effectively improves the accuracy of structural monitoring and the effectiveness

Gao, Sheng

Items per page:

1 – 50 of 58410