航空学报 > 2023, Vol. 44 Issue (S1): 727538-727538   doi: 10.7527/S1000-6893.2022.27538

空战格斗飞行机动数据库建立及应用

马金毅, 王灿, 薛涛, 艾剑良, 董一群()   

  1. 复旦大学 航空航天系,上海 200433
  • 收稿日期:2022-05-09 修回日期:2022-05-30 接受日期:2022-06-20 出版日期:2023-06-25 发布日期:2022-06-24
  • 通讯作者: 董一群 E-mail:yiqundong@fudan.edu.cn
  • 基金资助:
    上海市青年科技英才扬帆计划(20YF1402500);上海市自然科学基金(22ZR1404500)

Development and illustrative applications of an air combat engagement database

Jinyi MA, Can WANG, Tao XUE, Jianliang AI, Yiqun DONG()   

  1. Department of Aeronautics and Astronautics,Fudan University,Shanghai 200433,China
  • Received:2022-05-09 Revised:2022-05-30 Accepted:2022-06-20 Online:2023-06-25 Published:2022-06-24
  • Contact: Yiqun DONG E-mail:yiqundong@fudan.edu.cn
  • Supported by:
    Shanghai Sailing Program(20YF1402500);Natural Science Foundation of Shanghai(22ZR1404500)

摘要:

空战格斗任务面临环境高复杂性、博弈强对抗性、响应高实时性、信息不完整性、边界不确定性等多项挑战。为此,已建立人类飞行员空战格斗飞行机动数据库ACED(Air Combat Engagement Database),系统采集人类优秀飞行员空战格斗飞行机动数据。基于该数据库,首先分析了空战格斗飞行机动方程,提出应重点分析飞行员在空战任务中的滚转角及法向过载决策指令;研究确定了近距空战格斗任务中的人类飞行员飞行机动决策时间窗,并采用能量谱分析方法确定了飞行员在近距空战格斗飞行机动中的滚转角决策频率;针对采用航炮作为主武器的近距空战格斗任务,研究了近距空战格斗敌机轨迹预测算法。相关方法可有效预测航炮炮弹生命周期内的敌机未来轨迹,有力支撑了航炮自动火控算法的研发,助力在相关空战竞赛中取得优异成绩。本文系列应用示例验证了已建立的空战格斗飞行机动数据库的有效性。

关键词: 自主空战, 近距空战格斗, 人-机协同, 飞行机动数据库, 机器学习

Abstract:

The main challenges in autonomous air combat mission include complex environment, strong gaming, fast dynamics, insufficient information, and uncertain boundaries. Nowadays, artificial intelligence (especially human-machine collaborative intelligence) has provided a good opportunity for addressing these challenges. We thus constructed an Air Combat Engagement Database (ACED). The ACED database is currently focused on Within-Visual-Range (WVR) air combat, which allocates the flight states and controls of experienced human pilots in WVR air combat missions. Based on this database, we first investigate the flight dynamics in air combat missions, and pro-pose that we should primarily analyze the roll angle and vertical load factor for researching the human pilot decision-making. The time window of pilot decision-making in WVR air combat is also studied, and the frequency of pilots maneuvering decision-making is analyzed by energy spectrum method. Moreover, the enemy aircraft trajectory prediction algorithm in WVR air combat is studied, the optimal key parameters of the algorithm are obtained for the trajectory prediction of different types of enemy aircraft. These illustrative applications verify the database established in this paper.

Key words: autonomous air combat, within-visual-range, human-machine collaboration, air combat engagement database, machine learning

中图分类号: