欢迎访问《兵工学报》官方网站,今天是 分享到:

兵工学报 ›› 2022, Vol. 43 ›› Issue (8): 1913-1925.doi: 10.12382/bgxb.2021.0417

• 论文 • 上一篇    下一篇

基于机动单元库的TSO-GRU-Ada机动轨迹预测

唐上钦1, 魏政磊2, 谢磊1, 周欢1, 张卓然3   

  1. (1.空军工程大学 航空工程学院, 陕西 西安 710038;2.中国空气动力研究与发展中心, 四川 绵阳 621000;3.93184部队, 北京 100000)
  • 上线日期:2022-07-29
  • 作者简介:唐上钦(1984—),男,讲师,博士。E-mail:630909448@qq.com
  • 基金资助:
    陕西省自然科学基金项目(2020JQ-481、2021JM-223);航空科学基金项目(201951096002)

TSO-GRU-Ada Maneuver Trajectory Prediction Based on Maneuver Unit Library

TANG Shangqin1, WEI Zhenglei2, XIE Lei1, ZHOU Huan1, ZHANG Zhuoran3   

  1. (1.Aeronautics Engineering College, Air Force Engineering University, Xi'an 710038, Shaanxi, China;2.China Aerodynamics Research & Development Center, Mianyang 621000, Sichuan, China;3.Unit 93184 of PLA, Beijing 100000, China)
  • Online:2022-07-29

摘要: 机动轨迹预测是自主空战中的一个重要组成部分。针对无人战斗机机动轨迹预测精度低且时耗过长的问题,提出一种基于机动单元库的自适应集成三角优化门控循环神经网络预测方法。建立无人战斗机3自由度模型,解决轨迹数据来源问题;通过4种轨迹特征,将轨迹分为平面机动、空间左转弯机动和空间右转弯机动三类,构建21种基本机动单元;介绍门控循环神经网络,为避免网络梯度优化陷入局部最优,引入三角搜索优化算法更新网络内部权值和偏置。为提高预测精度,采用自适应增强算法构建强预测器;通过实验选取预测器最优参数,在不同机动单元情况下进行预测,预测精度较高且均能满足时耗要求;为检验在机动轨迹上的预测性能,从空战训练测量仪中选取一段轨迹,与5种不同预测模型进行对比。研究结果表明,所提模型的预测精度最佳。

关键词: 轨迹预测, 基本机动单元, 门控循环神经网络, 三角搜索优化算法, 自适应增强算法

Abstract: Maneuver trajectory prediction is an important part of autonomous air combat. To deal with the problem of low accuracy and time-consuming prediction of Unmanned Combat Aerial Vehicle (UCAV) maneuver trajectory, a prediction model based on the gated recurrent neural network with adaptive boosting algorithm integrated with triangle optimization is proposed. Firstly, a three-degree-of-freedom model of the UCAV is established to solve the trajectory data source problem. Secondly, through the four trajectory characteristics, the trajectories are divided into three categories, namely, planar maneuver, spatial left-turning maneuver and spatial right-turning maneuver, and 21 basic maneuver units are constructed. Then the gated recurrent neural network is explained. To prvent the network gradient optimization from falling into the local optimum, the triangle search optimization algorithm is introduced to update the internal weights and biases of the network. At the same time, to improve the prediction accuracy, the adaptive boosting algorithm is used to build a strong predictor. The optimal parameters of the predictor are selected through experiments, and the predictions are made under different maneuver units. The prediction results have high accuracy and all of them can meet the time consumption requirements. Finally, to test the prediction performance for the maneuver trajectory, a trajectory is selected from the Air Combat Maneuvering Instrument, and compared with results from five different prediction models. The results show that the proposed method has the best prediction accuracy.

Key words: trajectoryprediction, basicmaneuverunit, gatedrecurrentneuralnetwork, trianglesearchoptimizationalgorithm, adaptiveboostingalgorithm

中图分类号: