基于注意力机制改进的LSTM空战目标意图识别方法

空战对抗过程中的目标状态数据呈现时序性、多维性等特征, 为进一步提升目标意图识别的准确率, 提出了一种基于改进注意力机制的长短期记忆网络(LSTM)目标识别方法, 将空战可能出现的目标意图识别当成一个多分类问题处理。该方法首先通过目标实时的状态数据, 生成特征序列; 接着采用注意力机制提升目标的特征学习能力, 增强空战过程中的主要目标状态特征表示, 得到具有权值分配的特征向量; 最后利用LSTM网络对目标特征向量进行训练, 通过softmax层实现目标意图的识别。仿真实验表明, 该方法利用注意力机制有效增强目标的特征学习, 进一步提升了LSTM网络的识别精度, 具有一定的科学性和有效性。

Abstract

The target state data in the process of air combat confrontation presents the characteristics of time sequence and multi-dimensionality.In order to further improve the accuracy of target intention recognition, an LSTM target recognition method based on improved attention mechanism is proposed, and the target intention recognition that may occur in air combat is treated as a multi-classification problem.Firstly, the feature sequence is generated by the real-time state data of the target.Then, the attention mechanism is used to improve the feature learning ability of the target, enhance the state feature representation of the main target in the air combat process, and obtain the feature vector with weight allocation.Finally, the LSTM network is used to train the target feature vector, and the target intention is recognized through the softmax layer.The simulation results show that the proposed method effectively enhances the feature learning to the target by using the attention mechanism, and further improves the recognition accuracy of the LSTM network, which is scientific and effective.

参考文献

[1] 夏曦.基于模板匹配的目标意图识别方法研究［D］.长沙:国防科学技术大学,2006.

[2] 冷画屏,吴晓锋,胡剑光,等.海上目标战术意图序贯识别技术研究［J］.系统工程与电子技术,2008, 30(3):462-465.

[3] 宋元,章新华,郭徽东.空中目标战术意图层次推理框架及实现［J］.指挥控制与仿真,2005(5):67-70.

[4] 朱波,方立恭,张小东.基于贝叶斯网络的空中目标意图识别方法［J］.现代防御技术,2012, 40(2):117-121.

[5] 陈霞.基于贝叶斯网络的防空目标攻击意图评估［J］.舰船电子工程,2014, 34(6):52-55.

[6] 陈浩,任卿龙,滑艺,等.基于模糊神经网络的海面目标战术意图识别［J］.系统工程与电子技术,2016, 38(3):1847-1853.

[7] WANG L, LI S Z.Tactical intention recognition of aerial target based on XGBoost decision tree［J］.Journal of Measurement Science and Instrumentation, 2018, 9(2):148-152.

[8] 欧微,柳少军,贺筱媛,等.基于时序特征编码的目标战术意图识别算法［J］.指挥控制与仿真,2016, 38(6):36-41.

[9] 周旺旺,姚佩阳,张杰勇,等.基于深度神经网络的空中目标作战意图识别［J］.航空学报,2018, 39(11):322468-322476.

[10] 尹翔,张萌,陈梦乔.基于判别分析的空中作战意图识别［J］.弹箭与制导学报,2018, 30(3):46-50.

[11] 黄安祥,雷祥,苏玉强,等.空战作战环境仿真设计［M］.北京:国防工业出版社,2017:11-15.

[12] 徐建平,张立凡,韩德强.基于模糊推理的空中目标意图识别［J］.指挥信息系统与技术,2020, 11(3):44-48.

[13] ZHOU T L, CHEN M, WANG H Y, et al.Information entropy-based intention prediction of aerial targets under uncertain and incomplete information［J］.Entropy, 2020, 22(3):279.

[14] HOCHREITER S, SCHMIDHUBER J.Long short-term memory［J］.Neural Computation, 1997, 9(8):1735-1780.

[15] LAROCHELLE H, HINTON G.Le-arning to combine foveal glimpses with a third-order Boltzmann machine［C］//Proceedings of the 23rd International Conference on Neural Information Processing Sy-stems.New York: Curran Associates Inc., 2010:1243-1251.

[16] DENIL M, BAZZANI L, LAROCHELLE H, et al.Learning where to attend with deep architectures for image tracking［J］.Neural Computation, 2012, 24(8):2151-2184.

[17] MNIH V, HEESS N, GRAVES A, et al.Recurrent models of visual attention［R］.Los Alamos: arXiv Preprint, 2014:arXiv:1406.6247.

[18] BAHDANAU D, CHO K, BENGIO Y.Neural machine translation by jo-intly learning to align and translate［R］.Los Alamos: arXiv Preprint, 2014: arXiv:1409.0473.

[19] XU K, BA J L, KIROS R, et al.Show, attend and tell:neural image caption generation with visual attention［C］//Proceedings of the 32nd International Conference on Machine Learning.Lille:JMLR, 2015:2048-2057.

[20] 陈优敏,李长云.基于知识图谱的目标战术意图识别仿真［J］.计算机仿真,2019, 36(8):1-4, 19.

李战武, 李双庆, 彭明毓, 江涛, 鞠明, 孙爱民. 基于注意力机制改进的LSTM空战目标意图识别方法[J]. 电光与控制, 2023, 30(3): 1. 李战武, 李双庆, 彭明毓, 江涛, 鞠明, 孙爱民. An Air Combat Target Intention Recognition Method Based on LSTM Improved by Attention Mechanism[J]. Electronics Optics & Control, 2023, 30(3): 1.

基于注意力机制改进的LSTM空战目标意图识别方法

关于本站 Cookie 的使用提示

全站搜索

基于注意力机制改进的LSTM空战目标意图识别方法

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索