High-resolution Range Profile Target Recognition Based on IGWO-1DCNN

doi:10.12382/bgxb.2024.1119

Abstract

Abstract:

The high resolution range profile (HRRP) is predominantly applied in the field of radar target recognition because of providing the detailed information of target features.The traditional radar HRRP recognition method of ballistic midcourse targets is affected by the environmental noise interference,atmospheric radiation and penetration strategies,resulting in low target recognition accuracy.Furthermore,the intelligent optimization algorithm faces the challenge of an extensive number of parameters when extracting the local features of a target,which makes it difficult to perform manual parameter adjustment.Aiming at this issue,a high-resolution range profile recognition method based on the improved grey wolf optimizer and one-dimensional convolutional neural network (IGWO-1DCNN) is proposed for ballistic targets.An improved 1D convolutional neural network is constructed for the feature extraction from HRRP samples of wideband radar targets.The improved grey wolf optimizer (IGWO) algorithm is introduced to accelerate the convergence speed and recognition performance of the model.The support vector machine (SVM) is used as the classifier to facilitate the recognition processes.The experimental results demonstrate that the proposed method is capable of accurately identifying the ballistic targets,automatically optimizing the parameters of neural network,and reducing the burden of manual training and exhibiting higher robustness.

Key words: radar target recognition, high-resolution range profile, 1D convolutional neural network, grey wolf algorithm

CLC Number:

TN957.52

CHEN Shibao, HAN Jiaxuan, ZHANG Huiwen, WU Yida, WANG Caiyun. High-resolution Range Profile Target Recognition Based on IGWO-1DCNN[J]. Acta Armamentarii, 2025, 46(11): 241119-.

Figures/Tables 11

References 20

[1]	LIN C L, CHEN T P, FAN K C, et al. Radar high-resolution range profile ship recognition using two-channel convolutional neural networks concatenated with bidirectional long short-term memory[J]. Remote Sensing, 2021, 13(7):1259. doi: 10.3390/rs13071259 URL
[2]	陈士超, 魏靖彪, 范俊, 等. 基于判别性无穷模糊受限玻尔兹曼机模型的HRRP序列识别[J]. 兵工学报, 2024, 45(增刊1):43-50.
	CHEN S C, WEI J B, FAN J, et al. Research on HRRP sequences recognition based on discriminative infinite fuzzy restricted boltzmann machine model[J]. Acta Armamentarii, 2024, 45(S1):43-50. (in Chinese) doi: 10.12382/bgxb.2024.0552
[3]	云涛, 潘泉, 郝宇航, 等. 基于HRRP时频特征和多尺度非对称卷积神经网络的目标识别算法[J]. 西北工业大学学报, 2023, 41(3):537-545.
	YUN T, PAN Q, HAO Y H, et al. Target recognition algorithm based on HRRP time-spectrogram feature and multi-scale asymmetric convolutional neural network[J]. Journal of Northwestern Polytechnical University, 2023, 41(3):537-545. (in Chinese) doi: 10.1051/jnwpu/20234130537 URL
[4]	孙晶明, 虞盛康, 孙俊. 基于深度学习的HRRP识别姿态敏感性分析[J]. 系统工程与电子技术, 2022, 44(3):802-807. doi: 10.12305/j.issn.1001-506X.2022.03.12
	SUN J M, YU S K, SUN J. Pose sensitivity analysis of HRRP recognition based on deep learning[J]. Systems Engineering and Electronics, 2022, 44(3):802-807. (in Chinese) doi: 10.12305/j.issn.1001-506X.2022.03.12
[5]	秦尉博, 张弓, 刘苏, 等. 基于TGAF特征和卷积神经网络的雷达一维距离像识别[J]. 电子测量技术, 2020, 43(15):53-57.
	QIN W B, ZHANG G, LU S, et al. HRRP target recognition based on triple gramian angular field with convolutional neural network[J]. Electronic Measurement Technology, 2020, 43(15):53-57. (in Chinese)
[6]	李璐, 李泽宇, 冯超. 基于一维卷积神经网络的HRRP雷达目标分类方法[J]. 火控雷达技术, 2023, 52(4):143-147.
	LI L, LI Z Y, FENG C. A radar target HRRP classification method based on one-dimensional convolutional neural network[J]. Fire Control Radar Technology, 2023, 52(4):143-147. (in Chinese)
[7]	李月琴, 张红莉, 张维, 等. 基于改进CNN的HRRP目标识别方法[J]. 兵器装备工程学报, 2022, 43(8):265-274.
	LI Y Q, ZHANG H L, ZHANG W, et al. Radar HRRP target recognition based on improved CNN[J]. Journal of Ordnance Equipment Engineering, 2022, 43(8):265-274. (in Chinese)
[8]	赵东波, 李辉. 基于中心矩特征和GA-BP神经网络的雷达目标识别[J]. 红外与激光工程, 2018, 47(8):394-400.
	ZHAO D B, LI H. Radar target recognition based on central moment feature and GA-BP neural network[J]. Infrared and Laser Engineering, 2018, 47(8):394-400. (in Chinese)
[9]	何隆玲, 胡桂明, 李维维, 等. 基于PSO-RBF神经网络的雷达目标识别[J]. 现代防御技术, 2014, 42(5):115-120.
	HE L L, HU G M, LI W W, et al. Radar target recognition based on PSO-RBF neural network[J]. Modern Defence Technology, 2014, 42(5):115-120. (in Chinese)
[10]	程志友, 姜帅, 胡杰, 等. 基于改进PSO对卷积层核数量优化的电能质量扰动分类[J]. 电工电能新技术, 2023, 42(11):40-49. doi: 10.12067/ATEEE2209031
	CHENG Z Y, JIANG S, HU J, et al. Classification of power quality disturbances based on improved PSO to optimize the number of convolution cores[J]. Advanced Technology of Electrical Engineering and Energy, 2023, 42(11):40-49. (in Chinese) doi: 10.12067/ATEEE2209031
[11]	程杰, 陈鼎, 李春, 等. 基于GWO-CNN-BiLSTM的超短期风电预测[J]. 科学技术与工程, 2023, 23(35):15091-15099.
	CHENG J, CHEN D, LI C, et al. Ultra-short-term wind power prediction based on GWO-CNN-BiLSTM[J]. Science Technology and Engineering, 2023, 23(35):15091-15099. (in Chinese)
[12]	WANG W L, YANG R F, GUO C X, et al. CNN-based hybrid optimization for anomaly detection of rudder system[J]. IEEE Access, 2021, 9:121845-121858. doi: 10.1109/ACCESS.2021.3109630 URL
[13]	董光德, 李道明, 陈咏涛, 等. 基于粒子群优化与卷积神经网络的电能质量扰动分类方法[J]. 发电技术, 2023, 44(1):136-142. doi: 10.12096/j.2096-4528.pgt.22004
	DONG G D, Ll D M, CHEN Y T, et al. Power quality disturbance classification method based on particleswarm optimization and convolutional neural network[J]. Power Generation Technology, 2023, 44(1):136-142. (in Chinese)
[14]	王朝阳. 基于一维卷积神经网络的旋转机械故障诊断关键技术研究[D]. 沈阳: 东北大学, 2020.
	WANG Z Y. Research on key technology of rotating machinery fault diagnosis based on one-dimensional convolutional neural network[D]. Shenyang: Northeastern University, 2020. (in Chinese)
[15]	ZAMFIRACHE I A, PRECUP R E, ROMAN R C, et al. Policy iteration reinforcement learning-based control using a grey wolf optimizer algorithm[J]. Information Sciences, 2022, 585:162-175. doi: 10.1016/j.ins.2021.11.051 URL
[16]	张娜, 赵泽丹, 包晓安, 等. 基于改进的Tent混沌万有引力搜索算法[J]. 控制与决策, 2020, 35(4):893-900.
	ZHANG N, ZHAO Z D, BAO X A, et al. Gravitational search algorithm based on improved Tent chaos[J]. Control and Decision, 2020, 35(4):893-900. (in Chinese)
[17]	LI S T, LI J H. Chaotic dung beetle optimization algorithm based on adaptive t-distribution[C]// Proceedings of the 2023 IEEE 3rd International Conference on Information Technology,Big Data and Artificial Intelligence.Chongqing,China:IEEE, 2023, 3:925-933.
[18]	SINGH H, KOMMURI S V R, KUMAR A, et al. A new technique for guided filter-based image denoising using modified cuckoo search optimization[J]. Expert Systems with Applications, 2021, 176:114884. doi: 10.1016/j.eswa.2021.114884 URL
[19]	LIN C R, CAO Z C, ZHOU M C. Learning-based cuckoo search algorithm to schedule a flexible job shop with sequencing flexibility[J]. IEEE Transactions on Cybernetics, 2023, 53(10):6663-6675. doi: 10.1109/TCYB.2022.3210228 URL
[20]	蔺美青, 蔡轶. 无源雷达目标识别的神经网络模型构建[J]. 雷达科学与技术, 2019, 17(5):557-563.
	LIN M Q, CAl Y. Building of neural networks model for target recognition of passive radar[J]. Radar Science and Technology, 2019, 17(5):557-563. (in Chinese)

目标	自旋频率/Hz	进动频率/Hz	进动角/(°)	章动频率/Hz	章动角/(°)	翻滚频率/Hz	翻滚角/(°)
真弹头	1.5	2:0.5:4	3:0.375:4.5
有缝球底锥	3.0	2.5:0.5:4.5	5:0.375:6.5	1.0	2
平底锥	2.0	1.5:0.5:3.5	4:0.375:5.5	0.5	1
椭球						2:1:6	70:5:90
助推器						4:1:8	70:5:90

目标	自旋频率/Hz	进动频率/Hz	进动角/(°)	章动频率/Hz	章动角/(°)	翻滚频率/Hz	翻滚角/(°)
真弹头	1.5	2:0.5:4	3:0.375:4.5
有缝球底锥	3.0	2.5:0.5:4.5	5:0.375:6.5	1.0	2
平底锥	2.0	1.5:0.5:3.5	4:0.375:5.5	0.5	1
椭球						2:1:6	70:5:90
助推器						4:1:8	70:5:90

函数	计算公式	搜索范围
Sphere	$f\left(x\right)=\sum _{i=1}^{n}{x}_{i}^{2}$	[-100,100]
Schwefel’s Problem 1.2	$f\left(x\right)=\sum _{i=1}^{n}{\left(\sum _{j=1}^{i}{x}_{j}\right)}^{2}$	[-100,100]

函数	计算公式	搜索范围
Sphere	$f\left(x\right)=\sum _{i=1}^{n}{x}_{i}^{2}$	[-100,100]
Schwefel’s Problem 1.2	$f\left(x\right)=\sum _{i=1}^{n}{\left(\sum _{j=1}^{i}{x}_{j}\right)}^{2}$	[-100,100]

分类模型	识别准确率/%
KNN	73.51
IGWO-KNN	78.86
SVM	79.00
IGWO-SVM	84.10
LSTM	75.42
IGWO-LSTM	85.92