连续凸逼近加权自相关波形优化方法  

Weighted autocorrelation waveform optimization design based on successive convex approximation

作　　者：张勇 宋青青 ZHANG Yong;SONG Qing-qing(Nanjing 6902 Science&Technology Co.,Ltd.,Nanjing 210009;The Eighth Research Academy of CSSC,Nanjing 211153)

机构地区：[1]南京六九零二科技有限公司,南京210009 [2]中国船舶集团有限公司第八研究院,南京211153

出　　处：《雷达与对抗》2023年第3期7-12,23,共7页Radar & ECM

摘　　要：针对雷达系统对距离向干扰抑制的需求,提出一种基于连续凸逼近的加权自相关恒模波形设计方法。由于原始问题的目标函数为不定二次型,无法直接求解,通过构造目标函数的上边界函数并对其最小化,获得原最小化优化问题的等效形式。同时,对非凸的恒模约束进行松弛处理,构建易于求解的凸优化模型。在此模型基础上,利用成熟优化工具对凸问题进行求解,并对最优解的幅度强制归一化得到恒模序列。通过数值仿真,将连续凸逼近算法与现有算法进行比较,验证了所提算法的可行性和快速收敛性。Weighted autocorrelation constant modulus waveform is designed based on successive convex approximation in response to the radar system's demand for range interference suppression.Since the objective function of the original problem is of indefinite quadratic form,it cannot be solved directly.The equivalent form of the original minimization optimization problem is obtained by constructing the upper boundary function of the objective function and minimizing it,and at the same time,the non-convex constant modulus constraints are relaxed to build an easily-solved convex optimization model.On this basis,a sophisticated optimization tool is used to solve the convex problem,and the constant modulus sequence is obtained by forced normalization of the magnitude of the optimal solution.The continuous convex approximation algorithm is compared with existing algorithms through numerical simulation to verify the feasibility and fast convergence of the algorithm proposed.

关 键 词：波形设计 上边界函数 凸优化 

分 类 号：TN959.72[电子电信—信号与信息处理]