雷达目标识别中的BP神经网络算法改进及应用  

Improvements and applications of BP neural network algorithmin radar target recognition

作　　者：张静[1] 宋锐[1] 郁文贤[1] 

机构地区：[1]国防科学技术大学ATR重点实验室,湖南长沙410073

出　　处：《系统工程与电子技术》2005年第4期582-585,共4页Systems Engineering and Electronics

基　　金："十五"国防预研基金资助课题

摘　　要：针对雷达目标信号的复杂性和实用雷达目标识别系统所应具备的稳健性、扩展性及通用性等要求,提出多种简单有效的BP神经网络算法改进。通过平衡训练样本数量、动态重置初始权值、评定网络规模等措施,解决了BP算法收敛速度慢、受初始样本分布影响大等缺陷,提高了识别算法的稳健性和泛化能力。结果已成功应用到不同型号雷达上的多套目标识别系统中。According to the complexity of radar target signals and the robustness, extensibility and generality requirements of practical radar target recognition systems, several effective improvements are made for the BP neural network algorithm. By balancing the training samples, dynamically resetting initial weights and adaptively evaluating net scales, some shortcomings of the BP algorithm, such as low convergence speed and high dependency on initial sample distribution are overcome, and the algorithm has become more robust and generic. The method has been applied in several recognition systems of some models of radar. Test and application results show that proposed algorithm is effective and practical.

关 键 词：BP神经网络 算法改进 雷达目标识别 应用 目标识别系统 目标信号 样本数量 初始权值 网络规模 收敛速度 BP算法 分布影响 泛化能力 识别算法 长期使用 稳健性 复杂性 通用性 扩展性 实用性 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TP391.41[自动化与计算机技术—控制科学与工程]