论文部分内容阅读
雷达抗干扰性能评估是雷达系统研制、引进、装备过程中必要的环节.如何综合评估复杂电磁环境下的雷达抗干扰性能评估已成为研究的重点.针对现有雷达抗干扰性能评估方法的特点和局限性,提出了一种基于粗糙集-自适应神经网络模糊推理系统(RS-ANFIS)的性能评估方法.首先,针对原始样本数据的不完备性和不确定性,采用粗糙集理论对原始样本数据进行数据归一化、离散化、属性约简处理,并得到覆盖原始样本特征的最小规则集.其次,建立了基于ANFIS的Sugeno型性能评估模型,设计了评估变量的隶属度函数和推理规则,确定了评估网络各层输入输出关系以及网络学习算法.最后,以12组雷达抗干扰性能评估指标为例进行算法模型验证,表明了方法的可行性和模型的有效性.实验结果表明,该方法能够有效改进网络结构,提高雷达抗干扰性能评估结果的可信度.
Radar anti-jamming performance evaluation is necessary for the development, introduction and equipment of radar system.How to evaluate radar anti-jamming performance in complex electromagnetic environment has become the focus of research.According to the characteristics of the existing radar anti-jamming performance evaluation method and This paper proposes a performance evaluation method based on RS-ANFIS (fuzzy inference system based on rough set theory and adaptive neural network) .Firstly, according to the incompleteness and uncertainty of the original sample data, the rough set theory is applied to the original sample Data were normalized, discretized and attribute reduction, and the minimum rule set covering the characteristics of the original samples was obtained.Secondly, a Sugeno performance evaluation model based on ANFIS was established, and the membership functions and inference rules Finally, the 12-group radar anti-jamming performance evaluation index is taken as an example to verify the algorithm model, which shows the feasibility of the method and the validity of the model.The experimental results show that the The method can effectively improve the network structure and improve the credibility of the radar anti-jamming performance evaluation results.