基于神经网络与似然比决策理论相结合的雷达型号识别研究

A Study on Radar Type Recognition Based on the Combination of ANN and Likelihood Ratio Theory

提出了一种数据融合中雷达型号的识别模型。将人工神经网络、模糊匹配和似然比决策理论有效地结合起来用神经网络进行粗分类,识别出雷达的体制;用模糊匹配识别出该体制下的雷达型号;并用似然比决策理论对不同空域和时域的数据进行融合。实验结果表明:该模型可以提高数据融合中的雷达型号识别率和可靠性,显示了强噪声环境下良好的应用前景。

The model for radar type recognition in data fusion is put forward in the paper.ANN is used to recognize radar system,fuzzy matching method is used to recognize radar type,and likelihood ratio theory is used to fuse the data in the different space and time field.These three methods are combined effectively in the paper.The result of recognition illuminates that this model can efficiently improve the recognition rate,the reliability and the ability of fault tolerance in the strong noise environment.