| 摘要: |
| 针对当前无源雷达目标识别存在的识别率低和容错性不足等问题，构建了一个基于BP神经网络的目标识别模型。围绕无源雷达目标识别效率提升和智能解决方案的构设问题，梳理总结了神经元原理、常用神经网络结构、激活函数和学习算法，设计了无源雷达目标识别总体流程，具体构建了神经网络目标识别模型，包括网络结构、隐含层节点数确定等，并给出了样本训练、测试和目标识别的工作流程，为无源雷达目标识别提供了方法途径。最后，给出了一个仿真实例，验证了模型的有效性。 |
| 关键词: 无源雷达 目标识别 神经网络 BP网络 模型构建 智能识别 |
| DOI：DOI:10.3969/j.issn.1672-2337.2019.05.014 |
| 分类号:TN958.97 |
| 基金项目: |
|
| Building of Neural Networks Model for Target Recognition of Passive Radar |
|
LIN Meiqing，CAI Yi
|
|
1.Department of Aerospace Early Warning，Air Force Early Warning Academy，Wuhan 430019，China;2.Teaching and Research Support Center，Air Force Early Warning Academy，Wuhan 430019，China
|
| Abstract: |
| According to the problems of target recognition of passive radar which currently have low recognition rate and lack of fault tolerance，a target recognition model based on BP neural network is established. Around the promotion of target recognition efficiency and construction of smart solutions of passive radar，neuron principle，frequently used neural network architecture，activation function and learning algorithm are summarized. Then target recognition overall workflow of passive radar is designed，and target recognition model based on neural networks is also established in some detail,which include network structure，ascertain of node number of hidden layer and so on,and the work flow of the sample training，testing and target recognition are provided，which supply the methods and ways for target recognition of passive radar. Finally，an example is provided，and the model is validated. |
| Key words: passive radar target recognition neural networks BP neural network model building intelligent identification |
