基于区间数和证据理论的雷达辐射源参数识别

针对雷达辐射源参数的不确定性，研究区间类型的雷达辐射源参数识别，构造区间参数的雷达辐射源数据库。首先，利用区间数距离形成区间相似度并基于此构造一种切合实际的基本概率赋值（basic probability assignment, BPA）。再将其与证据理论结合形成辐射源识别的信度区间，利用证据组合规则对信度区间进行区间重组。最后进行自适应判决识别，得到识别结果。仿真结果表明，区间证据理论方法能够较好的处理区间类型以及区间值和标量值混合类型的辐射源参数，得到满意的识别结果，具有一定实际意义。

Radar emitter parameter recognition based on interval number and evidence theory

To solve the uncertainty of radar emitter recognition, interval parameters are researched, and a radar emitter database is constructed with interval parameters. Interval similarity is formed by calculating the distance between the intervals, based on which a more facial basic probability assignment (BPA). Then the reliability interval of the emitters is introduced based on evidence theory and BPA, and reliability interval is restructured by evidence combination rules. In the end, the recognition results is obtained by adaptive classification. Simulation results show that the interval evidence theory can deal with both the interval parameters and the scalar mixed with interval parameters well, a satisfactory recognition results are obtained, which is of practical.