基于自适应网络模糊推理系统的γ能谱指纹模糊识别  

Fuzzy identification of γ ray fingerprints based on adaptive network-based fuzzy inference system

作　　者：王崇杰[1] 刘媛媛[1] 张博超[1] 张倩妮[1] 刘金艳[1] 金鸽[1] 张敏[1] 

机构地区：[1]辽宁师范大学物理与电子技术学院,大连116029

出　　处：《物理学报》2014年第12期125-131,共7页Acta Physica Sinica

基　　金：国家自然科学基金(批准号:51101080;E011002)资助的课题~~

摘　　要：提出了以自适应网络模糊推理系统参数为识别特征的γ能谱指纹模糊识别方法.通过建模和仿真,提取了γ能谱指纹的模糊系统特征参数,并建立了关于系统特征参数的模糊集及模糊识别原则,以较高的置信度实现了γ能谱指纹的类型识别和个体识别.对实测γ能谱指纹进行了识别,对方法的识别性能进行了研究和探讨.研究表明,该方法不但具有较强的类型识别能力和个体识别能力,并具有较低的识别下限和较强的抗噪声能力.An identification method of γ-ray fingerprints based on adaptive network-based fuzzy inference system is brought forward. By setting up model and performing simulation, the parameters of the system relevant to theγ-ray fingerprints are extracted as the identification features. The two-dimensional fuzzy set about the identification features is put forward, and the fundamental principle for identification is established. The types and the individuals of nuclear materials are identified successfully with high degree of confidence. The simulation materials as radiation sources are identified with the method, and the performance of the method is studied and discussed. The results show that the method has not only strong capabilities for identifying the types and the individuals of the radiation sources, but also strong de-noising capability and low identification limit, and it can be applied to the nuclear materials safeguard.

关 键 词：γ能谱指纹 自适应网络模糊推理系统 模糊集 模糊识别 

分 类 号：TP18[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]