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.