基于BP神经网络的n/γ甄别方法研究

常用的有机闪烁体探测器对中子和γ射线均敏感，所以消除或减弱γ射线在中子探测技术中的影响是必要的。考虑到BP神经网络能实现分类器的功能，因此本文结合脉冲形状甄别技术与BP神经网络，将BP神经网络应用在中子与γ射线混合场的粒子甄别中。通过训练BP神经网络达到记忆、分类测试样本的目的。对BP神经网络应用于n/γ脉冲波形甄别的准确性进行验证后与电荷比较法及频域梯度分析法甄别结果进行了对比。结果表明，BP神经网络甄别法不仅能为混合辐射场提供有效的甄别，而且在甄别时间上较电荷比较法与频域梯度分析法有所提高。

Study on n/γ Discrimination Method Based on BP Neural Network

The commonly used scintillator detectors are sensitive to neutrons and gamma rays, so it is necessary to eliminate or weaken the influence of gamma ray in neutron detection technology. BP neural network can realize the function of classifier. In this paper, BP neural network combining pulse shape discrimination technology was applied to particle discrimination in neutron and gamma ray mixed field. The purpose of memorizing and classifying test samples was achieved by training BP neural network. The accuracy of BP neural network in the discrimination of n/γ pulse waveform was verified and compared with the discrimination result of charge comparison method and frequency gradient analysis method. The results show that the discrimination method based on BP neural network can not only provide effective screening for mixed radiation field, but also improve the discrimination time compared with charge comparison method and frequency gradient analysis method.