基于BP神经网络的诱发铀部件裂变信号特征分析及识别  

Feature Analysis and Recognition of Induced Uranium Components Fission Signal Based on BP Neural Network

作　　者：谢军华[1] 刘知贵[2] 任立学[3] 张活力[4] 

机构地区：[1]西南科技大学计算机科学与技术学院,四川绵阳621010 [2]西南科技大学信息工程学院,四川绵阳621010 [3]西南科技大学国防科技学院,四川绵阳621010 [4]西南科技大学学生处,四川绵阳621010

出　　处：《原子核物理评论》2012年第2期202-207,共6页Nuclear Physics Review

基　　金：国家自然科学基金重点项目(11176031)~~

摘　　要：在对诱发铀部件裂变信号的测量原理及特点分析的基础上,开展了基于BP神经网络的诱发铀部件裂变时间关联信号特征参量分析处理的研究工作。采用无偏估计方法,计算信号的自相关函数和互相关函数,再利用比较法和导数法两种特征量提取方法,提取出不同状态下裂变信号的特征参量,借助于BP神经网络模式识别应用原理进行训练和预测。理论分析和研究结果表明:基于比较法和导数法获得的特征参量能较好地反映诱发铀部件裂变信号的特征;用BP神经网络对裂变信号进行模式识别,取得了较高的正确率,验证了此方法的有效性和合理性。The paper presents feature parameter analysis and processing in fission time-dependent signal of induced uranium components based on BP-Neural Networks through the analysis of the measuring princi- ple and signal characteristics of induced uranium components fission signal. The auto correlation functions and cross correlation functions are calculated by using unbiased estimate, and then the feature parameters of fission signal in different status are extracted by using feature abstraction method, comparative method and derivative method, and then applied to training and prediction by means of BP-neural networks based on pattern recognition. Theoretical analysis and the results show that, it is effective to obtain feature pa- rameters of induced uranium component fission signal via comparative method and derivative method. Using BP neural network to tiveness and reasonability of recognize patter of fission signal, we got good results that verified the effec the method.

关 键 词：铀部件 BP神经网络 特征提取 模式识别 

分 类 号：TL816[核科学技术—核技术及应用]