摘要
在能量色散X荧光分析(EDXRF)技术中,受均匀效应、颗粒效应和基体效应等的干扰,定量分析精度受到影响。本文针对这一问题提出了遗传算法(GA)优化BP神经网络(GA-BP)的混合算法,该算法无需考虑元素浓度和射线强度之间的复杂关系。遗传算法优化BP神经网络的目的是为了获得更好的网络初始权值和阈值,其基本思想是:将初始化的BP神经网络均方根误差的倒数编码为遗传算法中个体的适应度;初始的权值和阈值用遗传算法中的个体代替,然后通过选择、交叉和变异操作挑选出最优个体,最后通过解码用最优的权值和阈值创建一个新的BP网络模型。攀枝花矿区5类矿样中钛和铁含量的整体预测和分类预测实验表明,分类预测效果远好于整体预测。预测值与化学分析值比较结果表明,其中76.7%的样品相对误差小于2%,表明了该方法在元素间基体效应校正上的有效性。
The quantitative elemental content analysis is difficult due to the uniform effect ,particle effect and the element matrix effect ,etc ,w hen using energy dispersive X‐ray fluorescence （EDXRF ） technique .In this paper ,a hybrid approach of genetic algorithm （GA ） and back propagation （BP ） neural network was proposed without considering the complex relationship between the concentration and intensity .The aim＆amp;nbsp;of GA optimized BP was to get better network initial weights and thresholds .The basic idea was that the reciprocal of the mean square error of the initialization BP neural network was set as the fitness value of the individual in GA ,and the initial weights and thresholds were replaced by individuals ,and then the optimal individual was sought by selection ,crossover and mutation operations ,finally a new BP neural network model was created with the optimal initial weights and thresholds .The calculation results of quantitative analysis of titanium and iron contents for five types of ore bodies in Panzhi‐hua Mine show that the results of classification prediction are far better than that of overall forecasting ,and relative errors of 76.7% samples are less than 2% compared with chemical analysis values ,which demonstrates the effectiveness of the proposed method .
出处
《原子能科学技术》
EI
CAS
CSCD
北大核心
2015年第6期1143-1148,共6页
Atomic Energy Science and Technology
基金
国家杰出青年科学基金资助项目(41025015)
国家自然科学基金资助项目(41274109)
四川省青年科技创新研究团队资助项目(2011JTD001)
四川省科技支撑计划资助项目(2013FZ0022)
