节点文献

人工神经网络吸光光度法同时测定钛锆

SIMULTANEOUS DETERMINATION OF TITANIUM AND ZIRCONIUM BY ARTIFICIAL NEURAL NETWORKS ABSORPTIOPHOTOMETRY

  • 推荐 CAJ下载
  • PDF下载
  • 不支持迅雷等下载工具,请取消加速工具后下载。

【作者】 高礼让高志明吴秀红李井会孙海容曾庆山

【Author】 Gao Lirang, Gao Zhiming, Wu Xiuhong, Li Jinghui, Sun Hairong and Zeng Qingshan(Department of Applied Chemistry, Anshan Institute of Iron & Steel Technology, Anshan 114002)

【机构】 鞍山钢铁学院应用化学系鞍山钢铁学院应用化学系 鞍山114002鞍山114002

【摘要】 在钛,锆-二溴羟基苯基荧光酮-CTMAB显色体系中,应用三层ANN—BP网络解析钛和锆的吸收光谱,不经分离吸光光度法同时测定钛和锆。钛和锆的表观摩尔吸光系数分别为ε547=9.66×104533=1.80×105。同时测定合金钢中钛和锆,结果满意。使用改进的BP算法,避免了神经网络学习过程中可能产生的麻痹现象。提出了目标向量的简单变换方法及便于网络参数选择的收敛评价函数。

【Abstract】 It is reported in this paper, a three-layer artificial neural networks was applied to the simultaneous determination of titanium and zirconium by absorptiophotometry. The optimum conditions of the color reactions of Ti( Ⅵ ), Zr( Ⅵ ) with dibromo-hydrophenylfluorone in the presence of CTMAB was studied. The apparent molar absorptivity of the complex of titanium and zirconium are 9.66×104L·mol-1·cm-1 and 1.80×105L·mol-1 ·cm-1respectively, A method was developed for simultaneous determination of titanium and zirconium in steel with satisfactory results. The paralysis in the procedure of training about ANN was avoided with the improved backpropagation algorithms. The simple transformation method for target vectors and criterion function convenient for selection of the parameters about the netwoks was put forward.

  • 【文献出处】 理化检验(化学分册) ,Physical Testing and Chemical Analysis Partb Chemical Analgsis , 编辑部邮箱 ,1999年02期
  • 【分类号】O657.3
  • 【被引频次】5
  • 【下载频次】44
节点文献中: 

本文链接的文献网络图示:

本文的引文网络