人工神经网络分光光度法同时测定钼和铬  

Simultaneous Determination of Molybdenum and Chromium by Artificial Neural Network Spectrophotometry

作　　者：吴秀红[1] 李井会[1] 高礼让[1] 高志明[1] 陈兴泮[1] 

机构地区：[1]鞍山钢铁学院应用化学系,鞍山114002

出　　处：《分析试验室》1999年第6期34-36,共3页Chinese Journal of Analysis Laboratory

摘　　要：在钼，铬－二溴邻硝基苯基荧光酮－ＣＴＭＡＢ显色体系中，应用三层ＡＮＮ－ＢＰ网络解析钼和铬的吸收光谱，不经分离分光光度法同时测定钼和铬。钼和铬的表观摩尔吸光系数分别为ε５４５＝ ６．４８×１０４Ｌ·ｍ ｏｌ－ １·ｃｍ － １，ε５４７＝ １．５４×１０４Ｌ·ｍ ｏｌ－ １·ｃｍ － １。对合成样品和合金钢中钼和铬进行了同时测定，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。In this paper, a three layer artificial neural network has been applied to the simultaneous determination of molybdenum and chromium by spectrophotometry. The conditions of color reaction of Mo(Ⅵ),Cr(Ⅵ) with dibromo o nitrophenylfluorone and cetyltrimethy lammonium bromide have been studied. The apparent molar absorptivity of the complex of molybdenum and chromium is 6 48×10 4L·mol -1 ·cm -1 and 1 54×10 4L·mol -1 ·cm -1 respectively. A method has been developed for the simultaneous determination of molybdenum and chromium in steel with satisfactory results. The paralysis in the procedure of training about ANN has been avoided with the improved backpropagation algorithms.The simple transformation method for target vectors and criterion function convenient for selection of the parameters about the netwok has been put forward.

关 键 词：神经网络 分光光度法 钼 铬 

分 类 号：O614.61[理学—无机化学] O657.320.9[理学—化学]