论文部分内容阅读
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ε_(547)=9.66×10~4,ε_(533)=1.80×10~5。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。
In titanium and zirconium dibromohydroxyphenylfluorone-CTMAB color system, three layers of ANN-BP network were used to analyze the absorption spectra of titanium and zirconium, and titanium and zirconium were simultaneously determined without separation and absorption spectrophotometry. The apparent molar absorptivities of titanium and zirconium are ε 547 = 9.66 × 10 4 and ε 533 = 1.80 × 10 5, respectively. Simultaneous determination of titanium and zirconium alloy steel, the results were satisfactory. Using the improved BP algorithm, the possible paralysis phenomenon in neural network learning can be avoided. A simple transformation method of target vector and convergence evaluation function which is convenient for network parameter selection are proposed.