论文部分内容阅读
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 the molybdenum, chromium-dibromo-o-nitrophenylfluorone-CTMAB color system, the absorption spectrum of molybdenum and chromium was analyzed by the three-layer ANN-BP network and the molybdenum and chromium were simultaneously determined without separation spectrophotometry. The apparent molar absorptivities of molybdenum and chromium are respectively ε545 = 6.48 × 104L · mol-1 · cm-1 and ε547 = 1.54 × 104L · mol-1 · cm-1. Simultaneous determination of molybdenum and chromium in the synthesized samples and alloy steels showed satisfactory results. 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.