摘要
为了快速测定工业废水中的铬和铁,利用BP人工神经网络模型,并与分光光度法相结合,不经分离同时测定工业废水中的铬和铁。在铬-铁-二苯碳酰二肼显色体系中,控制pH在1.0-2.0之间,用分光光度法测定显色体系的吸收光谱,应用三层人工神经网络解析吸收光谱,同时测得铬和铁的浓度。详细研究了分光光度法同时测定铬和铁的测定条件和网络训练的最佳训练参数,BP人工神经网络的动量参数为0.8,拓扑结构为20-15-2,转换函数的形状参数为0.9。该测定方法不仅可用于环境监测,而且能用于食品、材料、药物、生物样品、矿物等物质中铬和铁的测定。
In order to test quickly chromium and iron in industrial wastewater, a model of BP artificial neural network and spectrophotometry are combined to simultaneously test chromium and iron in industrial wastewater, which need not separate from industrial wastewater. In developed system of chromium-iron-diphenylcarbazide, absorption spectrum of chromium-iron is tested by speetrophotometry. The value of pH was controlled in 1.0～2.0 during the test process. A three-layer artificial neural network is applied to simultaneously determine concentrations of chromium and iron. The simultaneous determination condition of chromium-iron by spectrophotometry and the best training parameter of network was stadied. The momentum of BP artificial neural network is 0.8, the topology is 20 - 15 - 2, and the transfer parameter was 0.9. This method is the one of effective components analysis methods. It can he used in not only environmental monitoring, but also testing chromium and iron in food, material, medicament, biologic sample, mineral and so on.
出处
《化学研究与应用》
CAS
CSCD
北大核心
2006年第11期1283-1287,共5页
Chemical Research and Application
基金
四川省科学技术厅应用基础研究基金资助项目(04JY029-001-5)
关键词
人工神经网络
分光光度法
铬
铁
artificial neural network
speetrophotometry
chromium and iron
