基于PSO的神经网络在分光光度法同时测定As(Ⅲ)和As(Ⅴ)中的应用  

Application of Neural Network Based on PSO in Simultaneously Analyzing As(Ⅲ) and As(Ⅴ) Using Spectrophotometer Analysis

作　　者：程迪[1] 于洁[1] 

机构地区：[1]新乡医学院化学教研室,河南新乡453003

出　　处：《新乡学院学报》2009年第2期57-59,共3页Journal of Xinxiang University

摘　　要：针对干扰严重的两组分体系——As(Ⅲ)和As(Ⅴ)难以利用分光光度法实现同时测定的问题,采用粒子群优化算法训练多层前向神经网络权值,有效地克服了传统反向传播算法误差收敛速度慢、易陷入局部极小值的缺点。结果表明,基于PSO的神经网络方法显著增强了数据处理的准确性和稳定性。A neural network based on Particle Swarm Optimization （PSO） is adopted to solve the problem of simulta- neously analyzing As（ ⅢI and As（ Ⅴ ） using Speetrophotometer Analysis. The weights of multi-layer forward neural network are trained by the PSO algorithm, which overcomes the disadvantages of error converging slowly and dropping into the local minimum inhering in traditional Back Propagation （BP） neural network. And the results show that the method improves the accuracy and stability of data processing greatly.

关 键 词：分光光度法 PSO 神经网络 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]