【摘要】 应用神经网络解析NO₃^-和NO₂^-的吸收光谱,不经分离紫外吸光光度法同时测定NO₃^-和NO₂^-。在经典BP的算法上,引用改进的误差传递函数,对学习系数和动量因子进行了动态调节,并采用均匀试验设计法确定最佳网络运行参数,建立了改进的BP算法。此法用于水样中NO₃^-和NO₂^-的同时测定,回收率分别为100.8％和95.3％。更多还原

【Abstract】 An artificial neural network was applied to simultaneous determination of nitrate and nitrite by ultraviolet spectrophotometry without separately. On the basis of the classic BP algorithm, the transfer function was improved , and the learning rate and momentum factor were adaptively adjusted . The best parameters were detemined by uniform design . The improved BP algorithm was applied to the determination of nitrate and nitrite in the water sample with satisfactory results.The mean recoveries are 100.8% and 95.3% for NO3- and NO2- (n = 5) respectively.更多还原