针对紫外分光光度法（UV法）检测混有干扰物质的硝酸盐氮溶液浓度精度不高的问题，提出一种基于主成分分析（principal component analysis，PCA）和BP神经网络的硝酸盐氮浓度检测方法。通过微型光谱仪物质成分检测系统测得硝酸盐氮试剂在196 nm～631 nm波段的吸光度数据，分为测试集和训练集。通过PCA计算训练集，得到主成分。根据BP算法搭建三层人工神经网络。将所得主成分除以8后输入网络展开训练。训练过程中采用留一法交叉验证。用该模型计算训练集和测试集，所得值与真实浓度的平均相对误差分别为2.411 5%和1.553%。实验结果表明，该方法能较好检测出混有干扰物质的硝酸盐氮溶液浓度。
Abstract
Aiming at the problem of inaccurate detection of the nitrate nitrogen solution concentration with interfering substances in ultraviolet spectrophotometry (UV method), a nitrate nitrogen concentration detection method based on principal component analysis (PCA) and BP neural network was proposed. First, the absorbance of the nitrate nitrogen reagent at 196 nm~631 nm was measured by the material composition detection system of the micro-spectrometer, which was divided into test set and training set. Then, the PCA was used to calculate the training set to obtain the principal components. Finally, a three-layer artificial neural network was built based on the BP algorithm. The obtained principal components were divided by 8 and input into the network for training. During the training, the leaving-one method was adopted for cross-validation. This model was used to calculate the training set and test set, the mean relative error between the obtained results and the true concentration is 2.411 5% and 1.553% respectively. The experimental results show that the method can better detect the concentration of the nitrate nitrogen reagent with interfering substances.
关键词
浓度 /
神经网络 /
主成分分析 /
硝酸盐氮 /
光谱分析
{{custom_keyword}} /
Key words
concentration /
spectral analysis /
nitrate nitrogen /
neural network /
principal component analysis
{{custom_keyword}} /
基金
浙江省属高校基本科研业务费专项资金资助（RF-C2019001）；浙江省教育厅一般科研项目（GZ18571030014）；浙江省重点研发计划(2019C01007)
{{custom_fund}}
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
张亚丽, 张依章, 张远, 等. 浑河流域地表水和地下水氮污染特征研究[J]. 中国环境科学,2014,34(1):170-177.
国家环境保护总局. SL84-1994 水质硝酸盐氮的测定紫外分光光度法[S]. 北京: 中国标准出版, 2007.
宋哥, 孙波, 教剑英. 测定土壤硝态氮的紫外分光光度法语其他方法的比较[J]. 土壤学报,2007,44(2):288-293.
杨鹏程. 紫外吸收光谱结合偏最小二乘法海水硝酸盐测量技术研究[D]. 天津: 国家海洋技术中心, 2013.
刘思乡, 范卫华, 郭慧, 等. 机器学习在紫外法测定硝酸盐氮浓度中的应用[J]. 光谱学与光谱分析,2017,37(4):1179-1182.
俞禄, 王雪洁, 明倩, 等. 几种建模方法在光谱水质分析中的应用和比较[C]. 烟台: 中国自动化学会控制理论专业委员会B卷, 2011: 5227-5230.
王雷, 乔晓艳, 张姝, 等. 基于BP神经网络的荧光光谱法农药残留检测[J]. 应用光学,2010,31(3):442-446.
李婵, 万晓霞, 谢伟
ZHANG Yali, ZHANG Yizhang, ZHANG Yuan, et al. Characteristics of nitrate in surface water and groundwater in the Hun River Basin[J]. China Environmental Science,2014,34(1):170-177.
State Environment Protection Administration.SL84-1994 Water quality-determination of nitrate-nitrogen-ultraviolet spectrophotometry[S]. Beijing: Chinese Standard Publishing, 2007.
SONG Ge, SUN Bo, JIAO Jianying. Comparison between ultraviolet spectrophotometry and other methods in determination of soil Nitrate-N[J]. Acta Pedologica Sinica,2007,44(2):288-293.
YANG Pengcheng. Research on determination of nitrate in seawater based on ultraviolet spectra combined with PLS method[D]. Tianjin: National Ocean Technology Center, 2013.
LIU Sixiang, FAN Weihua, GUO Hui, et al. Application of machine learning in determination of nitrate nitrogen based on ultraviolet spectrophotometry[J]. Spectroscopy and Spectral Analysis,2017,37(4):1179-1182.
YU Lu. WANG Xuejie, MING Qian, et al. Application and comparison of several mo
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
