近红外光谱技术结合支持向量回归法测定嘧菌酯的含量

Determination of the content of azoxystrobin by near-infrared spectroscopy and support vector regression

摘要: 采用近红外光谱(NIR)技术结合支持向量回归法(SVR)建立了乳油中嘧菌酯的定量分析方法。通过向25%苯醚甲环唑乳油中加入嘧菌酯原药和乙酸乙酯,配制不同浓度的校正集,采用SVR法建立了嘧菌酯的定量分析模型,得模型的决定系数(R2)、校正集均方根误差(RMSEC)、检验集均方根误差(RMSEV)、预测集均方根误差(RMSEP)分别为0.999 7、0.000 9、0.000 9和0.001 7。结果表明,近红外光谱技术结合支持向量回归法可以准确地定量分析乳油中嘧菌酯的含量,方法简单、快捷,在农药市场质量快速监测中具有实际应用价值。

Abstract: The method of rapid determination of the content of azoxystrobin in EC was established by near-infrared spectroscopy (NIR),combined with support vector regression (SVR).The calibration set was composed of samples with different content of azoxystrobin by adding azoxystrobin TC and ethyl acetate to difenoconazole 250 EC.The determination coefficient (R2), root mean squared error of calibration(RMSEC),root mean squared error of validation(RMSEV),and root mean squared error of prediction(RMSEP) for the model established by SVR for the content of active ingredient azoxystrobin were 0.999 7,0.000 9,0.000 9 and 0.001 7 respectively.The results showed that the method of NIR combined with SVR is convenient and quickly and can be used to accurately quantitative analysis of the content of azoxystrobin in EC.