摘要
利用近红外光谱分析结合偏最小二乘法测定甲苯、氯苯和正庚烷构成的三元混合体系中氯苯的浓度。通过考察混合物吸光度与氯苯浓度的相关性,以预测残差平方和为评价指标,对光谱进行了变量筛选,并将选择的33个波长变量建立的定量校正模型与全谱范围的校正模型进行比较。结果表明本方法可使最终所得的模型中变量数大大减少,通过波长变量优选最小化冗余信息、提高预测精度及建模效率。
chlorobenzene concentration in ternary mixture of chlorobenzene,methylbenzene and heptane was determined by near infrared(NIR) spectroscopy combined with partial least square(PLS).By calculate the correlation coefficient between chlorobenzene concentration and absorbency of the mixture,feature selection was performed according as root mean square(RMS) and 10 variables were selected and used to build quantitative calibration model.comparing with the model constructed with full spectral region,the proposed va...
出处
《生命科学仪器》
2009年第9期-,共3页
Life Science Instruments
基金
国家自然科学基金(20975039)资助项目
关键词
近红外光谱
偏最小二乘
变量筛选
校正模型
Near-infrared
partial least square
variable selection
calibration model
