基于光谱预处理结合遗传算法优化波长的面粉水分快速检测

基于光谱预处理及遗传算法(genetic algorithm,GA)法优化波长,再结合偏最小二乘(partial least squares,PLS)法建立面粉中水分的定量分析模型,对比在不同预处理方法下相关系数R~2、校正标准差(root mean square error of calibration,RMSEC)、预测标准偏差(root mean square error of prediction,RMSEP)3个指标,随机选择130份样本建立预处理+GA+PLS定量分析模型,实验结果为R~2从0.955 2提高到0.977 7、RMSEC从0.375 8降低到0.245 3、RMSEP从0.268降低到0.264。结果表明基于光谱预处理结合GA优化波长来定量分析面粉中水分含量是可行的,且准确性和误差度皆优于无优化模型。

Fast Detection of Flour Moisture through Spectral Data Pretreatment and Genetic Algorithm-Based Wavelength Selection

A near infrared (NIR) spectroscopic model for the quantitation of flour moisture was developed using partial least squares regression (PLSR). Infrared spectra of 130 randomly selected samples were used to establish PLSR models employing different spectral pretreatments combined with wavelength selection using genetic algorithm (GA). The correlation coefficient (R2), root mean square error of calibration (RMSEC) and root mean square error of prediction (RMSEP) of the optimized model were 0.977 7, 0.245 3 and 0.264, which were respectively higher, lower and lower than those of the unoptimized one. Thus tt is feasible to establish a quantitative model for estimating flour moisture by spectral data pretreatment and GA-based wavelength selection which had better accuracy and lower errors than the unoptimized one.