Abstract Fatty acid value is one of the important indexes to judge wheat flour quality during storage. A portable near-infrared (NIR) spectroscopy system was developed established for the quantitative detection of fatty acids in wheat flour during storage. First, the portable NIR spectroscopy system was used to obtain the spectra of wheat flour in different storage periods, and the spectra acquired were corrected by standard normal variate (SNV) method. Then, variable combination population analysis (VCPA) was used to optimize the characteristic wavelength variables of the SNV corrected spectra, and the characteristic wavelength variables highly related to the fatty acid value were determined. Finally, extreme learning machine (ELM) was employed to construct quantitative detection models based on different characteristic wavelength variables to achieve quantitative detection of fatty acid value. In the process, the effects of the “Sigmoidal” and “Sine” activation functions on the performance of the ELM model were compared. The experimental results showed that in this study, the two activation functions have little effect on the generalization performance of the ELM model. The ELM models based on different input characteristic wavelength variables all showed good prediction accuracy and stability when predicting independent samples in the validation set, and the mean of R P 2 from the ELM model in each mode was above 0.96. The overall results demonstrate that it is feasible to use the portable NIR spectroscopy system built combined with appropriate chemometric methods to achieve quantitative determination of fatty acid values in wheat flour during storage. In addition, the VCPA algorithm has a good application prospect in the optimization of NIR spectral characteristic wavelengths.

中文翻译：

---

基于便携式近红外（NIR）光谱系统的小麦粉贮藏过程中脂肪酸值的定量检测

摘要 脂肪酸值是判断小麦粉贮藏质量的重要指标之一。建立了一种便携式近红外（NIR）光谱系统，用于小麦粉贮藏过程中脂肪酸的定量检测。首先，利用便携式近红外光谱系统获取小麦粉不同贮藏期的光谱，并用标准正态变量（SNV）法对获得的光谱进行校正。然后，使用可变组合种群分析（VCPA）对SNV校正光谱的特征波长变量进行优化，确定与脂肪酸值高度相关的特征波长变量。最后，采用极限学习机（ELM）构建基于不同特征波长变量的定量检测模型，实现脂肪酸值的定量检测。在此过程中，比较了“Sigmoidal”和“Sine”激活函数对ELM模型性能的影响。实验结果表明，在本研究中，两个激活函数对ELM模型的泛化性能影响不大。基于不同输入特征波长变量的ELM模型在预测验证集中的独立样本时均表现出良好的预测精度和稳定性，各模式下ELM模型的RP 2 均值均在0.96以上。总体结果表明，利用构建的便携式近红外光谱系统结合适当的化学计量学方法实现小麦粉储存过程中脂肪酸值的定量测定是可行的。此外，VCPA算法在近红外光谱特征波长的优化方面具有很好的应用前景。