School of Agricultural Equipment Engineering, Jiangsu University, Zhenjiang 212013, PR China; School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, PR China.
School of Electrical and Information Engineering, Jiangsu University, Zhenjiang 212013, PR China.
Spectrochim Acta A Mol Biomol Spectrosc. 2018 Nov 5;204:73-80. doi: 10.1016/j.saa.2018.06.017. Epub 2018 Jun 5.
This study aimed to investigate the potential of FT-NIR spectroscopy technique combined with chemometrics method, which employed to monitor time-related changes of alcohol concentration and residual glucose during solid state fermentation (SSF) of ethanol. Characteristic wavelength variables were firstly selected by use of L1-norm regularization approach. Then, the partial least squares (PLS) regression model was finally developed using the variables selected by L1-norm regularization method to quantitative determine alcohol concentration and residual glucose in SSF of ethanol. Compared with the best results of full-spectrum PLS, the L1-PLS model obtained better results as follows: RMSECV = 1.0392 g/L, R = 0.9911, RMSEP = 1.0910 g/L, R = 0.9917 for alcohol concentration; RMSECV = 1.7002 g/L, R = 0.9880, RMSEP = 2.1859 g/L, R = 0.9896 for residual glucose. The overall results sufficiently demonstrate that FT-NIR spectroscopy technique coupled with appropriate chemometrics method is a promising tool for monitoring the process of SSF of ethanol.
本研究旨在探讨傅里叶变换近红外（FT-NIR）光谱技术结合化学计量学方法的潜力，该方法用于监测乙醇固态发酵（SSF）过程中酒精浓度和残余葡萄糖的时间相关变化。首先采用 L1-范数正则化方法选择特征波长变量。然后，最终使用 L1-范数正则化方法选择的变量建立偏最小二乘（PLS）回归模型，以定量测定 SSF 中乙醇的酒精浓度和残余葡萄糖。与全谱 PLS 的最佳结果相比，L1-PLS 模型得到了更好的结果：酒精浓度的 RMSECV=1.0392 g/L，R=0.9911，RMSEP=1.0910 g/L，R=0.9917；残余葡萄糖的 RMSECV=1.7002 g/L，R=0.9880，RMSEP=2.1859 g/L，R=0.9896。总体结果充分证明，FT-NIR 光谱技术结合适当的化学计量学方法是监测 SSF 乙醇过程的一种很有前途的工具。
