近红外光谱结合ELM快速检测固态发酵过程参数pH值

pH值是固态发酵过程关键参数之一,为此提出基于近红外光谱技术的秸秆蛋白饲料固态发酵过程参数pH值检测方法。利用近红外光谱系统获取140个固态发酵过程产物样本在10 000～4 000cm-1范围内的近红外光谱数据,通过酸度计测得近红外光谱预测模型的参考测量值;运用ELM算法建立pH值的预测模型,在模型建立过程中由交互验证法确定最佳主成分因子数和ELM网络隐含层节点数。试验结果显示:最佳ELM网络模型的拓扑结构为10-40-1,模型预测集相关系数(Rp)和预测均方根误差(RMSEP)分别为0.961 8和0.104 4。研究结果可为固态发酵过程参数的在线检测提供技术基础。

Determination of process variable pH in solid-state fermentation by FT-NIR spectroscopy and extreme learning machine (ELM)

Fourier transform near-infrared (FT-NIR) spectroscopy was attempted to determine pH, which is one of the key process parameters in solid-state fermentation of crop straws. First, near infrared spectra of 140 solid-state fermented product samples were obtained by near infrared spectroscopy system in the wavelength range of 10 000-4 000 cm(-1), and then the reference measurement results of pH were achieved by pH meter. Thereafter, the extreme learning machine (ELM) was employed to calibrate model. In the calibration model, the optimal number of PCs and the optimal number of hidden-layer nodes of ELM network were determined by the cross-validation. Experimental results showed that the optimal ELM model was achieved with 1040-1 topology construction as follows: R(p) = 0.961 8 and RMSEP = 0.104 4 in the prediction set. The research achievement could provide technological basis for the on-line measurement of the process parameters in solid-state fermentation.