基于BP神经网络检测面粉中滑石粉含量的研究

Rapid Determination of Talc-containing Flour Based on BP Neural Network

利用近红外光谱技术对掺杂滑石粉的小麦面粉进行了检测,采用多元散射校正对谱图进行预处理,利用BP神经网络中的SCG反向传播算法训练函数建立了面粉中滑石粉的定量分析模型,并对校正集和预测集进行了定量分析,分析结果为R2=0.997 3,RMSEC=0.436 7,RMSEP=1.708 8.结果表明,BP神经网络结合近红外光谱技术检测面粉中滑石粉含量具有快速、精度高、泛华能力强的优点,可用于面粉中滑石粉含量的快速准确检测.

Near infrared spectral technology （NIR） was used to test talc-containing spectrum was preprocessed with muhiplicative scatter correction. The quantitative anal wheat flour. The ysis model of talc containing flour was built using SCG back propagation algorithm training function of BP neural network, and the calibration set and prediction set were quantitatively analyzed. R2 was 0. 997 3, the root mean square error of calibration （RMSEC） was 0. 436 7, and the root mean square error of prediction （ RM- SEP） was 1. 708 8. The results showed that BP neural network with NIR for the determination of talc-con- taining flour has the advantages of fast, high precision, and the ability of Fanhua, and can be used for talc-containing flour.