小麦质量指标可见/近红外光谱动态检测方法研究

本文通过动态采集小麦的可见/近红外漫反射光谱(600～1 600 nm),结合偏最小二乘法(PLS)和BP神经网络(BP-ANN)建模方法建立小麦的蛋白质、水分、湿面筋、硬度指数的定量预测模型,利用决定系数(R2)、均方根误差(RMSE)和验证集标准偏差与预测标准偏差的比值(RPD)作为评价指标进行验证,比较分析了 3...

Prediction of Wheat Key Quality Parameters by Visible/Near Infrared Spectroscopy Under Dynamic Condition

The dynamic near infrared spectra of wheat were obtained by diffuse reflectance method(600-1600nm),The regression models of protein, moisture, wet gluten and hardness index of wheat were established by partial least squares (PLS) and BP neural network (BP-ANN),The coefficient of determination (R_²), root mean square error of cross validation and Ratio of Standard Deviation of the Validation set to Standard Error of Prediction(RPD)were used as evaluation indexes to verify the PLS model,At the same time, the influence of four different training algorithms on the BP-ANN model is analyzed and compared. Although the two different modeling methods are different, they have achieved good prediction results.The results show that different pretreatment methods can effectively improve the test results, and the deep learning method can effectively improve the prediction accuracy of water content and hardness index.It is proved that the dynamic spectrum model is feasible, and it has a certain reference value for near infrared on-line detection technology.