人工神经网络近红外光谱法用于粉末药品扑热息痛的非破坏定量分析

Nondestructive Quantitative Analysis of Paracetamoli Powder Pharmaceutical by Artificial Neural Network and Near Infrared Spectroscopy

研究了应用人工神经网络进行粉末药品的非破坏定量分析。使用扑热息痛粉末药品的近红外漫反射光谱数据建立人工神经网络模型 ,预测未知样品。讨论了影响网络的各参数。采用逼近度作为网络新的评价标准。由于人工神经网络好的非线性的多变量校正特点 ,预测结果是准确的。

The application of artificial neural network for pharmaceutical nondestructive quantitative analysis were investigated. Real data set from near infrared reflectance spectra of Paracetamoli powder pharmaceutical were used to build up artificial network to predict unknown samples. The parameters affecting network were discussed. A new network evaluation criterion, the degree of approximation, was employed. Owing to good nonlinear multivariate calibration nature of ANN, the predicted results was reliable.